
% David MacKay's BibTeX file
% .bib entries in Information Theory and Machine Learning
%

	@string{nips = {Advances in Neural Information Processing Systems}}
@string{springer = {Springer-Verlag}}

@BOOK{latex,
   author = "Leslie Lamport",
   title = "{\LaTeX \rm:} {A} Document Preparation System",
   publisher = "Addison-Wesley",
   year = 1986 }

%%%%%%% MacKay publications %%%%%%%%%%%%%%%%%%%

% online papers that need adding to this list and putting in their abstracts 
% delve
% distance
% cpi4
% advance
% gbm
% gene

@ARTICLE{MacKay92a,
 AUTHOR		="MacKay, D. J. C.",
 TITLE		="{B}ayesian Interpolation",
 JOURNAL	="Neural Computation",
 YEAR		="1992",
 VOLUME		="4",
 NUMBER		="3",
 PAGES		="415--447",
URL={http://www.inference.phy.cam.ac.uk/mackay/PhD.html},
 ANNOTE ="Date submitted: 21 May 1991; Date accepted: 29 Oct 1991;
		  Collaborating institutes: California Institute of
		  Technology"
}

@ARTICLE{MacKay92b,
 KEY		="MacKay",
 AUTHOR		="MacKay, D. J. C.",
 TITLE		="A Practical {B}ayesian Framework for Backpropagation Networks",
 JOURNAL	="Neural Computation",
 YEAR		="1992",
 VOLUME		="4",
 NUMBER		="3",
 PAGES		="448--472",
 ANNOTE ="Date submitted: 21 May 1991; Date accepted: 29 Oct 1991; Collaborating institutes: California Institute of Technology"}

@ARTICLE{MacKay92c,
 KEY		="MacKay",
 AUTHOR		="MacKay, D. J. C.",
 TITLE		="Information Based Objective Functions for Active
        Data Selection",
 JOURNAL	="Neural Computation",
 YEAR		="1992",
 VOLUME		="4",
 NUMBER		="4",
 PAGES		="589--603",
 ANNOTE ="Date submitted: 17 July 1991; Date accepted: 15 Nov 1991; Collaborating institutes: California Institute of Technology"}
 
@ARTICLE{MacKay92d,
 KEY		="MacKay",
 AUTHOR		="MacKay, D. J. C.",
 TITLE		="The Evidence Framework Applied to Classification Networks",
 JOURNAL	="Neural Computation",
 YEAR		="1992",
 VOLUME		="4",
 NUMBER		="5",
 PAGES		="698-714",
 ANNOTE ="Date submitted: 20 Nov 1991; Date accepted: 18 Feb 1992; Collaborating institutes: California Institute of Technology"}


@ARTICLE{MacKay95_kuipers_review,
 KEY		="MacKay",
 AUTHOR		="MacKay, D. J. C.",
 TITLE		="Book review: Qualitative Reasoning: Modeling and
		  Simulation with Incomplete Knowledge",
 JOURNAL	="Computers in Physics",
 YEAR		=1995,
 VOLUME		=9,
 NUMBER		=2,
 PAGES		=3}


@TECHREPORT{MacKay86,
 KEY		="MacKay",
 AUTHOR		="D. J. C. ~MacKay",
 TITLE		="Statistical Testing of High Precision Digitisers",
 YEAR		="1986",
 NUMBER		="3971",
 INSTITUTION	="Royal Signals and Radar Establishment, 
			Malvern, Worcester. WR14 3PS"
}
@TECHREPORT{MacKay87,
 KEY		="MacKay",
 AUTHOR		="D. J. C. MacKay",
 TITLE		="A Method of Increasing the Contextual Input to 
			Adaptive Pattern Recognition Systems",
 YEAR		="1987",
 NUMBER		="RIPR 1000/14/87",
 INSTITUTION	="Research Initiative in Pattern Recognition, 
			Royal Signals and Radar Establishment, 
			Malvern, Worcester. WR14 3PS"
}
% vfe
@INPROCEEDINGS{MacKay94:fe,
 KEY		="MacKay",
 AUTHOR		="D. J. C. MacKay",
 TITLE		="A Free Energy Minimization Framework for 
	Inference Problems in Modulo 2 Arithmetic",
 BOOKTITLE      ="Fast Software Encryption (Proceedings of 1994 K.U. Leuven Workshop on
		  Cryptographic Algorithms)",
  editor =	 "B. Preneel",
  series =	 "Lecture Notes in Computer Science Series",
  number = 	 "1008",
 YEAR		=1995,
  publisher =	 "Springer",
 PAGES		="179-195",
 ANNOTE ="Date submitted: 15 Jan 1995; Date accepted: 22 March 1995; Collaborating institutes:
		  Cambridge University Computer Laboratory"}

@ARTICLE{MacKay94:fes,
 KEY		="MacKay",
 AUTHOR		="D. J. C. MacKay",
 TITLE		="Free Energy Minimization Algorithm for Decoding
		  and Cryptanalysis",
 YEAR		=1995,
 JOURNAL="Electronics Letters",
 VOLUME =31,
 NUMBER=6,
 PAGES		="446-447",
 ANNOTE ="Date submitted: Jan 1995; Date accepted: 24 Feb 1995; Date
		  published: 16 March 1995; 
 Collaborating institutes: Cambridge University Computer Laboratory"}
% ISSN: 0013-5194

@UNPUBLISHED{mnc4pfoutdated,
  KEY		="MacKay and Neal",
  AUTHOR		="D. J. C. MacKay and R. M. Neal",
  TITLE		="Good Codes based on Very Sparse Matrices",
  YEAR		=1995,
  NOTE="Available from {\tt http://www.inference.phy.cam.ac.uk/}",
  PAGES		="",
  ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
 		  University of Toronto"}

@Article{mncEL,
  author = 	 "D. J. C. MacKay and R. M. Neal",
  title = 	 "Near {S}hannon Limit Performance of Low Density Parity
		  Check Codes",
  key =		 "MacKay and Neal",
  journal =	 "Electronics Letters",
 ISSN={ 0013-5194},
year =	 1996,
  volume =	 32,
  number =	 18,
  pages =	 "1645-1646",
  month =	 "August",
 note = {Reprinted {\em Electronics Letters}, 
                 {\bf 33}(6):457--458, March 1997},
 annoteb = {Reprinted {\em Electronics Letters}, 
                 vol 33, no 6, 13th March 1997, pp.457--458},
  annote =	 "Date submitted: Jul 12 1996; Date accepted: Aug 12
		  1996; printed 29 Aug. Collaborating institutes:
		  University of Toronto"
}
@Article{mncEL1,
  author = 	 "D. J. C. MacKay and R. M. Neal",
  title = 	 "Near {S}hannon Limit Performance of Low Density Parity
		  Check Codes",
  key =		 "MacKay and Neal",
  journal =	 "Electronics Letters",
  year =	 1996,
  volume =	 32,
  number =	 18,
  pages =	 "1645-1646",
  month =	 "August",
  annote =	 "Date submitted: Jul 12 1996; Date accepted: Aug 12
		  1996; printed 29 Aug. Collaborating institutes:
		  University of Toronto"
}
@Article{mncEL2,
  author = 	 "D. J. C. MacKay and R. M. Neal",
  title = 	 "Near {S}hannon Limit Performance of Low Density Parity
		  Check Codes",
  key =		 "MacKay and Neal",
  journal =	 "Electronics Letters",
  year =	 1997,
  volume =	 33,
  number =	 6,
  pages =	 "457-458",
  month =	 "March",
 note = {Reprinted because of printing errors in 1996},
  annote =	 "Date submitted: Jul 12 1996; Date accepted: Aug 12
		  1996; printed 29 Aug. Collaborating institutes:
		  University of Toronto"
}

% ",; Available from {\tt http://www.inference.phy.cam.ac.uk/}",
%
%  KEY		="MacKay and Neal",
%  AUTHOR		="D. J. C. MacKay and R. M. Neal",
%  TITLE		="Good Error Correcting Codes based on Very Sparse Matrices",
%  YEAR		=1996,
%  NOTE="To be submitted to IEEE transactions on Information Theory. Available from {\tt http://www.inference.phy.cam.ac.uk/}",
%  PAGES		="",
%  ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
% 		  University of Toronto"}

@article{mncN,
 AUTHOR		="D. J. C. MacKay",
 TITLE		="Good Error Correcting Codes based on Very Sparse Matrices",
 YEAR		=1999,
journal={IEEE Trans. on Info. Theory},
issn={0018-9448},
volume={45},number={2},
 PAGES		="399-431",
url={http://www.inference.phy.cam.ac.uk/mackay/abstracts/mncN.html},
 ANNOTE ="Date submitted: June 9th 1997; Date accepted: July 27th 1998;
 Collaborating institutes:
		  University of Toronto"}

@inproceedings{mncisit,
 AUTHOR		="D. J. C. MacKay",
 TITLE		="Good Error-Correcting Codes based on Very Sparse Matrices",
 YEAR		=1997,
 booktitle={Proceedings of 1997 IEEE International Symposium on Info. Theory. Ulm, Germany.},
 PAGES		="113",
 ANNOTE ="Date submitted: Sep 24 96; Date accepted: Feb 97; Collaborating institutes:
		  University of Toronto. MRAO number: "}
% mnc
@incollection{MacKay_Neal_Codes:95,
 KEY		="MacKay and Neal",
 AUTHOR		="D. J. C. MacKay and R. M. Neal",
 TITLE		="Good Codes based on Very Sparse Matrices",
  cutbooktitle =	 "Cryptography and Coding. 5th {IMA} Conf., LNCS 1025",
  booktitle =	 "Cryptography and Coding. 5th {IMA} Conf., LNCS 1025",
  publisher =	 "Springer",
address = "Berlin",
  year =	 1995,
  editor =	 "Colin Boyd",
  cutseries =	 "LNCS",
cutnumber = 	 "1025",
pages="100-111",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  University of Toronto. ISBN 3-540-60693-9"}

@article{McElieceMacKay96,
 AUTHOR		="R. J. McEliece and D. J. C. MacKay and J.-F. Cheng",
 TITLE		="Turbo Decoding as an Instance of {P}earl's `Belief Propagation' Algorithm",
 YEAR		=1998,
 journal={IEEE Journal on Selected Areas in Communications},
 ISSN={ 0733-8716},
volume={16}, number={2},
 PAGES		="140-152",
month={February},
 ANNOTE ="Date submitted: sep 27, 96; Date accepted: may 3, 97;
 Collaborating institutes:
		  Caltech; Communications Society Leonard G. Abraham Prize Paper Award"}

@inproceedings{mackayIBIS2000,
 AUTHOR		="D. J. C. MacKay",
 TITLE		="Relationships between Sparse Graph Codes",
 YEAR		=2000,
 booktitle={Proceedings of the workshop  on
 {\em Information-Based Induction Sciences (IBIS 2000), Shizuoka, Japan}},
 date={July 17-18 2000},
 PAGES		="257-264",
 publisher="IEEE IT Japan Chapter",
annote="publisher: (? -- not sure, because I can't read Japanese!)"
}


% aka Daveyphd
@PhdThesis{mcdthesis,
  author = 	 {M. C. Davey},
  title = 	 {Error-correction using Low-Density Parity-Check Codes},
type={PhD},
  school = 	 {University of Cambridge},
  year = 	 {1999},
}

@Unpublished{DMacKay_GFq,
  author =       {D. J. C. MacKay},
  title =        {Optimizing Sparse Graph Codes over {$GF(q)$}},
  note =         {Available from {\tt http://www.inference.phy.cam.ac.uk/mackay/abstracts/gfqoptimize.html}},
  year =         {2003}
}

@Unpublished{DM_LDPC_MonteCarlo,
  author =       {M. C. Davey and D. J. C. MacKay},
  title =        {Monte {C}arlo simulations of infinite low density parity check codes over {$GF(q)$}},
  note =         {Available from {\tt http://www.inference.phy.cam.ac.uk/is/papers/}},
  key =          {Davey and MacKay},
  year =         {1997}
}

%DM_LDPC_CLGFq,
@Article{DaveyMacKay96,
  author =       {M. C. Davey and D. J. C. MacKay},
  title =        {Low Density Parity Check Codes over {GF}$(q)$},
  journal =      {IEEE Communications Letters},
issn={1089-7798 },
  year =         {1998},
  key =          {Davey and MacKay},
  volume =    {2},
  number =    {6},
  pages =     {165-167},
  month =        {June},
annote={M. C. Davey was my supervised research student}
}
@InProceedings{cbj_97b0,
  Author =       {Bailer-Jones, C. A. L. and MacKay, D. J. C. and Sabin, T. J. and Withers, P. J.},
  title =        {Static and Dynamic Modelling of Materials Forging},
  booktitle =     {Ninth Australian Conf. on Neural Networks},
  year =         {1998},
  note =         {identical to cbj-97b I think},
}
@article{cbj_97b,
  Author =       {Bailer-Jones, C. A. L. and MacKay, D. J. C. and Sabin, T. J. and Withers, P. J.},
  title =        {Static and Dynamic Modelling of Materials Forging},
  booktitle =     {Ninth Australian Conf. on Neural Networks},
  volume =    {5},
  number =    {1},
journal={Australian Journal of Intelligent Information Processing Systems},
  year =         {1998},
  pages =     {10-17},
}
@InProceedings{sabin_97a,
  Author =       {Sabin, T. J. and Bailer-Jones, C. A. L. and Roberts, S. M. and MacKay, D. J. C. and Withers, P. J.},
  title =        {Modelling the Evolution of Microstructures in Cold-Worked and Annealed Aluminium Alloy},
  booktitle =    {International Conf.
on Thermomechanical Processing},
  year =         {1997},
  OPTorganization = {},
  OPTpublisher = {},
  OPTaddress =   {},
  OPTpages =     {}
}


@InProceedings{cbj_97bb,
  Author =       {Bailer-Jones, C. A. L. and Sabin, T. J. and MacKay, D. J. C. and Withers, P. J.},
  title =        {Prediction of Deformed and Annealed Microstructures
    Using {B}ayesian Neural Networks and {G}aussian
    Processes},
  booktitle =    {Australasia Pacific Forum on Intelligent Processing and
Manufacturing of Materials},
  year =         {1997},
}

@article{cbj_98a,
  Author =       {Bailer-Jones, C. A. L. and Bhadeshia, H. K. D. H. and
 MacKay, D. J. C.},
  title =        {{G}aussian    Process Modelling of Austenite Formation in Steel},
  year =         {1999},
volume={15},
pages =     {287-294},
  journal =         {Materials Science and Technology}
}

@article{Cole_etal99,
  Author =       {Cole, D. and Martin-Moran, C. and Sheard, A. G. and Bhadeshia, H. K. D. H. and
 MacKay, D. J. C.},
  title =        {Modelling Creep Rupture Strength of Ferritic Steel Welds},
  year =         {2000},
volume={5},
number={2},
pages =     {81-89},
  journal={Science and Technology of Welding and Joining},
annote=         {Submitted 3 May 1999, accepted 17 June 1999}
}

@article{Tancret_etal99,
  Author =       {Tancret, F. and Bhadeshia, H. K. D. H.  and
 MacKay, D. J. C.},
  title =        {Comparison of Artificial Neural Networks with {G}aussian    Processes to Model the Yield Strength of {N}ickel-base Superalloys},
  year =         {1999},
volume={39},
number={10},
pages =     {1020-1026},
  journal =         {ISIJ International}
}

@article{Tancret_etal00,
title={Design of new creep-resistant nickel-base superalloys for power-plant applications},
author={Tancret, F. and Bhadeshia, H. K. D. H.  and MacKay, D. J. C.},
journal={CREEP AND FRACTURE OF ENGINEERING MATERIALS AND STRUCTURES},
volume={171},
number={1},
 pages={529-536},year={2000}
}

@article{Tancret_etal03,
title={Design of a creep resistant nickel base superalloy for power plant applications. {P}art 1 -- {M}echanical properties modelling},
author={Tancret, F. and Bhadeshia, H. K. D. H.  and MacKay, D. J. C.},
journal={Materials Science and Technology},
volume={19},
month={march},
 pages={283-289},
year={2003}
}

@article{cbj_98b,
  Author =       {Bailer-Jones, C.A.L.  and
 MacKay, D. J. C. and  Withers, P.J.},
  title =        {A Recurrent Neural Network for  Modelling Dynamical Systems},
  year =         {1998},
journal = {Network: Computation in Neural Systems},
volume={9},
number={4},
pages =     {531-547},
}


@UNPUBLISHED{DaveyMacKay96old,
 KEY		="",
 AUTHOR		="M. C. Davey and D. J. C. MacKay",
 TITLE		="Good Codes over {$GF(q)$} based 
                        on Very Sparse Matrices",
 YEAR		=1997,
 NOTE="In preparation",
 PAGES		="",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}

@UNPUBLISHED{WilsonMacKay96,
 KEY		="",
 AUTHOR		="S. T. Wilson and D. J. C. MacKay",
 TITLE		="Decoding Shortened Cyclic Codes by Belief Propagation",
 YEAR		=1996,
 NOTE="In preparation",
 PAGES		="",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  none"}

@INPROCEEDINGS{Renals_MacKay,
 KEY            ="Renals and MacKay",
 AUTHOR         ="S. J. Renals and D. J. C.  MacKay",
 TITLE          ="{B}ayesian regularisation methods in a hybrid 
			{MLP}-{HMM} system", 
 BOOKTITLE      ="Proceedings of {E}urospeech 93, {B}erlin",
 YEAR           ="1993",
  pages =        {1719--1722},
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  Cambridge University Engineering Department. MRAO 1820"}
% PAGES          ="",
%	September 1993.

@INPROCEEDINGS{MM89:nips,
 KEY            ="MacKay and Miller",
 AUTHOR         ="D. J. C.  MacKay and K. D. Miller",
 TITLE          ="Analysis of {L}insker's simulations of {H}ebbian rules",
 BOOKTITLE      ="Advances in Neural Information Processing Systems II", 
 EDITOR         ="D. Touretzky",
 PAGES          ="694-701",
 YEAR           ="1989"}

@ARTICLE{MM90:nc,
 KEY            ="MacKay and Miller",
 AUTHOR         ="D. J. C.  MacKay and K. D. Miller",
 TITLE          ="Analysis of {L}insker's simulations of {H}ebbian rules",
 JOURNAL        ="Neural Computation",
 VOLUME		="2",
 NUMBER 	="2",
 PAGES          ="173-187",
 YEAR           ="1990"}

@ARTICLE{MM90:network,
 KEY            ="MacKay and Miller",
 AUTHOR         ="D. J. C.  MacKay and K. D. Miller",
 TITLE          ="Analysis of {L}insker's application of 
			{H}ebbian rules to linear networks",
 JOURNAL        ="Network",
 VOLUME		="1",
 NUMBER 	="3",
 PAGES          ="257-297",
 YEAR           ="1990"}

@ARTICLE{MM94:nc,
 KEY            ="",
 AUTHOR         ="K. D. Miller and D. J. C.  MacKay",
 TITLE          ="The role of constraints in {H}ebbian learning",
 JOURNAL        ="Neural Computation",
 VOLUME		="6",
 NUMBER 	="1",
 PAGES          ="98-124",
 YEAR           ="1994",
 ANNOTE ="Date submitted: 9 Oct 1992; Date accepted: 13 May 1993; 
                  Collaborating institutes:
		  California Institute of Technology"}
@INPROCEEDINGS{phnips,
 KEY		="Bridle, Heading and MacKay",
 AUTHOR		="J. S. Bridle and A. J. R. Heading and D. J. C.  MacKay",
 TITLE		="Unsupervised Classifiers, Mutual Information and `Phantom targets'",
 BOOKTITLE	="Advances in Neural Information Processing Systems 4",
 EDITOR		="J. E. Moody and S. J. Hanson and R. P. Lippmann",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1992",
 PAGES		="1096-1101"}

@INPROCEEDINGS{MacKay.nips4,
 KEY		="MacKay",
 AUTHOR		="D. J. C.  MacKay",
 TITLE		="Bayesian Model Comparison and Backprop Nets",
 BOOKTITLE	="Advances in Neural Information Processing Systems 4",
 EDITOR		="J. E. Moody and S. J. Hanson and R. P. Lippmann",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1992",
 PAGES		="839-846",
 url={http://www.inference.phy.cam.ac.uk/mackay/nips91.ps.gz}
}
@ARTICLE{Bhadeshia_etal95,
 AUTHOR		="Bhadeshia, H. K. D. H.  and  MacKay, D. J. C.  
                        and L. E. Svensson",
 TITLE		="Impact toughness of {C-MN} Steel Arc Welds --
		  {B}ayesian neural network analysis", 
 YEAR		="1995",
 JOURNAL = "Materials Science and Technology",
 VOLUME		="11",
number=10,
pages="1046-1051",
 ANNOTE ="Date submitted: Jul 1994; Date accepted: Sep 1994; Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@inproceedings{Jones_etal95,
 AUTHOR		="J. Jones  and		  D. J. C.  MacKay  and
            H. K. D. H. Bhadeshia",
 TITLE		="The Strength of  {N}ickel Base Superalloys -- a
 {B}ayesian Neural Network Analysis",
 YEAR = 1995,
 booktitle={Proceedings of the 5th International Symposium on Advanced
Materials, Pakistan},
 pages={659-666},
 ANNOTE ="Date submitted:  1995; Date accepted:  1995; Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@UNPUBLISHED{Jones_etal95old,
 AUTHOR		="J. Jones and J. King and H. K. D. H. Bhadeshia and
		  D. J. C.  MacKay",
 TITLE		="Modelling the Strength of {N}ickel Base
		  Superalloys",
 YEAR = 1995,
 NOTE = "3rd International Parsons Turbine Conf.",
 ANNOTE ="Date submitted:  1995; Date accepted:  1995; Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@article{Gavard_etal95,
 AUTHOR		={L. Gavard and H. K. D. H. Bhadeshia and
		  D. J. C.  MacKay and S. Suzuki},
 TITLE		={Bayesian Neural Network Model for Austenite
		  Formation in Steels},
 journal        ={Materials Science and Technology},
 vol            =12,
 pages          ={453-463},
 YEAR           = 1996,
 ANNOTE         ="Date submitted: May 1995; Date accepted: n/k 1995;
                  Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science. MRAO reprint number 1941."}

@ARTICLE{Fujii_etal96,
 AUTHOR		="H. Fujii and D. J. C.  MacKay   and H. K. D. H. Bhadeshia",
 TITLE		="{B}ayesian neural network analysis of Fatigue Crack
		  Growth Rate in {N}ickel Base Superalloys", 
 YEAR		="1996",
 JOURNAL = "ISIJ International",
 VOLUME		="36",
number=11,
pages="1373-1382",
 ANNOTE ="Date submitted: May 96; Date accepted: Sep 1996; Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@InCollection{Cool.B.M.97,
  author = 	 "T. Cool and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
  title = 	 "Modelling the Mechanical
		  Properties in the {HAZ} of Power Plant Steels {I}:
 {B}ayesian Neural Network Analysis of Proof Strength",
  booktitle =	 "Mathematical Modelling of Weld Phenomena 3",
  publisher =	 "Institute of Materials",
  editor =	 "H. Cerjak",
  series =	 "Materials Modelling Series",
  address =	 "London",
year={1997},
pages={403--442},
  annote =	 "Date submitted: 96; Date accepted: 1996; Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"
}



@Article{Cool.B.M.97b,
  author = 	 "T. Cool and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
  title = 	 "The Yield and Ultimate Tensile Strength of Steel Welds",
  journal =	 "Materials Science and Engineering A",
  year =	 1997,
  volume =	 "A223",
  pages =	 "186-200"
}

@InCollection{MacKay.weld.review.97,
  author = 	 "D. J. C.  MacKay",
  title = 	 "{B}ayesian Non-linear Modelling with Neural Networks",
  booktitle =	 "Mathematical Modelling of Weld Phenomena 3",
  publisher =	 "Institute of Materials",
  editor =	 "H. Cerjak",
  series =	 "Materials Modelling Series",
  address =	 "London",
year={1997},
pages={359--389},
  annote =	 "Date submitted: 96; Date accepted: 1996; Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"
}

@article{Takeuchi_etal94:Jap,
 AUTHOR		="R. Takeuchi and D. J. C.  MacKay 
                        and T. Matsumoto",
 TITLE		="A {B}ayesian Inference of  Hyperparameters and Regularizers
		  for Standard Regularization Problems", 
 YEAR		=1994,
 journal = "Technical report of IEICE",
 pages="", 
note="In Japanese",
 ANNOTE ="Date submitted:  1994; Date accepted:  1994; 
Collaborating institutes:
		  Waseda University, Tokyo"}

@inproceedings{Takeuchi_etal94,
 AUTHOR		="R. Takeuchi and D. J. C.  MacKay 
                        and T. Matsumoto",
 TITLE		="Determining Optimal Hyperparameters and Regularizers
		  for Standard Regularization Problems", 
 YEAR		=1994,
 booktitle = "Proceedings of 1994 International Symposium on Artificial
		  Neural Networks (ISANN-94), Tainan, Taiwan",
 pages="419-428",
 ANNOTE ="Date submitted:  1994; Date accepted:  1994; 
Collaborating institutes:
		  Waseda University, Tokyo"}



@article{MacKay_Peto,
 AUTHOR		="D. J. C.  MacKay and L. Peto",
 TITLE		="A Hierarchical {D}irichlet Language Model",
 YEAR		="1995",
 journal	="Natural Language Engineering",
 volume=1,
 number=3,
 pages="1-19",
 ANNOTE ="Date submitted: 31 March 1995; Date accepted: ; Collaborating institutes:
		  University of Toronto"}
@UNPUBLISHED{MacKay94:amino,
 AUTHOR		="D. J. C.  MacKay",
 TITLE		="Models for Dice Factories and Amino Acid Probability Vectors",
 YEAR		="1995",
 NOTE		="Unpublished",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  MRC Laboratory of Molecular Biology, Cambridge"}

@INPROCEEDINGS{MaxentCons,
 KEY		="MacKay",
 AUTHOR		="D. J. C.  MacKay",
 TITLE		="Maximum Entropy Connections{:} Neural Networks",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 YEAR		="1991",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht",
 PAGES		="237-244"
}

% modelling input dependent noise level
@INPROCEEDINGS{MacKay95:icann,
 KEY		="MacKay",
 AUTHOR		="D. J. C.  MacKay",
 TITLE		="Probabilistic Networks: New Models and New Methods",
 BOOKTITLE	="ICANN '95",
 YEAR		="1995",
 PUBLISHER	="EC2 and Cie", 
 ADDRESS	="Paris",
 PAGES		="331-337", annote={this is where I use BUGS to model
 input-dependent noise. MRAO 1927}
}

@INPROCEEDINGS{MacKay95:snn,
 KEY		="MacKay",
 AUTHOR		="D. J. C.  MacKay",
 TITLE		="Developments in Probabilistic Modelling with Neural
		  Networks -- Ensemble Learning",
 BOOKTITLE	="Neural Networks: Artificial Intelligence and
		  Industrial Applications. Proceedings of the 3rd
		  Annual Symposium on Neural Networks, Nijmegen,
		  Netherlands, 14-15 September 1995",
 YEAR		="1995",
 PUBLISHER	="Springer", 
 editors="Kappen, B. and Gielen, S.",
 ADDRESS	="Berlin",
 PAGES		="191-198", annote={MRAO 1926}
}

@INPROCEEDINGS{MacKay92am,
 KEY		="MacKay",
 AUTHOR		="D. J. C.  MacKay",
 TITLE		="{B}ayesian interpolation",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {S}eattle 1991",
 EDITOR		="C.R. Smith and G.J. Erickson and P.O. Neudorfer",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1992",
 PAGES		="39-66"}

@INPROCEEDINGS{MacKay92bm,
 KEY		="MacKay",
 AUTHOR		="D. J. C.  MacKay",
 TITLE		="The evidence for neural networks",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {S}eattle 1991",
 EDITOR		="C.R. Smith and G.J. Erickson and P.O. Neudorfer",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1992",
 PAGES		="165-183"}


@Unpublished{MacKay95:nips,
  author = 	 "D. J. C. MacKay",
  title = 	 "Ensemble Learning and Evidence Maximization",
  note = 	 "submitted to NIPS*95",
  year =	 1995,
  annote =	 "Date submitted: May 1995"
}

@Unpublished{Macphee_MacKay,
  author = 	 "K. Macphee and D. J. C. MacKay",
  title = 	 "Ensemble Learning for Hidden {M}arkov Models",
  note = 	 "in preparation",
  year =	 1996,
  annote =	 ""
}

@Unpublished{MacKay_hmm,
  author = 	 "D. J. C. MacKay",
  title = 	 "Ensemble Learning for Hidden {M}arkov Models",
  note = 	 "{\tt http://www.inference.phy.cam.ac.uk/mackay/abstracts/ensemblePaper.html}",
  year =	 1997,
  annote =	 ""
}
@Unpublished{MacKay_vfeprob,
  author = 	 "D. J. C. MacKay",
  title = 	 "A Problem with Variational Free Energy Minimization",
  note = 	 "{\tt http://www.inference.phy.cam.ac.uk/mackay/abstracts/minima.html}",
  year =	 2001,
  annote =	 ""
}
%submitted to NIPS 97",
% Available from {\tt http://www.inference.phy.cam.ac.uk/}",

@Unpublished{Gibbs_MacKay97a,
  author = 	 "M. N. Gibbs and D. J. C. MacKay",
  title = 	 "Efficient implementation of {G}aussian Processes for Interpolation",
  note = 	 "{\tt http://www.inference.phy.cam.ac.uk/mackay/abstracts/gpros.html}",
  year =	 1996,
  annote =	 ""
}

@article{Gibbs_MacKay97b,
  author = 	 "M. N. Gibbs and D. J. C. MacKay",
  title = 	 "Variational {G}aussian Process Classifiers",
  annote = 	 "{\tt http://www.inference.phy.cam.ac.uk/mackay/abstracts/vgc.html}",
journal={IEEE Trans. on Neural Networks},
volume={11},
 number={6},
  year =2000,
month={November},
pages={1458-1464},
  annote =	 "submitted 9 sep 1998"
}

@Unpublished{MacKay96:ica,
  author = 	 "D. J. C. MacKay",
  title = 	 "Maximum Likelihood and Covariant Algorithms for
		  Independent Component Analysis",
  note = 	 "{\tt http://www.inference.phy.cam.ac.uk/mackay/abstracts/ica.html}",
  year =	 1996,
  annote =	 ""
}

@article{MacKay96:laplace,
  author = 	 "D. J. C. MacKay",
  title = 	 "Choice of Basis for {Laplace} Approximation",
  journal = 	 "Machine Learning",
  year =	 1998,
volume={33},
 number={1},
 pages={77-86},
  annote =	 ""
}

@Misc{MacKay97:ipd,
  author =	 "D. J. C. MacKay",
  title =	 "Iterative Probabilistic Decoding of Low Density Parity Check Codes",
  howpublished = "Animations available on world wide web",
  year =	 1997,
  note =	 "{\tt http://www.inference.phy.cam.ac.uk/mackay/codes/gifs/}"
}


@inproceedings{WaterhouseMacKayRobinson95-nips8,
author="S. R. Waterhouse and D. J. C. MacKay and A. J. Robinson",
title="Bayesian Methods for Mixtures of Experts",
booktitle="Neural Information Processing Systems",
editor="D. S. Touretzky and M. C. Mozer and M. E. Hasselmo",
publisher="MIT Press",
pages={351-357},
year ="1996",
}

@inproceedings{Waterhouse_etal95:nips,
author="S. R. Waterhouse and D. J. C. MacKay and A. J. Robinson",
title="Bayesian Methods for Mixtures of Experts",
booktitle="Neural Information Processing Systems",
editor="D. S. Touretzky and M. C. Mozer and M. E. Hasselmo",
publisher="MIT Press",
year ="1996",
pages={351-357},
annote={MRAO 1928}
}
@INPROCEEDINGS{MacKay94:alpha,
 KEY            ="MacKay",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Hyperparameters: Optimize, or Integrate out?",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, {S}anta {B}arbara 1993",
 EDITOR 	="G. Heidbreder",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1996",
 pages="43-60",
 abstractURL="ftp://www.inference.phy.cam.ac.uk/pub/mackay/abstracts/alpha.html",
 postscriptURL="ftp://www.inference.phy.cam.ac.uk/pub/mackay/alpha.ps.Z",
 keywords="alpha",
 ANNOTE ="Date submitted: 1993; Date accepted: 1993; Collaborating institutes: none"}

@article{MacKay94:alpha_nc,
 KEY            ="MacKay",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Comparison of Approximate Methods for Handling Hyperparameters",
 YEAR           ="1999",
volume={11}, 
number={5},
pages={1035-1068},
journal={Neural Computation},
 abstractURL="http://www.inference.phy.cam.ac.uk/mackay/abstracts/alpha.html",
 postscriptURL="ftp://www.inference.phy.cam.ac.uk/pub/mackay/alpha.ps.Z",
 ANNOTE ="Date submitted: 1994/1996/1997; Date accepted: October 1998; Collaborating institutes: none"
}


@InCollection{MacKay95:arbib,
  author = 	 "D. J. C.  MacKay",
  title = 	 "Bayesian Methods for Supervised Neural Networks",
booktitle= 	 "The Handbook of Brain Theory and Neural Networks",
  publisher =	 "MIT Press",
  year =	 1995,
  editor =	 "M. A. Arbib",
  pages =	 "144-149"
}

%MacKay93:review,
@INCOLLECTION{MacKay94:springer,
 KEY            ="MacKay",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Bayesian Methods for Backpropagation Networks",
 BOOKTITLE      ="Models of Neural Networks III",
 EDITOR 	="E. Domany and van Hemmen, J. L.   and K. Schulten",
 PUBLISHER	="Springer",
 ADDRESS	="New York",
 YEAR           ="1994",
 CHAPTER	="6",
 pages = {211-254},
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}

@article{MacKay95:network,
 KEY            ="MacKay",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Probable Networks and Plausible Predictions -- A
		  Review of Practical {B}ayesian Methods for Supervised
		  Neural Networks",
 journal ="Network: Computation in Neural Systems",
 volume = 6,
 YEAR           =1995,
 pages = "469-505",
 ANNOTE ="Date submitted: 1994; Date accepted: 1994; Collaborating
		  institutes: none"}
%  (August
% ISSN 0954-898X

@INPROCEEDINGS{MacKay94:pred_ashrae,
 KEY            ="MacKay",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Bayesian non-linear modelling for the  prediction 
        competition",
 BOOKTITLE      ="ASHRAE Transactions, V.100, Pt.2",
 EDITOR 	="",
 PUBLISHER	="American Society of Heating, Refrigeration, and Air-conditioning Engineers",
 ADDRESS	="Atlanta GA",
 YEAR           ="1994",
 PAGES ="1053-1062",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}

@INPROCEEDINGS{MacKay94:pred,
 KEY            ="MacKay",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Bayesian non-linear modelling for the 1993 energy prediction 
        competition",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, {S}anta {B}arbara 1993",
 EDITOR 	="G. Heidbreder",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1996",
 pages="221-234",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}


@INPROCEEDINGS{Green_MacKay94,
 AUTHOR         ="A. G. Green and  D. J. C.  MacKay",
 TITLE          ="Bayesian analysis of linear phased-array radar",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, 
			{S}anta {B}arbara 1993",
 EDITOR 	="G. Heidbreder",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1996",
 pages="309-318",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}

@INPROCEEDINGS{Tansley_etal94,
 AUTHOR         ="J. E.  Tansley and M. J.  Oldfield and D. J. C.  MacKay",
 TITLE          ="Neural network image reconstruction",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, 
			{S}anta {B}arbara 1993",
 EDITOR 	="G. Heidbreder",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1996",
 pages="319-326",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}

@UNPUBLISHED{MacKay_Oldfield95,
 KEY            ="",
 AUTHOR         ="D. J. C.  MacKay and M. J.  Oldfield",
 TITLE          ="Generalization Error 
	and the Number of Hidden units in a Multilayer Perceptron",
 YEAR           ="1995",
 note = "In preparation",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}

@Article{MacKay_Takeuchi95,
 AUTHOR         ="D. J. C.  MacKay and R. Takeuchi",
 TITLE          ="Interpolation Models with Multiple Hyperparameters",
  journal = 	 {Statistics and Computing},
  year = 	 {1998},
  volume = 	 {8},
  pages = 	 {15--23},
 ANNOTE ="Date submitted: Sep 1995; Date accepted: Jan 1997; Collaborating institutes:
		  Waseda University, Tokyo"}

@UNPUBLISHED{Evans_MacKay,
 AUTHOR         ="E. F. Evans and D. J. C.  MacKay",
 TITLE          ="A convenient method for generating constrained
		  randomized sequences on-line for physiological and
		  psychophysical stimulus selection",
 YEAR           =1995,
 NOTE           ="In preparation",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  Department of Communication and Neuroscience, Keele
		  University. MRAO 1834"}

@INPROCEEDINGS{MacKay_Takeuchi95_maxent,
 AUTHOR         ="D. J. C.  MacKay and R. Takeuchi",
 TITLE          ="Interpolation Models with Multiple Hyperparameters",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, 
			{C}ambridge 1994",
 EDITOR 	="J. Skilling and S. Sibisi",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1995",
 PAGES		="249-257",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  Waseda University, Tokyo. MRAO 1835"}

@INPROCEEDINGS{Barnett_MacKay95,
 AUTHOR         ="A. H. Barnett and D. J. C.  MacKay",
 TITLE          ="Bayesian Comparison of Models for Images",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, 
			{C}ambridge 1994",
 EDITOR 	="J. Skilling and S. Sibisi",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1995",
 PAGES		="239-248",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes: none"}

@INPROCEEDINGS{MacKay95:density_nets,
 KEY            ="",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Density Networks and their Application to Protein Modelling", 
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, 
			{C}ambridge 1994",
 EDITOR 	="J. Skilling and S. Sibisi",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1996",
 PAGES		="259-268",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  MRC Laboratory of Molecular Biology, Cambridge. MRAO 1837"}

@ARTICLE{MacKay95:wonsda,
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Bayesian Neural Networks and Density Networks", 
 JOURNAL        ="Nuclear Instruments and Methods in Physics 
                  Research, Section A",
 volume = 354,
 number = 1,
 YEAR           =1995,
 PAGES="73-80",
 ANNOTE ="Date submitted: 1994; Date accepted: 1994; Collaborating institutes: none"}
%  (Nucl. Inst. and Meth.)
% Jan 15 1995


@Incollection{MacKay97:dn,
  author = 	 "D. J. C.  MacKay and M. N. Gibbs",
  title = 	 "Density Networks",
  publisher = "Oxford University Press",
booktitle={Statistics and Neural Networks},
annote={subtitle: Advances at the Interface},
annote={Proceedings of meeting on Statistics and Neural Nets, Edinburgh, 1997},
  year = 	 "1998",
  editor = 	 "J. W. Kay and D. M. Titterington",
  pages = 	 "129-146"
}
% ,  note = 	 "in press"

@article{MacKay94:BC,
  author = 	 "D. J. C.  MacKay",
  title = 	 "Equivalence of {B}oltzmann Chains and Hidden {M}arkov Models",
  journal = 	 "Neural Computation",
  year =	 1996,
 volume=8,
 number=1,
 pages="178-181",
 ANNOTE ="Date submitted: Nov 1994;
modified 31 March 1995; Date accepted: April 10 1995; Collaborating institutes: none"
}

% better to cite Radford_book,MacKay94:pred_ashrae,MacKay95:network
@TECHREPORT{ARD,
 KEY            ="MacKay and Neal",
 AUTHOR         ="D. J. C. MacKay and R. M. Neal",
 TITLE          ="Automatic relevance determination for Neural Networks",
 YEAR           ="1994",
 NUMBER         ="In preparation",
 INSTITUTION    ="Cambridge University",
 ANNOTE ="Date submitted: ; Date accepted: ; Collaborating institutes:
		  University of Toronto"}

@PHDTHESIS{MacKay91,
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Bayesian Methods for Adaptive Models",
type={PhD},
 YEAR           =1991,
 SCHOOL		="California Institute of Technology"}

@Misc{Eddy_MacKay,
  author =	 "S. R. Eddy and D. J. C. MacKay",
  title =	 "Is the {P}ope the {P}ope? (Correspondence in {\em {N}ature\/} 382, p.\ 490)",
journal="Nature",
volume=382,
  year =	 1996,
  month =	 "August",
  pages =	 490,
  annote =	 "8 Aug 96"
}


@InCollection{MullerMacKayHerz96,
  author = 	 {R. M\"uller and D. J. C. MacKay and Herz, A. V. M.},
  title = 	 "Associative memory using action potential timing",
  booktitle =	 "Proceedings of BioNet'96: Third Workshop
		  `Bio-informatics and Pulsepropagating networks'",
editor ="G.K. Heinz",
publisher =	 "",
  year =	 1996,
  pages =	 "",
 ANNOTE ="Date submitted: 15 Nov 96; Date accepted: 15 Nov 96; Collaborating institutes:
		  University of Bremen"}



@book{MacKay:itp,
  author = 	 "David J. C. MacKay",
  title = 	 "Information Theory, Inference, and Learning Algorithms",
  note = 	 "Available from {\tt{http://www.inference.phy.cam.ac.uk/mackay/itila/}}",
publisher={Cambridge University Press},
 url="http://www.cambridge.org/0521642981",
  year =	 {2003}
}
% David J. C. MacKay (2003).  	 "Information Theory, Inference, and Learning Algorithms",
% Cambridge University Press,
% available from http://www.inference.phy.cam.ac.uk/mackay/itila/


@book{mackay-information,
  author = 	 "David J. C. MacKay",
  title = 	 "Information Theory, Inference, and Learning Algorithms",
  note = 	 "available from {\tt{http://www.inference.phy.cam.ac.uk/mackay/itila/}}",
publisher={Cambridge University Press},
 url="http://www.cambridge.org/0521642981",
  year =	 {2003}
}

@article{Badmos_etal97,
 AUTHOR		="A. Y. Badmos   and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="Tensile Properties of
		  Mechanically Alloyed Oxide Dispersion Strengthened
Iron Alloys. Part 1 -- Neural network Models", 
 YEAR		="1998",
 JOURNAL = "Materials Science and Technology",
 VOLUME		="14",
number={},
pages="793-809",
 ANNOTE ="Date submitted: Mar 97; accepted May 97;  Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}
% mrao number?

@article{Brun_etal97,
 AUTHOR		="F. Brun and T. Yoshida and J. D. Robson and V.
		  Narayan and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="Theoretical Design of Ferritic Creep Resistant Steels using Neural Network, Kinetic and Thermodynamic Models", 
 YEAR		="1999",
 JOURNAL = "Materials Science and Technology",
 VOLUME		="15",
number={},
pages="547-554",
 ANNOTE ="Date submitted: Sep 97; accepted July 98. Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science.
 contains the new steels A and B"}
% mrao number?

@article{Lalam_etal97,
 AUTHOR		="S. H. Lalam and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="Estimation of the Mechanical Properties of Ferritic Steel Welds: Part {I}: Yield and Tensile Strength", 
 YEAR		="2000",
 JOURNAL = "Science and Technology of Welding and Joining",
 VOLUME		="5",
number={3},
pages="135-147",
 ANNOTE ="Date submitted: May 99; accepted . Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science."}
% mrao number?


@INPROCEEDINGS{FreyMacKay97,
 KEY            ="",
 AUTHOR         ="B. J. Frey and D. J. C.  MacKay",
 TITLE          ="Trellis-constrained Codes", 
 BOOKTITLE      ="Proceedings of the 35th Allerton Conference on Communication, Control, and Computing, Sept.\ 1997",
  place =        "Champaign-Urbana, Illinois",
  annote =         "Available at {\tt http://www.cs.utoronto.ca/\verb+~+frey}",
 EDITOR 	="",
 PUBLISHER	="",
 ADDRESS	="",
 YEAR           ="1998",
 PAGES		="",
 ANNOTE ="Date submitted: jun 97; Date accepted: jun 97; Collaborating institutes:
		  Univ of Toronto. MRAO "}

@Unpublished{frey-mackay-98b,
  key =          "Frey",
  author =       "B.~J. Frey and D.~J.~C. MacKay",
  title =        "Trellis-constrained codes",
  note =         "Submitted to \emph{IEEE Trans. on Communications}",
  year =         "1998"
}

@INPROCEEDINGS{FreyMacKay98,
 KEY            ="",
 AUTHOR         ="B. J. Frey and D. J. C.  MacKay",
 TITLE          ={A Revolution: Belief Propagation in Graphs with Cycles}, 
 BOOKTITLE      ={Advances in Neural Information Processing Systems 10},
 EDITOR 	="M. I. Jordan and M. J. Kearns and S. A. Solla",
 PUBLISHER	="MIT Press",
 ADDRESS	="Cambridge MA.",
 YEAR           ="1998",
 PAGES		="479--485",
 anNOTE		="Available at {\tt http://www.cs.utoronto.ca/\verb+~+frey}",
 ANNOTE ="Date submitted: jun 97; Date accepted: ; Collaborating institutes:
		  Univ of Toronto. MRAO "}

% Same as:
@InCollection{frey-mackay-98c,
  key =          "Frey",
  author =       "B.~J. Frey and D.~J.~C. MacKay",
  title =        "A revolution: {B}elief propagation in graphs with cycles",
  booktitle =    "Advances in Neural Information Processing Systems
                  1997, Volume 10",
  editor =       "M.~I. Jordan and M.~I. Kearns and S.~A. Solla",
  year =         "1998",
  publisher =    "MIT Press",
  place =        "Cambridge MA.",
  pages =        "479--485",
  note =         "Available at {\tt http://www.cs.utoronto.ca/\verb+~+frey}"
}


@article{Takeuchi_etal97:Jap,
 AUTHOR		="R. Takeuchi and D. J. C.  MacKay 
                        and S. Nakazawa and T. Matsumoto",
 TITLE		="Inferring   Hyperparameters and Regularizers
		  for Standard Regularization Problems", 
 YEAR		=1997,
 journal = "Trans. of the Institute of Electronics, Information
		  and Communication Engineers",
 volume={J80-D-II},
 number={9},
 pages="2502-2511", 
note="In Japanese",
 ANNOTE ="Date submitted: ; Date accepted: ; 
Collaborating institutes:
		  Waseda University, Tokyo"}

@Incollection{MacKay97:erice,
  author = 	 "D. J. C.  MacKay",
  title = 	 "Introduction to {M}onte {C}arlo Methods",
  publisher = "Kluwer",
booktitle={Learning in Graphical Models},
  year = 	 "1998",
  editor = 	 "M. I. Jordan",
  pages = 	 "175-204",
series={NATO Science Series}
}

@article{Fujii_etal99,
 AUTHOR		="H. Fujii and D. J. C.  MacKay   and H. K. D. H. Bhadeshia
 and H. Harada and K. Nogi",
 TITLE		="Prediction of Creep Rupture Life in {N}ickel-Base Superalloys using {B}ayesian Neural Network", 
 YEAR		="1999",
 journal={J. Japan Inst. Metals},
volume={63},
number={7},
pages={905-911},
note={In Japanese},
 ANNOTE ="Submitted Nov 2 98; Accepted Apr 19 1999. Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@inproceedings{Fujii_etal98,
 AUTHOR		="H. Fujii and D. J. C.  MacKay   and H. K. D. H. Bhadeshia
 and H. Harada and K. Nogi",
 TITLE		="Estimation of Creep Rupture Strength
 in {N}ickel Base Superalloys", 
 YEAR		="1998",
booktitle={Proceedings 6th Liege Conference on Materials for Advanced Power Engineering},
 ANNOTE ="May 1998. conference 5-7 October 1998; Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@article{Ichikawa96,
 KEY		="K. Ichikawa",
 AUTHOR		="K. Ichikawa and H. K. D. H. Bhadeshia and D. J. C. MacKay",
 TITLE		="Model for Hot Cracking in Low-Alloy Steel Weld Metals",
 YEAR		=1996,
 JOURNAL        = "Science and Technology of Welding and Joining",
 VOLUME         = "1",
 PAGES		="43-50"
}
@Incollection{MacKay98:gp,
  author = 	 "D. J. C.  MacKay",
  title = 	 "Introduction to {G}aussian Processes",
  publisher = "Kluwer",
 booktitle={Neural Networks and Machine Learning},
 series={NATO ASI Series},
  year = 	 "1998",
  editor = 	 "C. M. Bishop",
  pages = 	 "133-166"
}

@InProceedings{DM_LDPC_ITW98,
  author =       {M. C. Davey and D. J. C. MacKay},
  title =        {Low Density Parity Check Codes over {GF}(q)},
  booktitle =    {Proceedings of the 1998 IEEE Info. Theory Workshop},
  year =         {1998},
  month =        {June},
  organization = {IEEE},
pages={70-71},
  key =          {Davey and MacKay}
}

%MD_LDPC_IRREG,

@INPROCEEDINGS{MacKayAllerton98,
 KEY            ="",
 AUTHOR         ="D. J. C.  MacKay and S. T. Wilson and M. C. Davey",
 TITLE          ="Comparison of Constructions of Irregular {G}allager Codes", 
 BOOKTITLE      ="Proceedings of the 36th Allerton Conference on Communication, Control, and Computing, Sept.\ 1998",
 EDITOR 	="",
 PUBLISHER	="Allerton House",
 ADDRESS	="Monticello, Illinois",
 YEAR           ="1998",
 PAGES		="220-229",
 ANNOTE ="Date submitted: jun 98; Date accepted: jun 98;  MRAO "}
@article{MacKayWilsonDavey98,
 KEY            ="",
 AUTHOR         ="D. J. C.  MacKay and S. T. Wilson and M. C. Davey",
 TITLE          ="Comparison of Constructions of Irregular {G}allager Codes", 
journal={IEEE Trans. on Communications},
issn={0018-9332},
YEAR           ="1999",
 PAGES		="1449-1454",
volume={47},number={10},month={October},
annote={Both co-authors were supervised research students},
 ANNOTE ="Date submitted: jun 98; Date accepted: apr 21 1999;  MRAO "}
% To appear. Also available from {\tt{http://www.inference.phy.cam.ac.uk/mackay/abstracts/ldpc-irreg.html}}},

@article{Narayan_etal98,
 AUTHOR		="V. Narayan and R. Abad and B. Lopez 
 and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="Estimation of Hot Torsion Stress Strain Curves in Iron
 Alloys Using a Neural  Network Analysis",
 YEAR		="1998",
 JOURNAL = "ISIJ International",
volume={39},
number={10},
pages =     {999-1005},
 ANNOTE ="Date submitted: Sep 98;  Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@article{Yoshitake_etal98,
 AUTHOR		="S. Yoshitake and  V. Narayan and H. Harada
 and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="Estimation of the $\gamma$ and $\gamma'$ Lattice Parameters
 in {N}ickel-base Superalloys Using Neural Network Analysis",
 YEAR		="1998",
 JOURNAL = "ISIJ International",
 VOLUME		="38",
number={5},
pages="495-502",
 ANNOTE ="Date submitted: Sep 97;  Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

@article{Singh_etal98,
 AUTHOR		="S. B. Singh and H. K. D. H. Bhadeshia and D. J. C. MacKay
 and H. Carey and I. Martin",
 TITLE		={Neural Network Analysis of Steel Plate Processing},
 YEAR		="1998",
 JOURNAL = "Ironmaking and Steelmaking",
 VOLUME		="25",
number={5},
pages="355-365",
abstract={The process of rolling is very complicated and the number of parameters which determines the final properties
can be very large. It is extremely difficult therefore to develop a physical model for predicting various properties
like yield and tensile strengths. In the present work, a neural network technique which can recognise complex
relationships was employed to develop a quantitative method for estimating the yeild and tensile strengths as a
function of steel composition and rolling parameters. The model was tested extensively to confirm that the
predictions are reasonable in the context of metallurgical principles and other data published in the literature. 
},
 url={http://www.msm.cam.ac.uk/phase-trans/abstracts/processing.html},
 ANNOTE ="Date submitted: Jan 98;
 Accepted: July 1998;  Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science"}

%%%   up to here (search ahead for ADD NEW)

% 22 Feb 2001, print issue march 2001
@article{PattersonChildsMacKay00,
 title={Exact sampling from non-attractive distributions using summary states},
 author={Andrew M. Childs and Ryan B. Patterson and David J. C. MacKay},
 year={2001},
 journal={Physical Review E},
 volume={63},
 annote={036113},
 pages={036113},
 annote={036113 (5 pages)}
}
@unpublished{MacKayEncyclopedia98,
 KEY            ="",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Encyclopedia of Sparse Graph Codes", 
 ADDRESS	="",
 YEAR           ="1998",
 PAGES		="",
note={{\verb|http://www.inference.phy.cam.ac.uk/mackay/|}},
 ANNOTE ="Date submitted: ; Date accepted: ;  MRAO "}
@unpublished{MacKay99ENC,
 KEY            ="",
 AUTHOR         ="D. J. C.  MacKay",
 TITLE          ="Encyclopedia of Sparse Graph Codes (hypertext archive)", 
 ADDRESS	="",
 YEAR           ="1999",
 PAGES		="",
note={{\verb|http://www.inference.phy.cam.ac.uk/mackay/codes/data.html|}},
 ANNOTE ="Date submitted: ; Date accepted: ;  MRAO "}

@article{Lalam_etal99a,
 AUTHOR		="S. H. Lalam and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="Estimation of the Mechanical Properties of Ferritic Steel Welds: Part {II}:  Elongation and  {C}harpy Toughness", 
 YEAR		="2000",
 JOURNAL = "Science and Technology of Welding and Joining",
 VOLUME		="5",
number={3},
pages="149-160",
 ANNOTE ="Date submitted: Dec 99; accepted . Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science."}
@article{Lalam_etal99b,
 AUTHOR		="S. H. Lalam and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="The {C}harpy Impact Transition Temperature
 for some  Ferritic Steel Welds", 
 YEAR		="2000",
 JOURNAL = "Australisian Welding Journal",
 VOLUME		="45",
number={},
pages="33-37",
 ANNOTE ="Date submitted: Dec 99; accepted . Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science."}
% Science and Technology of Welding and Joining",

@article{Lalam_etal99c,
 AUTHOR		="S. H. Lalam and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="{B}ruscato factor in the Temper Embrittlement of Welds", 
 YEAR		="2000",
 JOURNAL = "Science and Technology   of Welding and Joining",
 VOLUME		="5",
number={5},
pages="338-340",
 ANNOTE ="Date submitted: Dec 99; accepted . Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science."}
% mrao number?
% de Sa, V.R., & MacKay, D. J. C. (2001). Model fitting as an Aid to Bridge Balancing in Neuronal Recording. {\it Neurocomputing} (special issue devoted to Proceedings of the CNS 2000 meeting) Vol38-40, 1651--1656.

@article{deSaMacKay2001,
author={de Sa, V. R. and MacKay, D. J. C.},
year={2001},
title={Model fitting as an Aid to Bridge Balancing in Neuronal Recording},
journal={Neurocomputing},
annote={special issue devoted to Proceedings of the CNS 2000 meeting},
volume={38-40},
pages={1651-1656}
}

@misc{MacKaydeCharmsdeSa1999,
year={1999},
title={A Comment on Data Shuffling},
author={David J. C. MacKay and Christopher deCharms and  de Sa, Virginia R.},
note={Available from {\tt{http://www.inference.phy.cam.ac.uk/mackay/abstracts/shuffle.html}}}
}

@misc{MacKayWills2000,
year={2000},
title={Time-warp-invariant computation with action potentials:
                     {D}eductions about the {Hopfield--Brody} Mouse},
author={David J. C. MacKay and Sebastian A. Wills},
note={{\tt{http://www.inference.phy.cam.ac.uk/mackay/HBMouse.html}}},
annote={In December 2000, the Inference Group  won both parts of Hopfield and Brody's `mouse brain' competition.}
}

@misc{MacKayWills2003,
year={2003},
title={ Simultaneous Multiple Recall with Spiking Neurons},
author={ Sebastian A. Wills and David J. C. MacKay },
note={Submitted to Computational and Systems Neuroscience 2004}
}


@article{Yescas_etal01,
 AUTHOR		="M. A. Yescas and H. K. D. H. Bhadeshia and D. J. C.  MacKay",
 TITLE		="Estimation of the amount of retained austenite in austempered ductile irons using neural networks", 
 YEAR		="2001",
 JOURNAL = "Materials Science and Technology",
 VOLUME		="A311",
pages="162-173",
 ANNOTE ="Date submitted: 21 Aug 2000; accepted . Collaborating institutes:
		  Cambridge University Department of Metallurgy and
		  Materials Science."}
% mrao number?

@Article{KMK:03,
  author =	 {Kreil, David P. and MacKay, David J. C.},
  title =	 {Reproducibility Assessment of Independent Component
                  Analysis of Expression Ratios from {DNA} Microarrays},
  journal =	 {Comparative and Functional Genomics},
  year =	 2003,
  volume =	 4,
  number =	 {3},
  pages =	 {300-317}
}

@article{DasherACNR,
author={MacKay, David J. C.},
title={Dasher -- an Efficient Keyboard Alternative},
journal={Advances in Clinical Neuroscience and Rehabilitation},
volume={3},number={2},pages={24},month={May/June},year={2003},
url={http://www.acnr.co.uk/contents3-2.htm}
}
% ADD ME!!
@article{saidi2002,
title={Independent Component Analysis of Microarray Data in the Study of Endometrial Cancer},
author={Saidi, Sam and  Cath Holland  and Kreil, David P.
                 and Steve Charnock-Jones and Cris Print
              and MacKay, David J. C. and Smith, Stephen},
year={2004},
journal={Oncogene},
note={To appear},
annote={Independent Component Analysis of Microarray Data in the Study of
Endometrial Cancer}
}

% ADD NEW MacKay papers here (search back for 'up to here')
%
% DJCM marker 1 (another below)


@unpublished{MacKay-irreg-its,
 title={Decoding Times of Irregular {G}allager Codes},
 author={D. J. C.  MacKay},
 note={Unpublished},
 year={1998}
}
@unpublished{MacKay-ra-its,
 title={Decoding Times of Repeat-Accumulate Codes},
 author={D. J. C.  MacKay},
 note={Unpublished},
 year={1998}
}
@unpublished{MacKay-SGC-AmblesideI,
 title={Sparse Graph Codes},
 author={D. J. C.  MacKay},
 note={Extended Abstract, Ambleside meeting},
 year={1999}
}

@inproceedings{MacKay-SGC-AmblesideII,
 title={{G}allager Codes -- Recent Results},
 author={D. J. C.  MacKay},
 booktitle={Coding, Communications and Broadcasting},
annote={Proceedings of International Symposium on Communication Theory and
 Applications, Ambleside, 1999},
 publisher={Research Studies Press},
 address={Baldock, Hertfordshire, England},
 editor={P. Farrell, M. Darnell and B. Honary},
 pages={139-150},
 year={2000}
}
% MacKay Kschischang and Frey 
% compound codes


% Frey and MacKay
% shortened turbo codes and irregular turbo codes

@inproceedings{FreyMacKay00b,
title={Irregular Turbocodes},
author={B. J. Frey and David J. C. MacKay},
 year={2000},
 booktitle={Proceedings 2000 IEEE International Symposium on Info. Theory},
pages={121},
annote={ISIT 2000}
}
@inproceedings{DaveyMacKay99a,
 title={Watermark Codes: Reliable communication over Insertion/Deletion channels.},
 author={Matthew C. Davey and  David J. C. MacKay},
 year={2000},
 booktitle={Proceedings 2000 IEEE International Symposium on Info. Theory},
pages={477},
annote={ISIT 2000}
}

@article{DaveyMacKay99b,
 title={Reliable communication over  channels with insertions, deletions and substitutions.},
 author={Matthew C. Davey and  David J. C. MacKay},
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={687-698},
annote={Submitted 1999}
}

@inproceedings{RatzerMacKay00,
title={Codes for Channels with Insertions, Deletions and Substitutions},
author={Edward A. Ratzer and David J. C. MacKay},
pages={149-156},
booktitle={Proceedings of 2nd International Symposium on Turbo Codes and Related Topics,
 Brest, France, 2000},
year={2000}
}
@inproceedings{FreyMacKay00,
title={Irregular Turbo-like Codes},
author={B. J. Frey and David J. C. MacKay},
pages={67-72},
booktitle={Proceedings of 2nd International Symposium on Turbo Codes and Related Topics,
 Brest, France, 2000},
year={2000}
}
@unpublished{MacKay00RLLT,
 title={An Alternative to  Runlength-limiting Codes:
 Turn Timing Errors into Substitution Errors},
 author={David J. C. MacKay},
 year={2000},
 abstractURL="http://www.inference.phy.cam.ac.uk/mackay/abstracts/rllt.html",
 postscriptURL="ftp://www.inference.phy.cam.ac.uk/pub/mackay/rllt.ps.Z",
 note={Available from {\tt{http://www.inference.phy.cam.ac.uk/mackay/}}}
}

@inproceedings{MacKay99RLL,
 title={Almost-certainly Runlength-limiting Codes},
 author={David J. C. MacKay},
booktitle={Proceedings of the
IMA Cryptography and Coding Conf. 2001},
publisher={Springer},
 year={2001},
 note={Also available from {\tt www.inference.phy.cam.ac.uk/mackay}}
}

@InCollection{McElieceMacKay00,
 AUTHOR		="S. Aji and H. Jin and A. Khandekar and R. J. McEliece and D. J. C. MacKay",
 title={{BSC} Thresholds for Code Ensembles based on `Typical Pairs' Decoding},
  booktitle = 	 {Codes, Systems and Graphical Models},
volume={123},
  series =	 {IMA Volumes in Mathematics and its Applications},
  publisher =	 {Springer},
  year =	 2000,
  editor =	 {B. Marcus and J. Rosenthal},
  address =	 {New York},
pages={195-210}
}
@InCollection{MacKayDaveyR3,
 AUTHOR		="D. J. C. MacKay and M. C. Davey",
 title={Two Small {G}allager codes},
  booktitle = 	 {Codes, Systems and Graphical Models},
volume={123},
  series =	 {IMA Volumes in Mathematics and its Applications},
  publisher =	 {Springer},
  year =	 2000,
  editor =	 {B. Marcus and J. Rosenthal},
  address =	 {New York},
pages={131-134}
}
% seagate
@InCollection{MacKayHighRate98,
 KEY            ="",
 AUTHOR         ="D. J. C.  MacKay and M. C. Davey",
 TITLE          ="Evaluation of {G}allager Codes for Short Block Length and High Rate
 Applications",
  booktitle = 	 {Codes, Systems and Graphical Models},
volume={123},
  series =	 {IMA Volumes in Mathematics and its Applications},
  publisher =	 {Springer},
  year =	 2000,
pages={113-130},
  editor =	 {B. Marcus and J. Rosenthal},
  address =	 {New York},
url={http://www.inference.phy.cam.ac.uk/mackay/CodesRegular.html}
}

% was dasher00
@inproceedings{ward2000,
author="D. J. Ward and A. F. Blackwell and D. J. C. MacKay",
year="2000",
booktitle="Proceedings of {User Interface Software and Technology} 2000",
title="Dasher -- {A} Data Entry Interface Using Continuous Gestures and Language Models",
pages="129-137",
annote={The 13th Annual ACM Symposium on User Interface Software and Technology}
}
@article{ward2002,
author="D. J. Ward and A. F. Blackwell and D. J. C. MacKay",
title="Dasher -- {A} Data Entry Interface Using Continuous Gestures and Language Models",
year="2002",
journal={Human-Computer Interaction},
volume={17},
number={2-3},
pages={}
}

@article{wardmackay2002,
author="D. J. Ward  and D. J. C. MacKay",
title="Fast Hands-free writing by Gaze Direction",
year="2002",
journal={Nature},
volume={418},
number={6900},
pages={838},
url={http://www.inference.phy.cam.ac.uk/mackay/abstracts/eyeshortpaper.html}
}


@unpublished{Dasher00,
 title={Dasher -- a Data Entry Interface Using Continuous Gestures and
  Language Models},
author={David J. Ward and  Alan F. Blackwell and  David J.C. Mackay},
year={2000},
 note={submitted to ACM conference}
}

@unpublished{MacKay00Thresholds,
 title={On Thresholds of Codes},
 author={David J. C. MacKay},
 year={2000},
 note={{\tt www.inference.phy.cam.ac.uk/mackay/abstracts/theorems.html}}
}
@unpublished{MacKay00Puncture,
 title={Punctured and Irregular High-Rate {G}allager Codes},
 author={David J. C. MacKay},
 year={2000},
 note={{\tt www.inference.phy.cam.ac.uk/mackay/abstracts/puncture.html}}
}

% kji
@article{Inskip2001,
 title={{K-Z} diagrams for {3CR} and {6C} Galaxies
in a selection of Different Cosmologies},
 author={K. J. Inskip and P. N. Best and M. S. Longair and D. J. C. MacKay},
 journal={M.N.R.A.S.},
 year={2002},
page =277, volume =329, issue= 2,
note={astro-ph/0110054}
}
@techreport{MYFW2001,
 author={D. J. C. MacKay and J. S. Yedidia and W. T. Freeman and Y. Weiss},
 title={A Conversation about the {B}ethe Free Energy and Sum-Product},
 institution={Cambridge University / Mitsubishi},
 note={MERL TR-2001-18},
 year={2001},
url={http://www.merl.com/reports/TR2001-18/index.html or http://www.inference.phy.cam.ac.uk/mackay/abstracts/bethe.html}
}

% non-negative
@inproceedings{ obd00nonnegative,
    author = "Downs, O. B. and MacKay, D. J. C. and Lee, D. D. ",
    title = "The Nonnegative {B}oltzmann Machine",
    booktitle = "Advances in Neural Information Processing Systems 12.",
editor={S.A. Solla and T.K. Leen and  K.-R. M\"uller},
publisher={MIT Press},
year = "2000",
    url = "citeseer.nj.nec.com/downs00nonnegative.html",
abstract={
The nonnegative Boltzmann machine (NNBM) is a recurrent neural network
model that can describe multimodal nonnegative data. Application of maximum likelihood
estimation to this model gives a learning rule that is analogous to the binary Boltzmann
machine. We examine the utility of the mean field approximation for the NNBM, and
describe how Monte Carlo sampling techniques can be used to learn its parameters. Reflective slice sampling is particularly
well-suited for this distribution, and can efficiently be implemented to sample the distribution. We illustrate learning of the
NNBM on a translationally invariant distribution, as well as on a generative model for images of human.}
}

@PhdThesis{MiskinPHD,
  author = 	 {James W. Miskin},
  title = 	 {Ensemble Learning for Independent Component Analysis},
  school = 	 {Department of Physics, University of Cambridge},
type={PhD},
  year = 	 2001,
url={http://www.inference.phy.cam.ac.uk/jwm1003/}
}

@InProceedings{miskin1,
  author =       {Miskin, J. W. and MacKay, D. J. C.},
  title =        {Ensemble Learning for Blind Image Separation and Deconvolution},
  booktitle =    {Advances in Independent Component Analysis},
editor={M. Girolami},
  publisher = {Springer},
  year      = {2000},
url={http://www.inference.phy.cam.ac.uk/jwm1003/}
}

@InProceedings{miskin2,
  author =       {Miskin, J. W. and MacKay, D. J. C.},
  title =        {Application of Ensemble Learning to Infra-Red Imaging},
  booktitle =    {Proceedings of the Second International Workshop on Independent Component Analysis and Blind Signal Separation},
  pages =        {399-404},
  year =         {2000}
}

% year  and editor  and ?????????},
@InCollection{miskin3,
author =       {Miskin, J. W. and MacKay, D. J. C.},
  title =        {Ensemble Learning for Blind Source Separation},
 booktitle={ICA: Principles and     Practice},
editor={S.J. Roberts and R.M. Everson},
year={2001},
publisher={Cambridge University Press},
address={Cambridge}
}

@techreport{mackaymiskin01,
title={Latent Variable Models for Gene Expression Data},
author={David J. C. MacKay and James W. Miskin},
institution={University of Cambridge, Department of Physics},
year=2001,
url={http://www.inference.phy.cam.ac.uk/mackay/abstracts/icagenes.html}
}

@article{martogliomiskin,
  author =       {Martoglio, A.-M. and Miskin, J. W. and Smith, S. K. and MacKay, D. J. C.},
  title =        {A Decomposition Model to Track Gene Expression Signatures: Preview on Observer-independent
             Classification of Ovarian Cancer},
journal={Bioinformatics},
 volume={18},
number={12},
pages={1617-1624},
  year      = {2002},
annote={Bioinformatics (2002) Dec; 18(12):1617-1624},
url={http://www.obgyn.cam.ac.uk/}
}

% what is this?

@techreport{MacKayDecision2001,
 author={D. J. C. MacKay},
 title={Decision theory -- a simple example},
 institution={Cambridge University},
 year={2001},
annote={Aug 6 2001},
 note={http://www.inference.phy.cam.ac.uk/mackay/Decision.html },
 url={http://www.inference.phy.cam.ac.uk/mackay/Decision.html }
}

@article{SkillingMacKay2002,
title={Slice Sampling --  a  Binary Implementation},
author={John Skilling and  MacKay, David J. C.},
year={2003},
Volume={31},number={3},
pages={753-755},
month={June},
url={http://www.inference.phy.cam.ac.uk/mackay/abstracts/slice.html},
journal={Annals of Statistics}, 
note={Discussion of {\em Slice Sampling\/} by Radford M.~Neal }
}
 
@unpublished{Bloj2001,
author="Roger F. Sewell and David J. C. MacKay and  Iain McLean",
year=2002,
title={A maximum entropy approach to fair elections},
url={http://www.cambridgeconsultants.com/PDFs/RFSpdf.pdf
 or http://www.inference.phy.cam.ac.uk/mackay/RFSpdf.pdf},
note={Submitted to {\em Politics, Philosophy, and Economics}, Dec 2002}
}

%  MISKIN PAPERS?????????????

% title={Dynamic neural network models for  aluminium alloy processing},

@inproceedings{ChristelleEtAl2002,
author={Christelle Royer Crotaz and Hugh Shercliffe and David J. C. MacKay},
conference={ICAA8},
booktitle={Materials Science Forum. volumes 396-402, Aluminium alloys,
their Physical and Mechanical Properties, proceedings of the 8th
international conference ICAA8, Cambridge, UK, July 2-5 2002},
publisher={Trans Tech Publications},
editor={P.J. Gregson and S.J. Harris},
title={Advanced Statistical Modelling of Processing of Aluminium Alloys},
pages={643-648},
year={2002}
}

@techreport{MacKayEuro2002,
 author={David J. C. MacKay},
 title={Belgian euro coins: 140 heads in 250 tosses -- suspicious?},
 institution={University of Cambridge, Department of Physics},
 note={Available online from
 http://www.inference.phy.cam.ac.uk/mackay/abstracts/euro.html},
 url={http://www.inference.phy.cam.ac.uk/mackay/abstracts/euro.html},
 year={2002}
}

% UNPUBLISHED  journal =	 "IEEE Trans. Communications",
@inproceedings{HeskethMacKay97,
 KEY		="",
 AUTHOR		="D. J. C. MacKay and C. P. Hesketh",
 TITLE		="Performance  of  Low Density Parity Check Codes
 as a Function of Actual and Assumed Noise Levels",
 YEAR		=2003,
 booktitle={Proceedings of MFCSIT2002, Galway},
 volume={74},
 series={Electronic Notes in Theoretical Computer Science},
 publisher={Elsevier},
url={{\tt http://www.inference.phy.cam.ac.uk/mackay/abstracts/sensit.html}},
 PAGES		="",
 ANNOTE ="Collaborating institutes: none.  Volume 74 of ENTCS"}


@inproceedings{MacKayPostol2002,
 author={MacKay, David J. C. and Postol,  M. J. },
 title={Weaknesses of  {M}argulis  and  {R}amanujan--{M}argulis Low-Density Parity-Check  Codes},
 booktitle={Proceedings of MFCSIT2002, Galway},
 volume={74},
 series={Electronic Notes in Theoretical Computer Science},
 publisher={Elsevier},
 url={http://www.inference.phy.cam.ac.uk/mackay/abstracts/margulis.html},
 year={2003}, annote={Volume 74 of ENTCS}
}

@misc{mackaymitchisonmcfadden2003,
year={2003},
note={Submitted to {\em IEEE Trans. on Info. Theory\/}  May 8, 2003},
  howpublished = {{\tt{quant-ph/0304161}}},
  annote={First published: Thu, 24 Apr 2003 21:20:34 GMT, Submitted to {\em IEEE Trans. on Info. Theory\/}  May 8, 2003.},
  author={MacKay, David J. C.  and  Mitchison, Graeme J. and  McFadden, Paul L.},
  title={Sparse-Graph Codes for Quantum Error-Correction},
  abstract={
    We present sparse graph codes appropriate for use in quantum error-correction.
    Quantum error-correcting codes based on sparse graphs are of interest for three reasons. First, the best codes currently known for classical channels are based on sparse graphs.
    Second, sparse graph codes keep the number of quantum interactions associated with the quantum error correction process small: a constant number per quantum bit, independent of the blocklength.
    Third, sparse graph codes often offer great flexibility with respect to blocklength and rate.
    We believe some of the codes we present are unsurpassed by previously published quantum error-correcting codes.
}
}

@misc{mackaymitchisonmcfadden2003Long,
year={2003},
  howpublished = {{\tt{quant-ph/0304161}}},
  annote={First published: Thu, 24 Apr 2003 21:20:34 GMT, Submitted to {\em IEEE Trans. on Info. Theory\/}  May 8, 2003.},
  author={MacKay, David J. C.  and  Mitchison, Graeme J. and  McFadden, Paul L.},
  title={Sparse-Graph Codes for Quantum Error-Correction},
  abstract={
    We present sparse graph codes appropriate for use in quantum error-correction.
    Quantum error-correcting codes based on sparse graphs are of interest for three reasons. First, the best codes currently known for classical channels are based on sparse graphs.
    Second, sparse graph codes keep the number of quantum interactions associated with the quantum error correction process small: a constant number per quantum bit, independent of the blocklength.
    Third, sparse graph codes often offer great flexibility with respect to blocklength and rate.
    We believe some of the codes we present are unsurpassed by previously published quantum error-correcting codes.
}
}

% ed's paris conference
@inproceedings{RatzerMacKay2003,
title={Sparse Low-Density Parity-Check Codes for Channels with Cross-Talk},
author={Edward A. Ratzer and David J. C. MacKay},
year={2003},
booktitle={Proceedings of 2003 IEEE Info. Theory Workshop, Paris},
annote={Paper 0164 on http://itw2003.enst.fr/program.html}
}

% need to add from here on to my publications
@misc{MacKayRectangles2003,
title={Simple Proofs of a Rectangle Tiling Theorem},
author={David J. C. MacKay},
year={2003},
note={{\tt{http://www.inference.phy.cam.ac.uk/mackay/abstracts/rectangles.html}}}
}

@inproceedings{GarrettDasher2003,
title={Implementation of {Dasher}, an Information-Efficient Input Mechanism},
author={Matthew Garrett and David Ward and Iain Murray and Phil Cowans and David J.C. MacKay},
year={2003},
booktitle={Proceedings of GUADEC 2003},
annote={Paper 0164 on http://itw2003.enst.fr/program.html}
}


@article{MacKayGlotDasher2003,
title={{Dasher}, an Efficient Keyboard Alternative},
author={David J. C. MacKay},
year={2003},
journal={Glot International},
volume=7,
number={7/8},
pages={}
}

@inproceedings{HansenMacKayNielsenHansen2004,
title={Eye Tracking in the Wild},
author={Dan Witzner Hansen and David J.C. MacKay and Mads Nielsen
 and John Paulin Hansen},
note={poster at Eye Tracking Research and Applications (ETRA04), San Antonio, TX, 22-24 March},
year={2004},
Abstract={
We address the problem of using off-the-shelf components for gaze-based interaction. We examine basic properties of gaze determination when the geometry of the the camera, screen and user is unknown. In particular we present a lower bound the number of calibration points needed for gaze determination and we examine degenerate configurations. Secondly we propose a method for gaze determination based on Gaussian Process interpolation. These facilitate error measures on gaze estimation based purely on the training data. Gaussian Processes provide a way of getting feedback from gaze estimation and thus holds potential for changing the common input-output approach to gaze estimation to a more dynamical one, without using any other information than the calibration data.
}
}

% ADD NEW MacKay papers here (search back for 'up to here') HERE
%
% DJCM marker 2

@article{Rectangles14,
title={Fourteen Proofs of a Result About Tiling a Rectangle},
author={Stan Wagon},
journal={The American Mathematical Monthly},
Volume={94},
number={7},
annote={Aug. - Sep.},
year={1987},
pages={601-617},
url={http://links.jstor.org/sici?sici=0002-9890%28198708%2F09%2994%3A7%3C601%3AFPOARA%3E2.0.CO%3B2-Y}
}

% Packing a Box with Bricks
%        Charles H. Jepsen
%        Mathematics Magazine, Vol. 64, No. 2. (Apr., 1991), pp. 92-97.

%Filling Boxes with Bricks (in Mathematical Notes)
%   N. G. de Bruijn
%    The American Mathematical Monthly, Vol. 76, No. 1. (Jan., 1969), pp. 37-40.

% this is an excellent article on the money pump
%    The Box Problem: To Switch or Not to Switch
%        Steven J. Brams; D. Marc Kilgour
%        Mathematics Magazine, Vol. 68, No. 1. (Feb., 1995), pp. 27-34.


% used my software:
@article{Grylls1997,
  title={Mechanical properties of a high-strength cupronickel alloy {B}ayesian 
    neural network analysis},
  author={Grylls, R. J.},
  journal={Materials Science and Engineering A-Structural Materials Properties 
    Microstructure and Processing},
  year={1997},
  volume={234},
  pages={267-270},
  abstract={In this work the mechanical properties of a highly alloyed 
    cupronickel have been analyzed using a neural network technique 
    within a {B}ayesian framework. In this way the mechanical properties 
    can be represented as an empirical function of the compositional 
    variables. This method has been used to analyze the relative 
    contributions of the various elements to the mechanical properties. 
    Whilst the method is entirely empirical, it will be shown that the 
    predictions made are of metallurgical significance. (C) 1997 Elsevier
    Science S.A.}
}

% -----------------------------------
% INDEX:
% -----------------------------------
%	SPIN GLASS PAPERS
%	STATISTICS AND NEURAL NETS
%
% I wonder if I can still find Hodge and Seed
%
%	LUTTRELL
%	BM'S, MEAN FIELD THEORY
%	TSP
%	BASIC NEURAL NET REFS
%	HEBBIAN, LINSKER
%	NUMERICAL
%	GULL, SKILLING, OCCAM, MAXENT, MDL
%	NEURAL NETS OPTIMISATION OF number parameters, regularisers, etc. 
%	OTHER PAPERS ON OCCAM

%%%%%%% QECC References %%%%%%%%%%%%%%%%%%%%%%%
@Book{NielsenChuang,
  author =       "M.~Nielsen and I.~Chuang",
  title =        "Quantum Computation and Quantum Information",
  publisher =    "Cambridge University Press",
  address =      "Cambridge",
  year =         "2000",
}

@InCollection{Steane,
  author =       {A.~Steane},
  title =        {Quantum Error Correction},
  booktitle =    {Introduction to Quantum Computation and Information},
  publisher =    {World Scientific},
  year =         1998,
  editor =       {H. K. Lo, S. Popescu and T. Spiller}
}

@Misc{Preskill219,
  author =       {J.~Preskill},
  title =        {Lecture Notes for {P}hysics 219: {Q}uantum  Computation},
  howpublished = {Available from {\tt{http://www.theory.caltech.edu/people/preskill/ph219}}},
year={2001}
}
@Misc{Preskill229dontuse,
  author =       {J.~Preskill},
  title =        {Lecture Notes for {P}hysics 229: {Q}uantum Information Theory},
  howpublished = {Available from http://www.theory.caltech.edu/people/preskill/ph229},
year={1999}
}

@Article{shor95,
  author =       {P. W. Shor},
  title =        {Quantum Error-Correction},
  journal =      {Phys. Rev. A},
  year =         1995,
  volume =       52,
  number =       {R2493}
}

@Misc{GF4codes,
  author =       {A. R. Calderbank and E. M. Rains and P. W. Shor and N. J. A. Sloane},
  title =        {Quantum Error Correction via Codes over {GF(4)}},
  howpublished = {{\tt{quant-ph/9608006}}},
  year =         1997
}

@Article{Steane96,
  author =       {A. Steane},
  title =        {Quantum Error Correcting Codes},
  journal =      {Phys. Rev. Lett.},
  year =         1996,
  volume =       77,
  pages =        793
}

% Andrew Steane:
% Quantum Reed-Muller codes
% IEEE Trans. Inf. Theory 45, 1701-1703 (1999).
% Preprint: quant-ph/9608026


@incollection{SteaneCodes,
author={Steane, A.M.},
title={Quantum computing and error correction},
annote={available from {\tt{http://xxx.soton.ac.uk/abs/quant-ph/0304016}}},
note={{\tt{quant-ph/0304016}}},
booktitle={Decoherence and its implications in quantum computation and information transfer},
editor={Turchi, P.E.A. and Gonis, A.},
pages={284-298},
publisher={IOS Press},
 volume = 	 {182},
series={NATO Science Series: Computer \& Systems Sciences},
address={Amsterdam},
year={2001},
isbn={1 58603 211 9}
}

@Article{Steane98,
  author =       {A. Steane},
  title =        {Enlargement of {C}alderbank {S}hor {S}teane Quantum Codes},
  journal =      {IEEE Trans. on Info. Theory},
  year =         1999,
 volume=45,
 pages={2492-2495},
 note={{\tt{quant-ph/9802061}}}
}

@Article{gottesman,
  author =       {D. Gottesman},
  title =        {A Class of Quantum Error-Correcting Codes saturating the Quantum Hamming Bound},
  journal =      {Phys. Rev. A},
  year =         1996,
  volume =       54,
  pages =        1862
}

@Article{Orthog_geometry,
  author =       {A. R. Calderbank and E. M. Rains and P. W. Shor and N. J. A. Sloane},
  title =        {Quantum Error-Correction and Orthogonal Geometry},
  journal =      {Phys. Rev. Lett.},
  year =         1997,
  volume =       78,
  pages =        405
}

@Article{SteaneCSS,
  author =       {A. Steane},
  title =        {Multiple Particle Interference and Quantum Error Correction},
  journal =      {Proc. Roy. Soc. Lond. A},
  year =         1996,
  volume =       452,
  pages =        2551
}


@Article{Landauer,
  author =       {R. Landauer},
  title =        {Irreversibility and heat generation in the computing process},
  journal =      {IBM J. Res. Dev.},
  year =         1961,
  volume =       5,
  pages =        183
}

@article{CaldShor96,
title={Good Quantum Error-Correcting Codes Exist},
    author={A. R. Calderbank and Peter W. Shor},
address={AT\&T Research},
journal={Phys. Rev. A}, Volume=54, Number=2, pages={1098-1106}, year=1996,
note={{\tt{quant-ph/9512032}}}
}


@article{Shor,
author={Shor, P. W.},
title={Scheme for reducing decoherence in quantum computer memory},
journal={Phys. Rev. A},
volume={52},
number={R},
pages={2493-6},
year={1995},
annote={ Shor, P.W. Scheme for reducing decoherence in quantum computer memory. Phys. Rev. A {\bf 52}, R2493-6 (1995). }
}

@book{Lo2001,
author={Lo, H.-K. and Popescu, S. and Spiller, T.},
title={Introduction to quantum computation and information},
publisher={World Scientific},
year={2001}
}

@Article{ShorCSS,
  author =       {A. R. Calderbank and P. W. Shor},
  title =        {Good Quantum Error-Correcting Codes Exist},
  journal =      {Phys. Rev. A},
  year =         1996,
  volume =       54,
  pages =        1098,
note={{\tt{quant-ph/9512032}}}
}

@article{LitsynEnumerator,
author={S. Litsyn and Shevelev, Vladimir},
title={On ensembles of low-density parity-check codes: asymptotic distance distributions},
journal={IEEE Trans. on Info. Theory},
volume={48},number={4},year={2002},pages={887-908}
}

@Misc{Ashikhmin,
  author =       {A. Ashikhmin and S. Litsyn and M. A. Tsfasman},
  title =        {Asymptotically Good Quantum Codes},
  howpublished = {{\tt{quant-ph/0006061}}},
  year =         2000
}

@article{Matsumoto2002,
author={R. Matsumoto},
title={Improvement of {A}shikhmin--{L}itsyn--{T}sfasman bound for quantum
codes},
  journal =      {IEEE Trans. on Info. Theory},
volume={48},
number={7},
pages={2122-2124},
year={2002},
month={July},
annote={R. Matsumoto, Improvement of Ashikhmin-Litsyn-Tsfasman bound for quantum
codes, IEEE Trans. Inform. Theory, vol. 48, no. 7, pp. 2122-2124, July 2002.}
}

@article{LingChenXing2001,
title={Asymptotically good quantum codes exceeding the {Ashikhmin--Litsyn--Tsfasman} bound},
author={S. Ling and H. Chen and C. Xing},
journal={IEEE   Trans. on Info. Theory},
volume={47},
pages={2055-2058},
annote={
Asymptotically good quantum codes exceeding the Ashikhmin-Litsyn-Tsfasman
bound (S.Ling, H. Chen and C. Xing). IEEE
   Trans. on Info. Theory 47, 2055 -2058 (2001).
},
year={2001}
}


% -----------------------------------
@UNPUBLISHED{WWWturbo,
  key =          {jpl},
  author =       {JPL},
  title =        {Turbo Codes Performance},
  year =         1996,
  month =        {August},
  note =         {Available from {\tt http://www331.jpl.nasa.gov/public/TurboPerf.html}}
}
@UNPUBLISHED{WWWcodes,
  key =          {jpl},
  author =       {JPL},
  title =        {Code Imperfectness},
  year =         1999,
  note =         {{\tt www331.jpl.nasa.gov/public/imperfectness.html}},
  annote =         {{\tt http://www331.jpl.nasa.gov/public/imperfectness.html}}
}


@INPROCEEDINGS{FreyMacKay00c,
author={B. J. Frey},
 TITLE          =" Knowing when to stop", 
 BOOKTITLE      ="Proceedings of the 38th Allerton Conference on Communication, Control, and Computing, Sept.\ 2000",
 EDITOR 	="",
 PUBLISHER	="Allerton House",
 ADDRESS	="Monticello, Illinois",
 YEAR           ="2000",
 PAGES		="",
 ANNOTE ="Date submitted: ; Date accepted: ;  MRAO "}

@Book{frey-97c,
  key =          "Frey",
  author =       "B.~J. Frey",
  title =        "{B}ayesian Networks for Pattern Classification, Data
                  Compression and Channel Coding",
  publisher =    "Department of Electrical and Computer Engineering,
                  University of Toronto",
  address =      "Toronto Canada",
  year =         "1997",
  note =         "Doctoral dissertation available at
                  {\tt http://www.cs.utoronto.ca/\verb+~+frey}"
}

% # B. J. Frey 1998. Graphical Models for Machine Learning and Digital Communication. MIT Press: Cambridge, MA.
% Brendan
@Book{frey-98,
   key =          "Frey",
   author =       "B.~J. Frey",
   title =        "Graphical Models for Machine Learning and Digital
                  Communication",
   publisher =    "MIT Press",
   address =      "Cambridge MA.",
   annote =         {See {\tt http://www.cs.utoronto.ca/\verb+~+frey}},
   year =         "1998"
}

% see also Yang and Ryan Globecom march 20 2001.
% burst noise  for ldpcc
@INPROCEEDINGS{Worthen,
 KEY            ="",
 AUTHOR         ="Worthen, A. P. and Stark, W. E.",
 TITLE          ="Low-Density Parity Check Codes for Fading Channels with Memory",
 BOOKTITLE      ="Proceedings of the 36th Allerton Conference on Communication, Control, and Computing, Sept.\ 1998",
 EDITOR 	="",
 PUBLISHER	="",
 ADDRESS	="",
 YEAR           ="1998",
 PAGES		="117-125" }

@article{Worthen2001,
 AUTHOR         ="Worthen, A. P. and Stark, W. E.",
 TITLE          ="Unified Design of Iterative Receivers Using Factor Graphs",
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={843-849}
} 


@techreport{bwt,
author={Michael Burrows and D. J. Wheeler},
title={A block-sorting lossless data compression algorithm},
year={1994},
institution={Digital SRC},
number={124},
annote={Research Report 124. 10th May 1994}, 
url={ftp://ftp.digital.com/pub/DEC/SRC/research-reports/SRC-124.ps.gz},
annote={If you have trouble finding it, try searching at the
   New Zealand Digital Library, http://www.nzdl.org.}
}



%	SPIN GLASS PAPERS

@TECHREPORT{Yau.tr,
 KEY		="Yau and Wallace",
 AUTHOR		="H. W.  Yau and D. J.  Wallace",
 TITLE		="Basins of 
	Attraction in Sparse Neural Network Models with Persistent Inputs,",
 YEAR		="1990",
 NUMBER		="In preparation",
 INSTITUTION	="Edinburgh University"}

@ARTICLE{Yau,
  AUTHOR = "H W Yau and D J Wallace",
  TITLE = "Enlarging the Attractor Basins of Neural Networks with Noisy
External Fields",
  JOURNAL = "Journal of Physics A: Maths and General",
  YEAR = "1991",
  VOLUME = "24",
  PAGES = "5639--5650"}


@ARTICLE{BDS,
 KEY		="Buhmann et. al.",
 AUTHOR		="J. Buhmann and R. Divko and K. Schulten",
 TITLE		="Associative memory with high information content",
 JOURNAL	="preprint",
 YEAR		="1988",
 VOLUME		="",
 NUMBER		="",
 PAGES		=""}


%	Papers on hop
@ARTICLE{Hopfield82,
 KEY		="Hopfield",
 AUTHOR		="J. J. Hopfield",
 TITLE		="Neural Networks and physical 
	systems with emergent collective computational abilities",
 JOURNAL	="Proc. Natl. Acad. 
	Sci. USA",
 YEAR		="1982",
 VOLUME		="79",
 NUMBER		="",
 PAGES		="2554--8"}

@ARTICLE{Hopfield84,
 KEY		="Hopfield",
 AUTHOR		="J. J. Hopfield",
 TITLE		="Neurons with 
	graded response properties have collective computational properties like those of
	two-state Neurons",
 JOURNAL	="Proc. Natl. Acad. Sci. USA",
 YEAR		="1984",
 VOLUME		="81",
 NUMBER		="",
 PAGES		="3088--92"}

@ARTICLE{Hopfield_Tank,
 KEY		="Hopfield and Tank",
 AUTHOR		="J. J. Hopfield and D. W. Tank",
 TITLE		="Neural Computation of Decisions in Optimization Problems",
 JOURNAL	="Biological Cybernetics",
 YEAR		="1985",
 VOLUME		="52",
 NUMBER		="",
 PAGES		="1-25"}

@ARTICLE{Hopfield87,
 KEY		="Hopfield",
 AUTHOR		="J. J. Hopfield",
 TITLE		="Learning algorithms 
	and probability distributions in feed-forward and feed-back 
	networks",
 JOURNAL	="Proc. Natl. Acad. Sci. USA",
 YEAR		="1987",
 VOLUME		="84",
 NUMBER		="",
 PAGES		="8429--33"}

%	 Discussion of introduction of biases or low levels of activity: see Amit in Network1 
%	 Best ref: 
@ARTICLE{RS89,
 KEY		="Rubin and Sompolinsky",
 AUTHOR		="N. Rubin and H. Sompolinsky",
 TITLE		="Neural Networks with low local firing rates",
 JOURNAL	="Europhys. Lett.",
 YEAR		="1989",
 VOLUME		="8",
 NUMBER		="",
 PAGES		="465"}

%	 they study thetas that look linear in average background but may not be.. 
%	 Applied field references: see 0.14 below. But the first good paper is:
@ARTICLE{EES89,
 KEY		="Engel et. al.",
 AUTHOR		="A. Engel and H. English and A. Schutte",
 TITLE		="Improved retrieval in Neural Networks with external fields",
 JOURNAL	="Europhys Lett.",
 YEAR		="1989",
 VOLUME		="8",
 NUMBER		="",
 PAGES		="393"}

@ARTICLE{Amit87b,
 KEY		="Amit et. al.",
 AUTHOR		="D. J. Amit and H. Gutfreund and H. Sompolinsky",
 TITLE		="Information storage in Neural Networks with low levels of activity",
 JOURNAL	="Phys.\ Rev.\ A",
 YEAR		="1987",
 VOLUME		="35",
 PAGES		="2293-2303"}

%	 Hop capacity: 
@ARTICLE{Amit85,
 KEY		="Amit et. al.",
 AUTHOR		="D. J. Amit and H. Gutfreund and H. Sompolinsky",
 TITLE		="Spin glass models of Neural Networks",
 JOURNAL	="Phys. Rev. A",
 YEAR		="1987",
 VOLUME		="32",
 PAGES		="1007"}

% 	 the above only discusses the case alpha -> 0, constant P, N-> infty. 
% 	 It derives T = 0.46 Tc for hopfield prescription 
% 	 p=0.14N derived in
@ARTICLE{Amit85b,
 KEY		="Amit et. al.",
 AUTHOR		="D. J. Amit and H. Gutfreund and H. Sompolinsky",
 TITLE		="Storing infinite numbers of patterns in a spin glass
		  model of Neural Networks",
 JOURNAL	="Phys. Rev. Lett.",
 YEAR		="1985",
 VOLUME		="55",
 NUMBER		="",
 PAGES		="1530-1533"}

@ARTICLE{Amit87,
 KEY		="Amit et. al.",
 AUTHOR		="D. J. Amit and H. Gutfrend and H. Sompolinsky",
 TITLE		="Statistical mechanics of Neural Networks near saturation",
 JOURNAL	="Ann. Phys. (New York)",
 YEAR		="1987",
 VOLUME		="173",
 PAGES		="30"}

% 	 ^^This one is prob the best 0.14 ref, and 
% 	 has a lot more in it too. It evven discusses applied fields and dismisses 
% 	 them because they imagine the field being fixed, regardless of the cue vector. 
% 	 Blackout is discussed in 
% 	 J-P Nadal, G. Toulouse, J.P Changeux, and S. Dehaene, 1986, Networks of formal 
% 	 Neurons and memory palimpsests. Europhys Lett 1 535
% 	 Blackout = loss of memories due to overload. Their paper suggests weight decay [?] 
% 	 So as to not go above capacity. 
% 	 Pseudoinverse refs can be found referred to in Gardner 1987 below. They get cap =1. 
% 	 alpha =2 is derived in 
@ARTICLE{Gardner,
 KEY		="Gardner",
 AUTHOR		="E. J. Gardner",
 TITLE		="Maximum storage capacity 
	of Neural Networks",
 JOURNAL	="Europhys. Lett.",
 YEAR		="1987",
 VOLUME		="4",
 PAGES		="481"}


% 	 Other Gardner refs: 
% 	B. Derrida and E. J. Gardner and A. Zippelius, Europhys Lett 4 1987 167
% 	 E.J. Gardner B. Derrida and Mottishaw, J. Phys (paris) 48 1987 441
% 	 E.J. Gardner  J. Phys A 19 1986 L 1047
% 	 A. Bruce, E.J. Gardner and D.J. Wallace, J. Phys A 20 1987 A 2909
% 		`Dynamics and Statistical Mechanics of the {H}opfield Model'
% 	 The latter two are meant to include derivariton of 0.14-like results. 
% 
@ARTICLE{Amit85,
 KEY		="Amit et. al.",
 AUTHOR		="D. J. Amit and H. Gutfreund and H. Sompolinsky",
 TITLE		="
	Statistical mechanics of Neural Networks near saturation",
 JOURNAL	="Ann. Phys. (New York)",
 YEAR		="1985",
 VOLUME		="173",
 PAGES		="30"}

@ARTICLE{Amit90,
 KEY		="Amit et. al.",
 AUTHOR		="D. J. Amit and G. Parisi and S. Nicolis",
 TITLE		="Neural Potentials as stimuli for attractor Neural Networks",
 JOURNAL	="Network",
 YEAR		="1990",
 VOLUME		="1 ",
 NUMBER		="1",
 PAGES		="75-88"}

@ARTICLE{Galland93,
 KEY		="",
 AUTHOR		="C. C. Galland",
 TITLE		="The Limitations of Deterministic {B}oltzmann Machine Learning",
 JOURNAL	="Network",
 YEAR		="1993",
 VOLUME		="4",
 NUMBER		="3",
 PAGES		="355-379"}
%
% Boosting
%
@article{boosting97,
 author={Y. Freund and Schapire, R.E.},
 title={A decision-theoretic generalization of on-line learning and an application to boosting},
 year={1997},
 journal={Journal of Computer and System Sciences},
 volume={55},
 number={1},
 pages={119-139},
} 
% 
@inproceedings{boosting95,
 author={Y. Freund and Schapire, R.E.},
 title={A decision-theoretic generalization of on-line learning and an application to boosting},
 year={1995},
 booktitle={Proceedings of the Second European Conference on Computational Learning Theory},
 pages={23-37},
} 
% 
@inproceedings{boosting96,
 author={Y. Freund and Schapire, R.E.},
 title={Experiments with a New Boosting Algorithm},
 year={1996},
 booktitle={Proceedings of the Thirteenth International Conference on Machine Learning},
} 
% 
@Article{Levenshtein66,
  author =       {V. I. Levenshtein},
  title =        {Binary Codes capable of correcting deletions, insertions,
 and reversals},
  journal =      {Soviet Physics -- Doklady},
  year =         {1966},
  volume =       {10},
  number =       {8},
  pages =        {707-710},
  month =        {February}
}

@Article{Ferreira97,
  author =       {H.C. Ferreira and W.A. Clarke and A.S.J. Helberg and K.A.
S. Abdel-Ghaffar and A.J. Han Vinck},
  title =        {Insertion/Deletion Correction with Spectral Nulls},
  journal =      {IEEE Trans. Info. Theory},
  year =         {1997},
  volume =       {43},
  number =       {2},
  pages =        {722-732},
  month =        {March},
}




@inproceedings{boosting98,
 author={Schapire, R.E. and Singer, Y.},
 title={Improved Boosting Algorithms using Confidence-rated Predictions},
 year={1998},
 booktitle={Proceedings of the Eleventh Annual Conference on Computational Learning Theory},
} 
% 
@unpublished{boostingFHT98,
 author={Friedman, J. and Hastie, T. and Tibshirani, R.},
 title={Additive Logistic Regression: a Statistical View of
Boosting},
 note={Tech. report available from 
 {\verb|http://www-stat.stanford.edu/~tibs/research.html|}},
 year={1998},
}
%
@article{boosting90,
 author={R. Schapire},
 title={The Strength of Weak Learnability},
 journal={Machine learning},
 year={1990},
 Volume={5},
 number={2},
}

@InCollection{mihaljevic_and_golic92,
 KEY		="Mihaljevic, M.J. and Golic, J.D.",
 AUTHOR		="M. J. Mihaljevi\'c and J. D. Goli\'c",
 TITLE		="A Fast Iterative Algorithm for a Shift Register Initial 
			State Reconstruction given the Noisy Output Sequence",
 BOOKTITLE	="Advances in Cryptology --   AUSCRYPT'90",
  series = 	 "Lecture Notes in Computer Science Series",
 YEAR		=1992,
 VOLUME		=453,
  publisher =	 "Springer",
 PAGES		="165-175"}
% should this date be 1990?

@InCollection{mihaljevic_and_golic93,
 KEY		="Mihaljevic, M.J. and Golic, J.D.",
 AUTHOR		="M. J. Mihaljevi\'c and J. D. Goli\'c",
 TITLE		="Convergence of a {B}ayesian iterative
		  error-correction procedure on a noisy shift register sequence",
 BOOKTITLE	="Advances in Cryptology -- EUROCRYPT 92", 
 series 	="Lecture Notes in Computer Science Series",
 VOLUME		=658,
 publisher 	="Springer",
 PAGES 		="124-137",
 YEAR=1993}
% check year

@ARTICLE{Anderson93,
 KEY		="Anderson",
 AUTHOR		="R. J. Anderson",
 TITLE		="Faster Attack on Certain Stream Ciphers",
 JOURNAL	="Electronics Letters",
 YEAR		="1993",
 VOLUME		="29",
 NUMBER		="15",
 PAGES		="1322-1323"}

@INPROCEEDINGS{Anderson94,
 KEY		="Anderson",
 AUTHOR		="R. J. Anderson",
 TITLE		="Searching for the optimum correlation attack",
 BOOKTITLE      ="Fast Software Encryption (Proceedings of 1994 K.U. Leuven Workshop on
		  Cryptographic Algorithms)",
  editor =	 "B. Preneel",
  series =	 "Lecture Notes in Computer Science Series",
 YEAR		=1995,
  publisher =	 "Springer",
 PAGES		="179-195"}
% `` Searching for the optimum correlation attack", in Preproceedings of
% the KU Leuven Workshop on Cryptographic Algorithms, pp 56 -- 62; and in
% full proceedings to be published in Springer LNCS series
% 
% Incidentally, the similar reference for your paper is pp 86 -- 98. The
% preproceedings will be posted tomorrow,



@InProceedings{JPLcode,
  author = 	 "L. Swanson",
  title = 	 "A New Code for {G}alileo",
  pages =	 "94-95",
  booktitle =	 "Proc. 1988 IEEE International Symposium Info. Theory",
  year =	 "1988",
annote={year? unsure}
}
% (3) Unfortunately the JPL guys never published anything 
% external about the Galileo Code. I could look up an internal JPL
% report, but there was at least an announcement of the code at
% the 1988 Information Theory Symposium

@article{McEliece1987,
  title={The Capacity of the {H}opfield Associative Memory},
  author={McEliece, R. J. and Posner, E. C. and Rodemich, E. R. and Venkatesh, S. S.},
  journal={IEEE Trans. on Info. Theory},
  year={1987},
  volume={33},
  number={4},
  pages={461-482}
}

@book{McEliece77firstEd,
  author = 	 "R. J. McEliece",
  title = 	 "The Theory of Information and Coding: A Mathematical
                 Framework for Communication",
  year = 	 1977,
  publisher="Addison-Wesley",
  address="Reading, MA",
  annote="Cambridge: Cambridge University Press, 1984,
                 [Univ. Lib.] 351:5.c.95.153
                 South Front 4"}

@book{McEliece77,
  author = 	 "R. J. McEliece",
  title = 	 "The Theory of Information and Coding",
  year = 	 2002,
  publisher="Cambridge University Press",
  address="Cambridge",
edition="Second"}

@article{Bhattacharyya,
author={Bhattacharyya, A.},
title={On a measure of divergence between two statistical 
 populations defined by their probability distributions},
journal={Bull. Calcutta Math. Soc.},
volume={35},
year={1943},
pages={99-110},
annote={Bhattacharyya, A. On a measure of divergence between two statistical 
 populations defined by their probability distributions. Bull. 
 Calcutta Math. Soc. 35 (1943), pp. 99-110.}
}



@Article{Gallager62,
  author = 	 "Gallager, R. G.",
  title = 	 "Low Density Parity Check Codes",
  journal =	 "IRE Trans. Info. Theory",
  year =	 1962,
  volume =	 "IT-8",
  pages =	 "21-28",
  month =	 "Jan",
  annote =	 "cited by Mihaljevic"
}


@Book{Guggenheim52,
  author =	 {E. A. Guggenheim},
  title = 	 {Mixtures},
  publisher = 	 {Oxford University Press},
  year = 	 1952
}




@Article{FowlerGuggenheim40,
  author =	 {R. H. Fowler and E. A. Guggenheim},
  title = 	 {},
  journal = 	 {Proc. Roy. Soc. A},
  year = 	 {1940},
 key = 	 {},
 volume = 	 {174},
 number = 	 {},
 pages = 	 {189}
}

@Book{Hinch,
  author = 	 "Hinch, E. J.",
  title = 	 "Perturbation Methods",
  publisher = 	 "Cambridge University Press",
  year = 	 "1991"
}
% Author:         Hinch, E. J.
% Title:          Perturbation methods/ E.J. Hinch
%                 Cambridge: Cambridge University Press, 1991
%                 xi,160p; 24cm
% Series title:   Cambridge texts in applied mathematics
% Subjects:       Perturbation (Mathematics)
% 
% Location:       [Univ. Lib.] 349:5.c.95.496
% Location:       [Univ. Lib.] 1994.9.1478 (paperback issue)
% 349:5.c.95.496  South Front 4
%                 Not on loan
% 1994.9.1478 (paperback issue)
%                 Order in West Room (Central Desk)
%                 Not ordinarily borrowable

@book{ORuanaidh,
 Author={O Ruanaidh, J. J. K. and Fitzgerald, W. J.},
 Title={Numerical {B}ayesian methods applied to signal processing},
 address={New York},
 publisher={Springer}, 
 year={1996},
 series={Statistics and Computing Series}
}
% Location:       [Trinity College] RR 335 O 3
% recommended for rayleigh

@Book{Khinchin,
  author = 	 "A. I. Khinchin",
  title = 	 "Mathematical Foundations of Information Theory",
  publisher = 	 "Dover",
  year = 	 1957,
  address =	 "New York",
  annote =	 "Cavendish 39 K 5."
}

@Book{Schwartz,
  author = 	 "L. S. Schwartz",
  title = 	 "Principles of Coding, Filtering and Information Theory",
  publisher = 	 "Spartan Books",
  year = 	 1963,
  address =	 "Baltimore",
  annote =	 "Cav: 39 S 1"
}

@article{Shannon48,
 author = 	 "Shannon, C. E.",
  title = 	 "A Mathematical Theory of Communication",
 journal="Bell Sys. Tech. J.",
 volume = 27,
 pages ="379-423, 623-656",
 year = 1948
}
  
@Book{Shannon&Weaver,
  author = 	 "Shannon, C. E. and Weaver, W.",
  title = 	 "The Mathematical Theory of Communication",
  publisher = 	 "Univ. of Illinois Press",
  year = 	 1949,
  address =	 "Urbana",
  annote =	 "Cav: 39 S 2"
}

@book{shannon93,
 author = 	 {Shannon, C. E.},
 title = {Collected Papers},
 publisher = {IEEE Press},
 address ={New York},
 year = {1993},
 editor =  {N. J. A. Sloane and A. D. Wyner}
}
%  editor={N. J. A. Sloane and A. D. Wyner}, 
% 84 S 101

@incollection{shannon44,
 author = 	 {Shannon, C. E.},
 title = {The Best Detection of Pulses},
 booktitle = {Collected Papers of Claude Shannon},
 publisher = {IEEE Press},
  editor={N. J. A. Sloane and A. D. Wyner},
 year = {1993},
pages={148--150},
address={New York}
}


@Book{Pierce,
  author = 	 "Pierce, J. R.",
  title = 	 "An Introduction to Information Theory",
  publisher = 	 "Dover",
  year = 	 1980,
  edition =	 2,
  address =	 "New York",
  annote =	 "Subtitle: Symbols, Signals and Noise. Cav: 39 P 5."
}

@Book{Peretto,
  author = 	 "Peretto, P.",
  title = 	 "An Introduction to the Modeling of Neural Networks",
  publisher = 	 "Cambridge University Press",
  year = 	 1992,
  annote =	 "Cav: 39 P 8"
}
% Has replica theory then temporal nets. 
% linear separability, the Cover limit
% Perceptrions
% Backprop (but with J_ij as the weights !
% Kohonen nets
% nets for optimization
% ------ looks a reasonable book.

@book		( kohonen-84,
key	=	"Kohonen" ,
author	=	"Kohonen, T." ,
title	=	"Self-Organization and Associative Memory (2nd
edition)" ,
publisher=	"Springer" ,
address	=	"Berlin" ,
year	=	"1984" 
)
@TechReport{Honkela96tr,
  author =       {Timo Honkela and Samuel Kaski and Krista Lagus and
                  Teuvo Kohonen},
  title =        {Newsgroup exploration with {WEBSOM} method and
                  browsing interface},
  institution =  {Helsinki University of Technology, Laboratory of
                  Computer and Information Science},
  year =         1996,
  number =       {A32},
  address =      {Espoo, Finland}
}

@Article{Honkela96alma,
  author =       {Timo Honkela and Samuel Kaski and Krista Lagus and
                  Teuvo Kohonen},
  title =        {Self-organizing maps of document collections},
  journal =      {ALMA},
  year =         1996,
  volume =       1,
  number =       2,
  note =         {Electronic Journal, address http://www.diemme.it/~luigi/alma.html}
}

@InCollection{Lagus96,
  author =       {Krista Lagus and Samuel Kaski and Timo Honkela and
                  Teuvo Kohonen},
  title =        {Browsing digital libraries with the aid of
                  self-organizing maps},
  booktitle =    {Proceedings of the Fifth International World Wide
                  Web Conference WWW5, May 6-10, Paris, France},
  publisher =    {EPGL},
  year =         1996,
  volume =       {Poster Proceedings},
  pages =        {71-79}
}

@InCollection{Honkela96,
  author =       {Timo Honkela and Samuel Kaski and Krista Lagus and
                  Teuvo Kohonen},
  title =        {Exploration of full-text databases with
                  self-organizing maps},
  booktitle =    {Proceedings of the ICNN96, International Conference
                  on Neural Networks},
  publisher =    {IEEE Service Center},
  year =         1996,
  volume =       {I},
  address =      {Piscataway, NJ},
  pages =        {56-61}
}

@InCollection{Kohonen96icann,
  author =       {Teuvo Kohonen and Samuel Kaski and Krista Lagus and
                  Timo Honkela},
  title =        {Very large two-level {SOM} for the browsing of newsgroups},
  booktitle =    {Proceedings of ICANN96, International Conference on
                  Artificial Neural Networks, Bochum, Germany, July
                  16--19, 1996},
  publisher =    {Springer},
  year =         1996,
  editor =       {C. von der Malsburg and W. von Seelen and
                  J. C. Vorbr{\"u}ggen and B. Sendhoff},
  series =       {Lecture Notes in Computer Science, vol. 1112},
  address =      {Berlin},
  pages =        {269-274}
}

@InCollection{Lagus96step,
  author =       {Krista Lagus and Timo Honkela and Samuel Kaski and
                  Teuvo Kohonen},
  title =        {{WEBSOM} -- A Status Report},
  booktitle =    {Proceedings of STeP'96, Finnish Artificial
                  Intelligence Conference},
  publisher =    {Finnish Artificial Intelligence Society},
  year =         1996,
  editor =       {Jarmo Alander and Timo Honkela and Matti Jakobsson},
  address =      {Vaasa, Finland},
  pages =        {73-78}
}

@InCollection{Lagus96kdd,
  author =       {Krista Lagus and Timo Honkela and Samuel Kaski and
                  Teuvo Kohonen},
  title =        {Self-organizing maps of document collections: {A}
                  new approach to interactive exploration},
  booktitle =    {Proceedings of the Second International Conference
                  on Knowledge Discovery and Data Mining},
  publisher =    {AAAI Press},
  year =         1996,
  editor =       {Evangelios Simoudis and Jiawei Han and Usama Fayyad},
  address =      {Menlo Park, CA},
  pages =        {238-243}
}

@InCollection{Kaski96wcnn,
  author =       {Samuel Kaski and Timo Honkela and Krista Lagus and
                  Teuvo Kohonen},
  title =        {Creating an order in digital libraries with
                  self-organizing maps},
  booktitle =    {Proceedings of WCNN'96, World Congress on Neural
                  Networks, September 15-18, San Diego, California},
  publisher =    {Lawrence Erlbaum and INNS Press},
  year =         1996,
  address =      {Mahwah, NJ},
  pages =        {814-817}
}

@book{Polya,
 title={Induction and Analogy in Mathematics},
 author={G. Polya},
 publisher={Princeton University Press},
 address={Princeton, NJ},
 annote={New Jersey},
 year={1954},
 annote={Volume 1 of Mathematics and Plausible Reasoning}
}
@Article{Kaski97thesis,
  author =       {Samuel Kaski},
  title =        {Data Exploration Using Self-Organizing Maps},
  journal =      {Acta Polytechnica Scandinavica, Mathematics,
                  Computing and Management in Engineering Series No.~82},
  year =         1997,
  month =        {March},
  note =         {DTech Thesis, Helsinki University of Technology, Finland}
}

@Article{Kaski97npl,
  author =       {Samuel Kaski},
  title =        {Computationally Efficient Approximation of a
                  Probabilistic Model for Document Representation in
                  the {WEBSOM} Full-Text Analysis Method},
  journal =      {Neural Processing Letters},
  year =         1997,
  volume =       5,
  pages =        {139-151}
}

@InCollection{Honkela97wsom,
  author =       {Timo Honkela and Samuel Kaski and Krista Lagus and
                  Teuvo Kohonen},
  title =        {{WEBSOM} -- Self-Organizing Maps of Document Collections},
  booktitle =    {Proceedings of WSOM'97, Workshop on Self-Organizing
                  Maps, Espoo, Finland, June 4-6},
  publisher =    {Helsinki University of Technology, Neural Networks
                  Research Centre},
  year =         1997,
  address =      {Espoo, Finland},
  pages =        {310-315},
}

@InCollection{Lagus97,
  author =       {Krista Lagus},
  title =        {Map of WSOM'97 Abstracts -- Alternative Index},
  booktitle =    {Proceedings of WSOM'97, Workshop on Self-Organizing
                  Maps, Espoo, Finland, June 4-6},
  publisher =    {Helsinki University of Technology, Neural Networks
                  Research Centre},
  year =         1997,
  address =      {Espoo, Finland},
  pages =        {368-372}
}

@InCollection{Kohonen97icnn,
  author =       {Teuvo Kohonen},
  title =        {Exploration of Very Large Databases by
                  Self-Organizing Maps},
  booktitle =    {Proceedings of ICNN'97, International Conference on
                  Neural Networks},
  publisher =    {IEEE Service Center},
  year =         1997,
  address =      {Piscataway, NJ},
  pages =        {PL1-PL6}
}

@InCollection{Honkela98klass,
  author =       "T. Honkela and S. Kaski and T. Kohonen and K. Lagus",
  title =        "Self-Organizing Maps of Very Large Document
                  Collections: Justification for the {WEBSOM} method",
  booktitle =    "Classification, Data Analysis, and Data Highways",
  publisher =    "Springer",
  year =         1998,
  editor =       "I. Balderjahn and R. Mathar and M. Schader",
  pages =        "245-252",
  address =      "Berlin"
}


@Book{Maxwells_demon,
  author = 	 "H. S. Leff and A. F. Rex",
  title = 	 "Maxwell's Demon: Entropy, Information, Computing",
  publisher = 	 "Adam Hilger",
  year = 	 1990,
  address =	 "Bristol",
  annote =	 "Cav: 39 L 8. A magnificent collection of papers on
		  this beast. Szilard (1929) made the connection of
		  entropy and information. Then the `light emission'
		  solution came along. Then the erasure of information
		  finally. The paper by Bennet at the end is very
		  good. Discusses Landauer's proof of entropy increase
		  during certain computational operations."
}

@Book{Hamming,
  author = 	 "Hamming, R. W.",
  title = 	 "Coding and Information Theory",
  publisher = 	 "Prentice-Hall",
  year = 	 1986,
  address =	 "Englewood Cliffs, NJ",
  edition =	 "2",
  annote =	 "Cav: 39 H 4"
}

@Book{HammingP,
  author = 	 "Hamming, R. W.",
  title = 	 "The Art of Probability",
  publisher = 	 "Addison Wesley",
  year = 	 1991,
  address =	 "Redwood City, CA",
  annote =	 {13 H 16}
}



@Book{Ash,
  author =       "Ash, R.",
  title =        "Information Theory",
  publisher =    "Interscience publishers",
  year =         1965,
  address =      "New York",
  annote =       "Cav: 39 A 1. Emphasizes the complementary Shannon
                  and Wiener approaches. Studies Shannon."
}
% ref on ``R0"
% international zurich seminar on communications 1974
% referenced in G Ungerbock 
% `IEEE trans info theory 1982' trellis coded modulation
% CHANNEL CODING WITH MULTILEVEL PHASE SIGNALS 
%   AU: UNGERBOECK_G    
%   NA: IBM,ZURICH RES LAB,CH-8803 RUSCHLIKON,SWITZERLAND
%   JN: IEEE TRANSACTIONS ON INFORMATION THEORY 1982 Vol.28 No.1 pp.55-67
%   CR: ANDERSON_JB, 1976 Vol.12 p.587, ELECTRON LETT
%       ANDERSON_JB, 1978 Vol.24 p.703, IEEE T INFORM THEORY 
%       AULIN_T, 1980 A2, 1980 P INT ZUR SEM D 
%       DIGEON_A, 1977 Vol.25 p.1238, IEEE T COMMUN
%       FORNEY_GD, 1970 Vol.16 p.720, IEEE T INFORMATION T
%       FORNEY_GD, 1973 Vol.61 p.268, P IEEE     
%       GALLAGER_RG, 1968 p.74, INFORMATION THEORY R
%       LARSEN_KJ, 1972 Vol.18 p.437, IEEE T INFORM THEORY
%***%       MASSEY_JL, 1974 E2, 1974 P INT ZUR SEM D    
%       ODENWALDER_JP, 1973, NASA CR114561 LINK C   
%       PAASKE_E, 1974 Vol.20 p.683, IEEE T INFORM THEORY
%       TAYLOR_DP, 1979, CRL68 MCMAST U REP 
%       UNGERBOECK_G, 1976, 1976 INT S INF THEOR
%       WOZENCRAFT_JM, 1965 p.318, PRINCIPLES COMMUNICA
%
% see also
% viterbi and omura


% normal graph aka GSR
@article{Forney2001,
  author = 	 "Forney, Jr., G. D.",
 TITLE          ="Codes on Graphs: Normal Realizations",
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={520-548}
} 
@PhdThesis{Forney63,
  author = 	 "Forney, Jr., G. D.",
  title = 	 "Concatenated Codes",
type={PhD},
  school = 	 "MIT",
  year = 	 1963
}

@Book{Gallager63,
  author = 	 "Gallager, R. G.",
  title = 	 "Low Density Parity Check Codes",
  publisher = 	 "MIT Press",
  year = 	 1963,
  address =	 "Cambridge, MA", 
 series = "MIT Research monograph series",
 number = "21",
note={Available from {\tt{http://www.inference.phy.cam.ac.uk/mackay/gallager/papers/}}}
}
% CL: [Computer Laboratory] Y256

@Book{Forney66,
  author = 	 "Forney, Jr., G. D.",
  title = 	 "Concatenated Codes",
  publisher = 	 "MIT Press",
  address =	 "Cambridge, MA", 
  year =	 "1966"
}
% MIT research monograph 37

@TechReport{Massey63,
  author = 	 "J. L. Massey",
  title = 	 "Threshold decoding",
  institution =  "MIT",
  year = 	 1963,
  address =	 "Cambridge, MA",
  number =	 410,
  annote =	 "[Computer Laboratory] V5 135"
}

@incollection{vanlint71,
  author = 	 {van Lint, J. H.},
  title = 	 {Nonexistence theorems for perfect error-correcting codes},
  booktitle = 	 {Computers in Algebra and Number Theory, volume IV, SIAM--AMS Proceedings},
  year = 	 {1971},
}

%     Computers in algebra and number theory 
%     Symposium in applied mathematics of the American Mathematical Society and the Society for Industrial and
%     Applied Mathematics 
%     March 1970 
%     New York, U.S.A. 
%     Proceedings: Birkhoff G., Hall M., A.M.S., Providence, 1971 
%     ISBN: 0-8218-1323-4  [Pure Maths] QA150.S9 1970

@article{tietavainen73,
  author = 	 {Tiet\"av\"ainen, A.},
  title = 	 {On the nonexistence of perfect codes over finite fields},
 journal = 	 {SIAM J. Appl. Math.},
 volume={24},
 pages={88-96},
  year = 	 {1973},
}
@article{Etzion1994,
  title={Perfect Binary Codes: Constructions, Properties, and Enumeration},
  author={Etzion, T. and Vardy, A.},
  journal={IEEE Trans. on Info. Theory},
  year={1994},
  volume={40},
  number={3},
  pages={754-763},
  abstract={Properties of nonlinear perfect binary codes are investigated and 
    several new constructions of perfect codes are derived from these 
    properties. An upper bound on the cardinality of the intersection of 
    two perfect codes of length n is presented, and perfect codes whose 
    intersection attains the upper bound are constructed for all n. As an
    immediate consequence of the proof of the upper bound we obtain a 
    simple closed-form expression for the weight distribution of a 
    perfect code. Furthermore, we prove that the characters of a perfect 
    code satisfy certain constraints, and provide a sufficient condition 
    for a binary code to be perfect. The latter result is employed to 
    derive a generalization of the construction of Phelps, which is shown
    to give rise to some perfect codes that are nonequivalent to the 
    perfect codes obtained from the known constructions. Moreover, for 
    any m greater-than-or-equal-to 4 we construct full-rank perfect 
    binary codes of length 2m -- 1. These codes are obviously 
    nonequivalent to any of the previously known perfect codes. 
    Furthermore the latter construction exhibits the existence of full-
    rank perfect tilings. Finally, we construct a set of 2(2cn) 
    nonequivalent perfect codes of length n, for sufficiently large n and
    a constant c = 0.5 -- epsilon. Precise enumeration of the number of 
    codes in this set provides a slight improvement over the results 
    previously reported by Phelps.}
}

@Book{macwilliams&sloane,
  author = 	 "MacWilliams, F. J. and Sloane, N. J. A.",
  title = 	 "The Theory of Error-correcting Codes",
  publisher = 	 "North-Holland",
  year = 	 1977,
  address =	 "Amsterdam",
  annote =	 "Cav: 39 M 2; [Univ. Lib.] 349:1.c.95.356;
                 South Front 4"
}

@incollection{Massey77,
  author = 	 "J. L. Massey",
  title = 	 "Coding and Complexity",
  publisher = 	 "Springer",
  year = 	 1977
}

@book{lincostello83,
annote={Shu Lin and Daniel J. Costello},
  author = 	 "S. Lin and Costello, Jr., D. J.",
  title = 	 "Error Control Coding: Fundamentals and Applications",
  publisher = 	 "Prentice-Hall",
year={1983},
address={Englewood Cliffs, New Jersey},
ISBN={013283796X},
  camannote =	 "[Univ. Lib.] 431.c.98.288
                 South Front 6
                 [King's College] BUF Lin"
}
% was {lin&costello,
%                  On loan, issued on 30 Nov 1994 16:40 
%                  Due back on 25 Jan 1995


@TechReport{McEliece78,
  author = 	 "R. J. McEliece",
  title = 	 "A Public-key Cryptosystem Based on Algebraic Coding Theory",
  institution =  "JPL",
  year = 	 1978,
  number =	 "DSN 42-44",
  address =	 "Pasadena"
}
% The McEliece Public-Key Cryptosystem
%
% Define a set of correctable error vectors Z = { z : low weight }
% Encryption:
%    E = S G P (left to right)
% where S is random invertible, G is a code with an efficient decoding
% 		  algm, P is a permutation matrix.
% Decryption: apply PT, decode, apply S^.
% Public key is the specification of Z and the matrix E. Secret key =
% 		  S, P, decoder.

@Article{BMT78,
  author = 	 "Berlekamp, E. R. and R. J. McEliece and van Tilborg,
		  H. C. A.",
  title = 	 "On the intractability of certain coding problems",
  journal =	 "IEEE Trans. on Info. Theory",
  year =	 1978,
  volume =	 24,
  number =	 3,
  pages =	 "384-386"
}
% shows that the general decoding problem for linear codes is NP-complete.

@BOOK{Blahut,
	AUTHOR	="R. E. Blahut",
	TITLE 	="Principles and Practice of Information Theory",
	YEAR	=1987,
	PUBLISHER	="Addison-Wesley",
	ADDRESS ="New York"}

@Book{gellmann,
  author = 	 "M. Gell-Mann",
  title = 	 "The Quark and the Jaguar",
  publisher = 	 "nk",
  year = 	 1994,
  address =	 "nk"
}



@Book{Deco96,
  author = 	 "G. Deco and D. Obradovic",
  title = 	 "An Information-Theoretic Approach to Neural Computation",
  publisher = 	 "Springer",
  year = 	 1996, 
 annote={50 dollars}
}

@Article{Cover65,
  author = 	 "T. M. Cover",
  title = 	 "Geometrical and Statistical Properties of Systems of
		  Linear Inequalities with Applications in Pattern
		  Recognition",
  journal =	 "IEEE Trans. on Electronic Computers",
  year =	 1965,
  volume =	 14,
  pages =	 "326-334"
}

@BOOK{Cover&Thomas,
	AUTHOR	="T. M. Cover and J. A. Thomas",
	TITLE 	="Elements of Information Theory",
	YEAR	=1991,
	PUBLISHER	="Wiley",
	ADDRESS ="New York", 
 annote="68 pounds"}

@BOOK{vanTilburg,
	AUTHOR	="van Tilburg, J.",
	TITLE 	="Security-Analysis of a Class of Cryptosystems Based
		  on Linear Error-Correcting Codes",
	YEAR	=1994,
	PUBLISHER	="Royal PTT Nederland NV",
	ADDRESS ="Leidschendam"}
% Ross lent me this. It is quite a good terse book.


@article{Berlekamp80,
	AUTHOR	="Berlekamp, E. R.",
	TITLE 	="The Technology of Error-Correcting Codes",
 volume={68},
 annote={Proceedings of the IEEE, Vol 68, pp 564-593, 1980. },
 number={},
 pages={564-593},
	YEAR	=1980,
 journal={IEEE Trans. on Info. Theory},
}

@BOOK{Berlekamp,
	AUTHOR	="Berlekamp, E. R.",
	TITLE 	="Algebraic Coding Theory",
	YEAR	=1968,
	PUBLISHER	="McGraw-Hill",
	ADDRESS ="New York", 
 annote = "Y432 in CL library"}
% p 231-240 discusses more than t errors with BCH code.
% BCH: each digit in the code corresponds to one element in a GF

@BOOK{Peterson&Weldon,
	AUTHOR	="W. W. Peterson and Weldon, Jr., E. J.",
	TITLE 	="Error-Correcting Codes",
  edition =	 "2nd",
	YEAR	=1972,
	PUBLISHER	="MIT Press",
ADDRESS ="Cambridge, Massachusetts",
annote="Y 179-2 in CL library"}

@ARTICLE{Meier_Staffelbach,
 KEY		="",
 AUTHOR		="W. Meier and O. Staffelbach",
 TITLE		="Fast Correlation Attacks on Certain Stream Ciphers",
 JOURNAL	="J. Cryptology",
 YEAR		="1989",
 VOLUME		="1",
 PAGES		="159-176"}

@BOOK{Feynman:SM,
	AUTHOR	="R. P. Feynman",
	TITLE 	="Statistical Mechanics",
	YEAR	=1972,
	ADDRESS ="New York",
publisher={Addison--Wesley}}
% 	PUBLISHER	="W. A. Benjamin, Inc.",

@BOOK{Stryer,
	AUTHOR	="L. Stryer",
	TITLE 	="Biochemistry",
	YEAR	=1981,
	PUBLISHER	="W.H. Freeman"}
% see page 631 (chapter 26 'the genetic code') for statement 
% `nearly all aa substitutions can be accounted for by a change of a 
% single base'. 

% Derives GCV?  Proves the discrepancy principle is no good. 
% Not the earliest ref for GCV though? Or is 1979 better?
% Mayeb this ref just deals with CV, not GCV. 
@ARTICLE{Wahba:75,
	AUTHOR	="G. Wahba",
	TITLE	="Smoothing Noisy Data with Spline Functions",
	JOURNAL ="Numer. Math.",
	VOLUME  ="24",
	YEAR	="1975",
	PAGES	="383-393"
}

% The ref that Wahba often uses for GCV -- maybe this is the first ref 
% where the formula V(lambda) for use where sigma not known
% and points not equispaced appears. 
@ARTICLE{Craven_Wahba,
	AUTHOR	="P. Craven and G. Wahba",
	TITLE	="Smoothing Noisy Data with Spline Functions",
	JOURNAL ="Numer. Math.",
	VOLUME  ="31",
	YEAR	="1979",
	PAGES	="377-403"
}

% Gamma and its use in estimating sigma appears in Wahba 1983: 
@ARTICLE{Wahba:83,
	AUTHOR	="G. Wahba",
	TITLE	="{B}ayesian `Confidence Intervals' for the 
			Cross-validated Smoothing  Spline",
	JOURNAL ="J.\ R.\ Statist.\ Soc.\ B",
	VOLUME  ="45",
	NUMBER	="1",
	YEAR	="1983",
	PAGES	="133-150"
}


@inproceedings{hintonICA,
author=		"G. E. Hinton and M. Welling and Y. W. Teh and S. Osindero",
title=          "A New View of {ICA}",
booktitle=      "Proceedings of the International Conference on 
                 Independent Component Analysis and Blind Signal Separation",
volume=         "3",
year=           "2001",
url={http://www.cs.toronto.edu/~ywteh/research/gatsbypoe/}
}


@phdthesis{Teh2003,
author=		"Y. W. Teh",
title=		"Bethe Free Energy and Contrastive Divergence Approximations 
		 for Undirected Graphical Models",
school=		"Department of Computer Science, University of Toronto",
year=		"2003"
}


@inproceedings{TehWel2003,
author=		"Y. W. Teh and M. Welling",
title=		"On Improving the Efficiency of the Iterative Proportional
		 Fitting Procedure",
booktitle=	"Proceedings of the International Workshop on Artificial 
		 Intelligence and Statistics",
volume=		"9",
year=		"2003"
}


@article{WelTeh2003,
author=		"M. Welling and Y. W. Teh",
title=		"Approximate Inference in {B}oltzmann Machines",
journal=	"Artificial Intelligence",
volume=		"143",
number=		"1",
pages=		"19-50",
year=		"2003"
}


@inproceedings{TehRow2003,
author=		"Y. W. Teh and S. Roweis",
title=		"Automatic Alignment of Local Representations",
booktitle=	"Advances in Neural Information Processing Systems",
volume=		"15",
year=		"2003"
}


@inproceedings{KakTehRow2002,
author=		"S. Kakade and Y. W. Teh and S. Roweis",
title=		"An Alternate Objective Function for {M}arkovian Fields",
booktitle=	"Proceedings of the International Conference on Machine 
		 Learning",
volume=		"19",
year=		"2002"
}


% was Hinton104.UAI-2001,
@INPROCEEDINGS{HinTeh2001,
  AUTHOR	= "Hinton, Geoffrey E. and Teh, Yee Whye",
  TITLE		= "Discovering Multiple Constraints that are Frequently Approximately Satisfied",
annote="(Invited Talk)",
  BOOKTITLE	= "Uncertainty in Artificial Intelligence: Proceedings of the Seventeenth Conference (UAI-2001)",
  PUBLISHER	= "Morgan Kaufmann",
  ADDRESS	= "San Francisco, CA",
  YEAR		= "2001",
  PAGES		= "227-234"
}
		 

@inproceedings{TehWel2002,
author=		"Y. W. Teh and M. Welling",
title=		"The Unified Propagation and Scaling Algorithm",
booktitle=	"Advances in Neural Information Processing Systems",
volume=		"14",
year=		"2002"
}


@inproceedings{WelTeh2001,
author=		"M. Welling and Y.W. Teh",
title=		"Belief Optimization for Binary Networks:
		 a Stable Alternative to Loopy Belief Propagation",
booktitle=	"Proceedings of the International Conference on Uncertainty 
		 in Artificial Intelligence",
volume=		"17",
year=		"2001"
}


@techreport{TehWel2001,
author=		"Y. W. Teh and M. Welling",
title=		"Passing and Bouncing Messages for Generalized Inference",
number=		"2001-01",
fullnumber=		"GCNU TR 2001-01",
institution=	"Gatsby Computational Neuroscience Unit, University College
		 London",
year=		"2001"
}

@techreport{hinton00training,
  author = "G. Hinton",
  title = "Training products of experts by minimizing contrastive divergence",
number=		"2000-004",
fullnumber=		"GCNU TR 2000-004",
institution=	"Gatsby Computational Neuroscience Unit, University College		 London",
year=		"2001",
  url = "citeseer.nj.nec.com/hinton00training.html" 
, annote = "G. E. Hinton. Training products of experts by minimizing contrastive divergence.
    Technical Report GCNU TR 2000-004, Gatsby Computational Neuroscience Unit,
    University College London, 2000.",
}


@inproceedings{TehHin2001,
author=		"Y. W. Teh and G. E. Hinton",
title=		"Rate-Coded Restricted {B}oltzmann Machines for Face
		 Recognition",
booktitle=	"Advances in Neural Information Processing Systems",
volume=		"13",
year=		"2001"
}


@mastersthesis{Teh2000,
author=		"Y. W. Teh",
title=		"Learning to Parse Images",
school=		"Department of Computer Science, University of Toronto",
year=		"2000"
}


@inproceedings{HinGhaTeh2000,
author=		"G. E. Hinton and Z. Ghahramani and Y. W. Teh",
title=          "Learning to Parse Images",
booktitle=      "Advances in Neural Information Processing Systems",
volume=         "12",
year=           "2000"
}


@inproceedings{BacTeh1998,
author=		"F. Bacchus and Y. W. Teh",
title=		"Making Forward Chaining Relevant",
booktitle=	"Proceedings of the International Conference on Artificial
		 Intelligence Planning Systems",
year=		"1998"
}

% Derives GML for the first time, according to Wahba.
% Also does comparisons and claims that GML is worse than GCV even when 
% the true function is smooth. Maybe not surprising since no care 
% is taken over the priors. 
% manages to derive GML without ever writing down the likelihood 
% that is discussed.
@ARTICLE{Wahba_GML,
	AUTHOR	="G. Wahba",
	TITLE	="A Comparison of {GCV} and {GML} for Choosing the 
			Smoothing Parameter in the Generalized Spline
			Smoothing Problem",
	JOURNAL ="Numer. Math.",
	VOLUME  ="24",
	YEAR	="1975",
	PAGES	="383-393"
}

% Proves that splines are the {B}ayesian MAP for given priors
% Wahba also cites Wahba 1978 for discussion of {B}ayes connection
@ARTICLE{Kimeldorf_Wahba,
	AUTHOR	="G. S. Kimeldorf and  G. Wahba",
	TITLE	="A Correspondence between {B}ayesian 
			Estimation of Stochastic Processes
			and Smoothing by Splines",
	JOURNAL ="Annals of {Math.} Statistics",
	VOLUME  ="41",
	NUMBER	="2",
	YEAR	="1970",
	PAGES	="495-502"
}

% Multiple alphas
% claims to do both GCV and GML...
% also discusses inference of sum model covariance matrix components, 
% I think. 
%	AUTHOR	="C. Gu and G. Wahba",
%	TITLE	="Minimizing {GCV}/{GML} Scores with 
%			Multiple Smoothing Parameters via the 
%			{N}ewton Method",
%	JOURNAL ="SIAM J. Sci. Stat. Comput.",
%	VOLUME  ="12",
%	YEAR	="1991",
%	PAGES	="383-398"
%}
@ARTICLE{Gu_Wahba,
  title={Minimizing {GCV}/{GML} Scores with Multiple Smoothing
		  Parameters via the           {N}ewton Method},
  author={Gu, C. and Wahba, G.},
  journal={{SIAM} Journal on Scientific and Statistical Computing},
  year={1991},
  volume={12},
  number={2},
  pages={383-398},
  abstract={The (modified) Newton method is adapted to optimize generalized cross
          validation (GCV) and generalized maximum likelihood (GML) sources 
          with multiple smoothing parameters. The main concerns in solving the 
          optimization problem are the speed and the reliability of the 
          algorithm, as well as the invariance of the algorithm under 
          transformations under which the problem itself is invariant. The 
          proposed algorithm is believed to be highly efficient for the 
          problem, though it is still rather expensive for large data sets, 
          since its operational counts are (2/3) kn3 + O(n2), with k the number
          of smoothing parameters and n the number of observations. Sensible 
          procedures for computing good starting values are also proposed, 
          which should help in keeping the execution load to the minimum 
          possible. The algorithm is implemented in Rkpack [RKPACK and its 
          applications: Fitting smoothing spline models, Tech. Report 857, 
          Department of Statistics, University of Wisconsin, Madison, WI, 1989]
          and illustrated by examples of fitting additive and interaction 
          spline models. It is noted that the algorithm can also be applied to 
          the maximum likelihood (ML) and the restricted maximum likelihood 
          (REML) estimation of the variance component models.}
}

@BOOK{Wahba90,
 AUTHOR		="G. Wahba",
 TITLE 	        ="Spline Models for Observational Data",
 PUBLISHER	="Society for Industrial and Applied Mathematics.
                 CBMS-NSF Regional Conference series in applied mathematics",
 YEAR		="1990",
}
% Other refs given by Wahba for inference of covariance matrix.
@BOOK{Rao,
	AUTHOR	="C. R. Rao",
	TITLE	="Linear Statistical Inference and its Applications",
	PUBLISHER="Wiley",
	ADDRESS	="New York",
	YEAR	="1973"
}
% above available in college libraries, below not in them or in UL. 
@BOOK{Rao_Kleffe,
	AUTHOR	="C. R. Rao and J. Kleffe",
	TITLE	="Estimation of Variance Components and Applications",
	PUBLISHER="North-Holland",
	ADDRESS	="Amsterdam",
	YEAR	="1988"
}
@ARTICLE{Harville,
	AUTHOR ="Harville, D. A.",
	TITLE	="Maximum Likelihood Approaches to Variance Component 
			Estimation and to Related Problems",
	JOURNAL	="J.\ Amer.\ Statist.\ Assoc.",
	VOLUME	="72",
	YEAR	=1977,
	PAGES	="320-340",
	NOTE	="(with discussion)"}

@ARTICLE{Lindstrom_Baies,
	AUTHOR	="Lindstrom, M. J. and Baies, D. M.",
	TITLE	="{N}ewton-{R}aphson and {EM} 
			Algorithms for Linear Mixed-effects
			Models for Repeated-measures Data",
	JOURNAL	="J.\ Amer.\ Statist.\ Assoc.",
	VOLUME	="83",
	YEAR	=1988,
	PAGES	="1014-1022"}


@INCOLLECTION{Bridle,
 KEY		="Bridle",
 AUTHOR		="J. S. Bridle",
 TITLE		="Probabilistic interpretation of 
			feedforward classification Network outputs, 
			with relationships to statistical 
			pattern recognition",
 BOOKTITLE	="Neuro-computing: Algorithms, Architectures and Applications",
 YEAR		="1989",
 EDITOR		="F. Fougelman--Soulie and J. H\'erault",
 PAGES		="",
 PUBLISHER	="Springer--Verlag"}

@ARTICLE{alphanets,
 KEY		="Bridle",
 AUTHOR		="J. S. Bridle",
 TITLE		="Alpha-Nets: A recurrent `neural' network 
			architecture with a hidden {M}arkov
			model interpretation",
 JOURNAL	="Speech Communication",
 VOLUME		="9",
 NUMBER		="1",
 YEAR		="1990",
 PAGES		="83-92",
}
% John S Bridle
% Speech Communication 9 (1990) 83-92.
% That's Volume 9, No.1, February 1990.
% ISSN 0167-6393
% Publisher: North Holland.
% A more recent version of the AlphaNet stuff, with CSR and better notation,
% is
% An AlphaNet approach to optimising input transformations
% for continuous speech recognition
% J S Bridle and L Dodd,
% Proc ICASSP91 (Toronto)


@TECHREPORT{Fantargs1,
 KEY		="Bridle",
 AUTHOR		="J. S. Bridle",
 TITLE		="The phantom target
        cluster Network: a peculiar relative of (unsupervised) 
        maximum likelihood stochastic modelling and (supervised)
        error backpropagation",
 YEAR		="1988",
 NUMBER		="SP4: 66",
 INSTITUTION	="RSRE"}


@INPROCEEDINGS{Moody,
 KEY		="",
 AUTHOR		="J. E. Moody",
 TITLE		="Note on generalization, 
        regularization  and architecture selection in nonlinear learning 
        systems",
 BOOKTITLE	="First IEEE--SP Workshop on neural networks for signal 
        processing",
 PUBLISHER	="IEEE Computer society press",
 YEAR		="1991",
 PAGES		="847-854"
}

@INPROCEEDINGS{Moody.nips4,
 KEY		="",
 AUTHOR		="J. E. Moody",
 TITLE		="The {\it Effective} Number of Parameters: An
	Analysis of Generalization and Regularization	in Nonlinear Learning 
	Systems",
 BOOKTITLE	="Advances in Neural Information Processing Systems 4",
 EDITOR		="J. E. Moody and S. J. Hanson and R. P. Lippmann",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1992",
 PAGES		="847-854"}

@INPROCEEDINGS{Keeler_Rumelhart.nips4,
 KEY		="",
 AUTHOR		="Keeler, J. and Rumelhart, D. E.",
 TITLE		="A Self-Organizing Integrated Segmentation and
		  Recognition Neural Net",
 BOOKTITLE	="Advances in Neural Information Processing Systems 4",
 EDITOR		="J. E. Moody and S. J. Hanson and R. P. Lippmann",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1992",
 PAGES		="496-503"}

@inproceedings{ bottou98coder,
    author = "L. Bottou and Howard,  P. G. and Y. Bengio",
    title = "The {Z}-Coder Adaptive Binary Coder",
booktitle = "Proceedings
      of the Data Compression Conference,  Snowbird, Utah, March 1998",
pages={13-22},
    year = "1998"
}

@INPROCEEDINGS{Guyon.nips4,
 KEY		="",
 AUTHOR		="I. Guyon and V. N. Vapnik and B. E. Boser 
			and L. Y. Bottou and S. A. Solla",
 TITLE		="Structural risk minimization for character recognition",
 BOOKTITLE	="Advances in Neural Information Processing Systems 4",
 EDITOR		="J. E. Moody and S. J. Hanson and R. P. Lippmann",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1992",
 PAGES		="471-479"}


@BOOK{Bayes.Kalman,
 KEY		="",
 AUTHOR 	="Bar-Shalom, Y. and T.E. Fortmann", 
 TITLE		="Tracking and Data Association",
 PUBLISHER	="Academic Press",
 YEAR		="1988"}
% Bayesian model comparison for Kalman filter models
 
@BOOK{Blake_Zisserman,
 KEY		="",
 AUTHOR 	="Blake, A. and Zisserman, A.", 
 TITLE		="Visual Reconstruction",
 PUBLISHER	="MIT Press",
 YEAR		="1987", 
 ADDRESS        ="Cambridge MA"}

@misc{ fox01particle,
  author = "D. Fox and S. Thrun and W. Burgard and F. Dellaert",
  title = "Particle filters for mobile robot localization",
  text = "Fox D., Thrun S., Burgard W. & Dellaert F. (2001). Particle filters for
    mobile robot localization. In Sequential Monte Carlo Methods in Practice
    (eds A. Doucet, J.F.G. de Freitas and N.J. Gordon). New York: Springer-Verlag.",
  year = "2001",
  url = "citeseer.nj.nec.com/fox01particle.html" }

@book{doucet-defreitas-gordon-2001,
   editor    = {Doucet, A.  and de Freitas, N. and Gordon, N.},
   title     = {{Sequential Monte Carlo Methods in Practice}},
   year      = {2001},
   publisher = {Springer}
}

@book{particlefilters01,
 title={Sequential {M}onte {C}arlo Methods in Practice},
 editor={A. Doucet and J.F.G. de Freitas and N.J. Gordon},
 address={New York},
 publisher={Springer},
  year = "2001",
ISBN={ 0-387-95146-6},
url={http://www-sigproc.eng.cam.ac.uk/~ad2/book.html}
}

@misc{ blake98learning,
  author = "A. Blake and B. North and M. Isard",
  title = "Learning multi-class dynamics",
  text = "A. Blake, B. North, and M. Isard, Learning multi-class dynamics,  in NIPS
    '98, 1998.",
  year = "1998"}

@article{ isard98condensation,
  author = "M. Isard and A. Blake",
  title = "Condensation -- conditional density propagation for visual tracking",
  journal = "International Journal of Computer Vision",
volume={29},
number={1},
 pages={ 5-28},
  year = "1998"
}
@inproceedings{ isard98smoothing,
    author = "Michael Isard and Andrew Blake",
    title = "A Smoothing Filter for {CONDENSATION}",
    booktitle = "{EVVC} (1)",
    pages = "767-781",
    year = "1998",
    url = "citeseer.nj.nec.com/isard98smoothing.html" }
@inproceedings{ isard96visual,
  author = "M. Isard and A. Blake",
  title = "Visual tracking by stochastic propagation of conditional density",
 booktitle = "Proc. Fourth European Conf. Computer Vision",
pages={343-356},
  year = "1996" }





@Article{Terzopoulos,
  author = 	 "D. Terzopoulos",
  title = 	 "Regularization of inverse problems involving
		  discontinuities",
  journal =	 "IEEE PAMI",
  year =	 1986,
  volume =	 8,
  number =	 4,
  pages =	 "417-438"
}

%	STATISTICS AND NEURAL NETS

@ARTICLE{Solla,
 KEY		="Solla",
 AUTHOR		="S. A. Solla and E. Levin and M. Fleisher",
 TITLE		="Accelerated learning in layered Neural Networks",
 JOURNAL	="Complex systems",
 YEAR		="1988",
 VOLUME		="2",
 NUMBER		="",
 PAGES		="625--640"}

@techreport{shokrollahiRaptor,
  author = {Amin Shokrollahi},
  title = {Raptor Codes},
  note = {Available from {\tt{http://algo.epfl.ch/}}},
 url={http://algo.epfl.ch/index.php?p=output_pubs&l=en},
 institution={Laboratoire d'algorithmique, \'Ecole Polytechnique F\'ed\'erale de Lausanne},
 address={Lausanne, Switzerland},
  year = 2003
}

@INPROCEEDINGS{HintonSej,
 KEY		="Hinton and Sejnowski",
 AUTHOR		="G. E. Hinton and T. J.  Sejnowski",
 TITLE		="Optimal Perceptual Inference",
 BOOKTITLE	="Proc. IEEE Conference on Computer Vision and Pattern Recognition",
 YEAR		="1983",
 PAGES		="448--453"}

@INCOLLECTION{Brain_Damage,
 KEY		="LeCun \etal",
 AUTHOR		="LeCun, Y. and J.S. Denker and S. A. Solla",
 TITLE		="Optimal Brain Damage",
 BOOKTITLE	="Advances in Neural Information Processing Systems 2",
 YEAR		="1990",
 EDITOR		="D.S. Touretzky",
 PAGES		="598--605",
 PUBLISHER	="Morgan Kaufmann"}

@INPROCEEDINGS{Luttrell,
 KEY		="Luttrell",
 AUTHOR		="S. P. Luttrell",
 TITLE		="Hierarchical Self-organising Networks",
 BOOKTITLE	="Proc. 1st {IEE} Conf on Artificial Neural Networks, {L}ondon",
 YEAR		="1989",
 PAGES		="2--6"}


% Luttrell 1989c, `Self-organisation: a derivation from first principles 
% 	of a class of learning algorithms' presented at IJCNN 1989, Washington

@INPROCEEDINGS{Luttrell_Maxent,
 KEY		="Luttrell",
 AUTHOR		="S. P. Luttrell",
 TITLE		="The use of 
	{B}ayesian and entropic methods in Neural Network theory",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 EDITOR		="J. Skilling",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1989",
 PAGES		="363--370"}

@ARTICLE{SL.transinformation,
 KEY		="Luttrell",
 AUTHOR		="S. P. Luttrell",
 TITLE		="The use of transinformation in the design of data sampling 
        schemes for inverse problems",
 JOURNAL	="Inverse Problems",
 VOLUME		="1",
 PAGES		="199-218",
 YEAR		="1985"}

@book         {kanerva-88,
key    =      "Kanerva",
author =      "Kanerva, P.",
year   =      "1988",
title  =      "Sparse Distributed Memory",
address =     "Cambridge, MA",
publisher =   "MIT Press"
}


@article{deerwester-dumais-landauer-furnas-harshman-90,
  author =       "S. Deerwester and S. T. Dumais and T. K. Landauer and
G. W.
                  Furnas and R. A. Harshman",
  year =         "1990",
  title =        "Indexing by latent semantic analysis",
  journal =      "Journal of the Society for Information Science",
  volume =       "41",
  number =       "6",
  pages =        "391-407",
  annote =       "first technical LSI paper; good background."
}

@inproceedings{landauer-laham-foltz-98,
  author =       "T. K. Landauer and D. Laham and P. W. Foltz",
  title =        "Learning Human-like Knowledge with Singular Value
                  Decomposition: A Progress Report",
  booktitle =    "Neural Information Processing Systems (NIPS*97)",
  year =         "1998"
}

@article{landauer-dumais-97,
  author =       "T. K. Landauer and S. T. Dumais",
  year =         "1997",
  title =        "Solution to Plato's Problem: The Latent Semantic
Analysis
                  Theory of Acquisition, Induction and Representation of
                  Knowledge",
  journal =      "Psychological Review",
  pages =        "211-240",
  volume =       "104",
  number =       "2"
}

@inproceedings{bartell-cottrell-belew-92,
  author =       "B.T. Bartell and G.W. Cottrell and R.K. Belew",
  year =         "1992",
  title =        "{Latent Semantic Indexing} is an optimal special case
of
                  multidimensional scaling",
  booktitle =      "Proc SIGIR-92",
  publisher =    "ACM Press",
  address =      "New York"
}

@article{hummel-holyoak-97,
  author =       "J. E. Hummel and K. J. Holyoak",
  title =        "Distributed representations of structure: {A} theory
of
                  analogical access and mapping",
  journal =      "Psychological Review",
  year =         1997,
  volume =       104,
  number =       3,
  pages =        "427--466",
  annote =       "LISA paper"
}

@inproceedings{kanerva-96,
  author =       "P. Kanerva",
  year =         1996,
  title =        "Binary spatter-coding of ordered K-tuples",
  volume =       1112,
  pages =        "869-873",
  publisher =    "Springer",
  editor =       "C. von der Malsburg and W. von Seelen and
                  J.C. Vorbruggen and B. Sendhoff",
  booktitle =    "Artificial Neural Networks--ICANN Proceedings",
  series =       "Lecture Notes in Computer Science Series",
  address =      "Berlin",
  keywords =     "HRRs, distributed representations"
}

@unpublished{halford-wilson-phillips-bbs98,
  author =       "Halford, Graeme and Wilson, William H. and Phillips,
Steven",
  title =        "Processing Capacity Defined by Relational
                  Complexity: Implications for Comparative,
                  Developmental, and Cognitive Psychology",
  note =         "Behavioral and Brain Sciences",
  year =         "to appear"
}

@InBook{plate-97c,
  author =       "Tony A. Plate",
  chapter =      "A Common Framework for Distributed
                  Representation Schemes for Compositional
                  Structure",
  title =        "Connectionist Systems for Knowledge
                  Representation and Deduction",
  publisher =    "Queensland University of Technology",
  year =         "1997",
  editor =       "Fr\'ed\'eric Maire and Ross Hayward and
                  Joachim Diederich",
  pages =        "15-34"
}
@article{plate95,
author={Tony A. Plate},
year={1995},
title={Holographic Reduced Representations},
journal={IEEE Trans. on Neural Networks},
volume={6},
number={3}, pages={623-641}
}

@incollection{plate-98,
  author =       "Tony Plate",
  title =        "Analogy retrieval and processing with distributed
                  represenations",
  year =         "1998",
  booktitle =    "Advances in Analogy Research: Integration of Theory
and
                  Data from the Cognitive, Computational, and Neural
                  Sciences",
  pages =        "154--163",
  editor =       "Keith Holyoak and Dedre Gentner and Boicho Kokinov",
  publisher =    "NBU Series in Cognitive Science, New Bugarian
University, Sofia."
}


@incollection   ( willshaw-81,
key     =       "Willshaw" ,
author  =       "Willshaw, D." ,
year    =       "1981" ,
title   =       "Holography, associative memory, and inductive
generalization" ,
editor  =       "G.~E. Hinton  and  J.~A. Anderson" ,
booktitle=      "Parallel models of associative memory" ,
address =       "Hillsdale, NJ" ,
publisher=      "Erlbaum" 
)

@inproceedings      (hinton-88,
    key    = "Hinton",
    author = "G. E. Hinton",
    title  = "Representing Part-whole Hierarchies in Connectionist Networks",
    pages  = "48-54",
    booktitle = COGSCI-88,
    year   = "1988"
    )

@article          (hinton-90,
key     =       "Hinton",
author  =       "Hinton, G.~E.",
title   =       "Mapping part-whole hierarchies into connectionist networks",
journal =       "Artificial Intelligence",
volume  =       "46",
number  =       "1-2",
pages   =       "47-76",
year    =       "1990"
)


@ARTICLE{WillshawDayan,
 KEY		="Willshaw and Dayan",
 AUTHOR		="D. Willshaw and P. Dayan",
 TITLE		="Optimal Plasticity from Matrix Memories: 
			what goes up must come down",
 JOURNAL	="Neural Computation",
 YEAR		="1990",
 VOLUME		="2",
 NUMBER		="1",
 PAGES		="85--93"}

@ARTICLE{Nadal_duality,
 KEY		="Nadal",
 AUTHOR		="J.-P. Nadal and N. Parga",
 TITLE		="Duality between learning machines: 
			a bridge between supervised and 
			unsupervised learning",
 JOURNAL	="Neural Computation",
 YEAR		="1994",
 VOLUME		="6",
 NUMBER		="3",
 PAGES		="489-506"}

@INPROCEEDINGS{Solla_generalisation,
 KEY		="Tishby \etal",
 AUTHOR		="N. Tishby and E. Levin and S. A. Solla",
 TITLE		="Consistent inference of probabilities 
	in layered Networks: predictions and generalization",
 BOOKTITLE	="Proc. {IJCNN}, {W}ashington",
 YEAR		="1989",
 PAGES		=""}

@INPROCEEDINGS{LevinTishbySolla,
 KEY		="Levin \etal",
 AUTHOR		="E. Levin and N. Tishby and S. A. Solla",
 TITLE		="A statistical approach to learning and generalization 
	in layered Neural Networks",
 BOOKTITLE	="{COLT} '89: 2nd workshop on computational learning theory",
 YEAR		="1989",
 PAGES		="245--260"}

%more details in Buntine paper

@ARTICLE{Buntine_Weigend,
 KEY		="Buntine and Weigend",
 AUTHOR		="W.L. Buntine and A.S. Weigend",
 TITLE		="{B}ayesian Back-propagation",
 JOURNAL	="Complex Systems",
 YEAR		="1991",
 VOLUME		="5",
 PAGES		="603--643"}

@TECHREPORT{Wolpert_rig,
 KEY		="Wolpert",
 AUTHOR		="D. H.  Wolpert",
 TITLE		="A rigorous investigation of 
	`evidence' and `{O}ccam factors' in {B}ayesian reasoning'",
 YEAR		="1992",
 NUMBER		="T.R. 92-03-013",
 INSTITUTION	="Santa Fe Inst."}

@TECHREPORT{Wolpert_Wolf,
 KEY		="Wolpert and Wolf",
 AUTHOR		="D. H.  Wolpert and D. R.  Wolf",
 TITLE		="Estimating functions of probability distributions 
			from a finite set of samples. Part I: 
			{B}ayes estimators and the {S}hannon entropy",
 YEAR		="1993",
 NUMBER		="LA-UR-92-4369",
 INSTITUTION	="Los Alamos National Laboratory"}

@TECHREPORT{Buntine2,
 KEY		="Buntine",
 AUTHOR		="W.L. Buntine",
 TITLE		="Theory refinement on {B}ayesian Networks",
 YEAR		="1991",
 INSTITUTION	=""}


@ARTICLE{Buntine:trees,
 KEY		="Buntine",
 AUTHOR		="W.L. Buntine",
 TITLE		="Learning classification trees",
 YEAR		="1992",
 JOURNAL	="Statistics and Computing",
 VOLUME		="2",
 PAGES		="63-73"}

@ARTICLE{Bishop,
 KEY		="Bishop",
 AUTHOR		="C. M. Bishop",
 TITLE		="Exact calculation 
	of the {H}essian matrix for the multilayer perceptron",
 JOURNAL	="Neural Computation",
 YEAR		="1992",
 VOLUME		="4",
 NUMBER		="4",
 PAGES		="494--501"}

@techreport{Peto,
 AUTHOR		="Peto, L. B.",
 TITLE		="A Comparison of Two Smoothing Methods for Word 
Bigram Models",
 YEAR		=1994,
  institution =  "Computer Systems 
Research Institute, University of Toronto",
 Number		="CSRI-304"}



%                      Amino Acid Index Database                       %
%                                                                      %
% Please cite the following reference when making use of the database. %
%    Nakai, K., Kidera, A., and Kanehisa, M.;  Cluster analysis of     %
%       amino acid indices for prediction of protein structure and     %
%       function.  Prot. Eng. 2, 93-100 (1988)                         %


@Article{amino_index,
  author = 	 "Nakai, K. and Kidera, A. and Kanehisa, M.",
  title = 	 "Cluster analysis of amino acid indices for
		  prediction of protein structure and function",
  journal =	 "Prot. Eng.",
  year =	 1988,
  volume =	 2,
  pages =	 "93-100"
}

% Protein superfamilies and domain superfolds
% C. A. Orengo and othewrs Nature vol 372 15 Dec 1994 p.631

@UNPUBLISHED{Buntine3,
 KEY		="Buntine",
 AUTHOR		="W. L. Buntine and A. S. Weigend",
 TITLE		="Calculating second derivatives on feed-forward Networks",
 NOTE		="Submitted to IEEE Trans. on Neural Networks",
 YEAR		="1991"}


@ARTICLE{Lewicki,
 KEY		="Lewicki",
 AUTHOR		="M.S. Lewicki",
 TITLE		="{B}ayesian modeling and classification of neural signals",
 JOURNAL	="Neural Computation",
 VOLUME         ="6",
  NUMBER        =5,
 PAGES		="1005-1030",
 YEAR		="1994"}

@INCOLLECTION{Denker2,
 KEY		="Denker and LeCun",
 AUTHOR		="J.S. Denker and LeCun, Y.",
 TITLE		="Transforming Neural-net output levels 
	to probability distributions",
 BOOKTITLE	="Advances in Neural Information Processing Systems 3",
 YEAR		="1991",
 EDITOR		="R. P. Lippmann",
 PAGES		="853--859",
 ADDRESS	="San Mateo, CA",
 PUBLISHER	="Morgan Kaufmann"}

@INCOLLECTION{Becker_Le_Cun,
 KEY		="Becker and LeCun",
 AUTHOR		="S. Becker and LeCun, Y.",
 TITLE		="Improving the convergence of back-propagation learning 
	with second order methods",
 BOOKTITLE	="Proc. of the connectionist 
	models Summer school",
 YEAR		="1988",
 EDITOR		="D.S. Touretzky et. al.",
 PAGES		="29",
 ADDRESS	="San Mateo, CA",
 PUBLISHER	="Morgan Kaufmann"}



%	LUTTRELL

@ARTICLE{Luttrell_IEEE90,
 KEY		="Luttrell",
 AUTHOR		="S. P. Luttrell",
 TITLE		="Derivation of a class of training algorithms",
 JOURNAL	="IEEE 
	Trans. on Neural Networks",
 YEAR		="1990",
 VOLUME		="1",
 NUMBER		="2",
 PAGES		="229--232"}

@ARTICLE{Luttrell94:SOM,
 KEY		="Luttrell",
 AUTHOR		="S. P. Luttrell",
 TITLE		="A {B}ayesian analysis of self-organising maps", 
 JOURNAL	="Neural Computation",
 YEAR		="1994",
 VOLUME		="6",
 PAGES		="767-794"}

@TechReport{Luttrell:BC,
  author = 	 "S. P. Luttrell",
  title = 	 "The {G}ibbs Machine applied to hidden {M}arkov model
		  problems. Part 1: Basic theory",
  institution =  "SP4 division, RSRE",
  year = 	 1989,
  number =	 99,
  address =	 "Malvern, U.K."
}

@article{Luttrell94:PMD,
 KEY		="Luttrell",
 AUTHOR		="S. P. Luttrell",
 TITLE 		="The partitioned mixture distribution: an adaptive {B}ayesian
			network for low-level image processing",
 volume={141},
 number={4},
 JOURNAL	={Proc. IEE Vision, Image and Signal Processing},
 YEAR		="1994",
 PAGES		="251-260"}
% IEE Proceedings on Vision Image and Signal Processing",

% An adaptive Bayesian network for low-level image processing", Proceedings of the 3rd 
% International IEE Conference on Artificial Neural Networks, Brighton, 1993, pp. 61-65
% this is the first PMD paper. 


%	BM'S, MEAN FIELD THEORY

@ARTICLE{mean-field,
 KEY		="Peterson et. al.",
 AUTHOR		="C. Peterson and J. R. Anderson",
 TITLE		="A Mean Field Theory Learning Algorithm for Neural Networks",
 JOURNAL	="Complex Systems",
 YEAR		="1987",
 VOLUME		="1",
 NUMBER		="",
 PAGES		="995-1019"}

@ARTICLE{peterson_soderberg87,
 KEY		="Peterson and Soderberg",
 AUTHOR		="C. Peterson and B. Soderberg",
 TITLE		="A New Method for Mapping Optimization Problems onto 
			Neural Networks",
 JOURNAL	="Int. Journal Neural Systems",
 YEAR		="1989",
 VOLUME		="1",
 NUMBER		="1",
 PAGES		=""}

@INPROCEEDINGS{Sej,
 KEY		="Sejnowski",
 AUTHOR		="T. J.  Sejnowski",
 TITLE		="Higher order {B}oltzmann machines",
 BOOKTITLE 	="Neural networks for computing",
 EDITOR		="J.S. Denker",
 PAGES		="398-403",
 ADDRESS	="New York",
 PUBLISHER	="American Institute of Physics",
 YEAR		="1986"
}
@TechReport{sejnowski-rosenberg-86,
  key =          "Sejnowski",
  author =       "T.~J. Sejnowski and C.~R. Rosenberg",
  title =        "{\em NETtalk: A parallel network that learns to read
                 aloud}",
  type =         "Technical Report 86-01",
  institution =  "Department of Electrical Engineering and Computer
                 Science, Johns Hopkins University, Baltimore, MD.",
  year =         "1986",
}

@Article{nettalk,
  author =       "T. J. Sejnowski and C. R. Rosenberg",
  title =        "Parallel Networks that Learn to Pronounce {E}nglish
                 Text",
  journal =      "Journal of Complex Systems",
  volume =       "1",
  number =       "1",
  month =        feb,
  year =         "1987",
  pages =        "145--168",
  comment =      "Classic paper covering the NETtalk system, which
                 learns to convert English text to speech.",
}

%	TSP

% 	 Other Neural Nets
@ARTICLE{DurbWill,
 KEY		="Durbin and Willshaw",
 AUTHOR		="R. Durbin and D. Willshaw",
 TITLE		="An 
	analogue approach to the travelling salesman problem using an elastic Net 
	method",
 JOURNAL	="Nature",
 YEAR		="1987",
 VOLUME		="326",
 NUMBER		="",
 PAGES		="689--91"}


@article(Eberhart&al:91, 
        Author = {Eberhart, S. P. and Daud, D. and Kerns, D. A. and
                  Brown, T. X. and Thakoor, A. P.}, 
        Title = {Competitive Neural Architecture for Hardware Solution
                 to the Assignment Problem}, 
        Journal = {Neural Networks}, 
        Volume = {4},
        Pages = {431--442}, 
        Year = {1991})

@article(Peterson&Soderberg:89, 
        Author = {Peterson, C. and S\"{o}derberg, B.}, 
        Title = {A new method for mapping optimization problems onto
                 neural networks}, 
        Journal = {International Journal of Neural Systems}, 
        Volume = {1},
        Number = {1},
        Pages = {3--22},
        Year = {1989})

@article(Peterson&Anderson:88, 
        Author = {Peterson, C. and Anderson, J. R.}, 
        Title = {Neural Networks and {NP}-complete Optimization Problems; A
                 Performance Study on the Graph Bisection Problem},
        Journal = {Complex Systems}, 
        Volume = {2},
        Number = {1},
        Pages = {59--89},
        Year = {1988})

@article(Van&Miller:89, 
        Author = {Van den Bout, D. E. and Miller, III, T. K.}, 
        Title = {Improving the Performance of the {Hopfield--Tank} Neural
                 Network Through Normalization and Annealing}, 
        Journal = {Biological Cybernetics}, 
        Volume = {62},
        Pages = {129--139},
        Year = {1989})

@article(Van&Miller:90, 
        Author = {Van den Bout, D. E. and Miller, III, T. K.}, 
        Title = {Graph Partitioning using Annealed Neural Networks}, 
        Journal = {IEEE Trans. on Neural Networks}, 
        Volume = {1},
        Number = {2},
        Pages = {192--203},
        Month = {June},
        Year = {1990})

@ARTICLE{Aiyer,
 KEY		="Aiyer et. al.",
 AUTHOR		="S. V. B. Aiyer and M. Niranjan and F. Fallside",
 TITLE		="
	A Theoretical investigation into the performance of the {H}opfield model",
 JOURNAL	="IEEE 
	Trans. on Neural Networks",
 YEAR		="1990",
 VOLUME		="1",
 NUMBER		="2",
 PAGES		="204--215"}

@PHDTHESIS{Aiyer_thesis,
 KEY		="Aiyer",
 AUTHOR		="S. V. B. Aiyer",
 TITLE		={Solving Combinatorial Optimization Problems Using
		  Neural Networks},
type={PhD},
 YEAR		="1991",
 SCHOOL={Cambridge University Engineering Department},
NOTE={CUED/F-INFENG/TR 89}
}

@ARTICLE{Gee_Prager,
 KEY		="Gee and Prager",
 AUTHOR		="A. H. Gee and R. W. Prager",
 TITLE		="Polyhedral Combinatorics and Neural Networks",
 JOURNAL	="Neural Computation",
 YEAR		="1994",
 VOLUME		="6",
 NUMBER		="",
 PAGES		="161-180"}


%	BASIC NEURAL NET REFS

@BOOK{PDP,
 KEY		="D. E. Rumelhart and J. E. McClelland",
 AUTHOR		="D. E. Rumelhart and J. E. McClelland",
 TITLE		="Parallel Distributed Processing",
 PUBLISHER	="MIT Press",
 YEAR		="1986", 
 ADDRESS        ="Cambridge MA"}

@ARTICLE{backprop,
 KEY		="Rumelhart \etal",
 AUTHOR		="D. E. Rumelhart and G. E. Hinton and 
	R. J. Williams",
 TITLE		="Learning representations by 
	back-propagating errors",
 JOURNAL	="Nature",
 YEAR		="1986",
 VOLUME		="323",
 NUMBER		="",
 PAGES		="533--536"}
%  in the pdp book this is 318--362

@TechReport{Williams85,
 KEY		="Williams",
 AUTHOR		="R. J. Williams",
 TITLE		="Feature Discovery through Error-Correction Learning",
  institution =  "Insititute for Cognitive Science",
  year = 	 1985,
  number =	 "ICS 8501"
}


@ARTICLE{Pineda,
 KEY		="Pineda",
 AUTHOR		="F.J. Pineda",
 TITLE		="Recurrent back-propagation and the dynamical approach to adaptive Neural computation",
 JOURNAL	="Neural Computation",
 YEAR		="1989",
 VOLUME		="1",
 NUMBER		="",
 PAGES		="161--172"}

% initial of Heil?
@ARTICLE{Baldi,
 KEY            ="Baldi",
 AUTHOR		="P. Baldi and Heiligenberg",
 TITLE		="How sensory maps could enhance resolution through ordered
arrangement of broadly tuned receivers",
 JOURNAL	="Biol. Cyb.",
 VOLUME		="59",
 PAGES		="313-318",
 YEAR		="1988"}

%	NUMERICAL

@BOOK{NR,
 KEY		="Press \etal",
 AUTHOR		="W.H. Press and B.P. Flannery and S. A. Teukolsky and W. T.  Vetterling",
 TITLE		="Numerical Recipes in {C}",
 PUBLISHER	="Cambridge University Press",
 YEAR		="1988"}


%	{B}ayes

@BOOK{Berger_Wolpert,
 KEY		="Berger and Wolpert",
 AUTHOR		="J.O. Berger and R. L.  Wolpert",
 TITLE		="",
 PUBLISHER	="Institute of Mathematical Statistics",
 ADDRESS	="Hayward, CA",
 YEAR		="1984"}

% Nice quote: [from savage originally] `Indeed to many {B}ayesians, belief 
% 	in the LP is the big difference between {B}ayesians and frequentists, 
% 	not the desire to involve prior information'
@BOOK{Berger,
 KEY		="Berger",
 AUTHOR		="J. Berger",
 TITLE		="Statistical Decision theory and {B}ayesian 
	Analysis",
 PUBLISHER	="Springer",
 YEAR		="1985"}

@BOOK{Zellner,
 KEY		="Zellner",
 AUTHOR		="A. Zellner",
 TITLE		="Basic issues in econometrics",
 PUBLISHER	="Chicago",
 YEAR		="1984"}

% University of Chicago Press, Chicago


@book{Duda_Hart_Stork,
author={Duda, Richard O. and  Hart, Peter E. and  Stork, David G.},
title={                       Pattern Classification},
note={2nd Edition},
isbn={0-471-05669-3},
publisher={Wiley},
address={New York},
year={2000},
}


@BOOK{Duda_Hart,
 KEY		="Duda and Hart",
 AUTHOR		="Duda, Richard O. and  Hart, Peter E.",
 TITLE		="Pattern Classification and Scene Analysis",
 PUBLISHER	="Wiley",
 YEAR		="1973"}

@misc{bombesimulator,
author={Nik Shaylor},
year={1997},
url={http://www.geocities.com/CapeCanaveral/Hangar/4040/bombe.html},
 annote={Nik Shaylor's page describes the logical circuitry that Turing and G. W. Welchman devised to accomplish the
 rejection of all rotor positions inconsistent with guessed plaintext. It also has a Java simulation of the process.}
}

@article{GoodEnigma,
author={I. J. Good},
title={Studies in the History of Probability and Statistics.
 {XXXVII}. {A.M.~Turing's} statistical work in {World War II}},
journal={Biometrika},
volume={66},
number={2}, pages={393-396},year={1979},
annote={reprinted also in the
 Collected Works}
}
% A. Hodges, Alan Turing: The Enigma, Simon and Schuster, New York, NY, 1983.
@book{hodges83,
 author={Andrew Hodges},
 title={Alan Turing: The Enigma},
 publisher={Simon and Schuster},
 address={New York, NY},
year=1983
}

%%%%%%%%%%%%
%
%% book{turing-pure-maths,
%% author={A. M. Turing},
% title={ Collected Works of A. M. Turing (North-Holland, 1992) Pure Mathematics} (ed. J. R.
%  Britton) 

@BOOK{Good,
 KEY		="Osteyee and Good",
 AUTHOR		="D. B. Osteyee and I. J. Good",
 TITLE		="Information, weight of 
	evidence, the singularity between probability measures and 
	signal detection",
 PUBLISHER	="Springer",
 YEAR		="1974"}

@inproceedings{Meyer_Collier,
  title = 	 "{B}ayesian statistics",
  year = 	 1970,
  key =		 "Meyer and Collier",
  editor =	 "D. L. Meyer and R. O. Collier",
  publisher =	 "Peacock publishers"
}

@INCOLLECTION{Lindley-philosophy,
 KEY		="Lindley",
 AUTHOR		="D.V. Lindley",
 TITLE		="{B}ayesian analysis in regression problems",
 BOOKTITLE	="{B}ayesian statistics",
 YEAR		="1970",
 EDITOR		="D.L. Meyer and R.O. Collier",
 PUBLISHER	="Peacock publishers"}


% 	History

@ARTICLE{laplace,
 KEY		="Stigler",
 AUTHOR		="S.M. Stigler",
 TITLE		="Laplace's 1774 memoir on inverse 
	probability",
 JOURNAL	="Stat. Sci.",
 YEAR		="1986",
 VOLUME		="1",
 NUMBER		="3",
 PAGES		="359--378"}

@ARTICLE{cox,
 KEY		="Cox",
 AUTHOR		="R.T. Cox",
 TITLE		="Probability, frequency, and reasonable expectation",
 JOURNAL	="Am. J. Physics",
 YEAR		="1946",
 VOLUME		="14",
 PAGES		="1-13"}

@ARTICLE{Akaike,
 KEY		="Akaike",
 AUTHOR		="H. Akaike",
 TITLE		="Statistical predictor identification",
 JOURNAL	="Ann.\ Inst.\ Statist.\ Math.",
 YEAR		="1970",
 VOLUME		="22",
 NUMBER		="",
 PAGES		="203--217"}


%	CLT
@ARTICLE{clt,
 KEY		="Walker",
 AUTHOR		="A.M. Walker",
 TITLE		="On the asymptotic behaviour of posterior
	distributions",
 JOURNAL	="J. R. Stat. Soc. B",
 YEAR		="1967",
 VOLUME		="31",
 NUMBER		="",
 PAGES		="80--88"}


%	GULL, SKILLING, OCCAM, MAXENT, MDL

@ARTICLE{Smith_and_Spiegelhalter,
 KEY		="Smith and Spiegelhalter",
 AUTHOR		="A.F.M. Smith and D.J. Spiegelhalter",
 TITLE		="{B}ayes factors and choice criteria for linear models",
 JOURNAL	="Journal of the Royal Statistical Society B",
 YEAR		="1980",
 VOLUME		="42",
 NUMBER		="2",
 PAGES		="213-220"}

@ARTICLE{Smith_review,
 KEY		="Smith",
 AUTHOR		="A.F.M. Smith",
 TITLE		="{B}ayesian Computational Methods",
 JOURNAL	="Philosophical Trans. of the Royal Society of
		  London A",
 YEAR		=1991,
 VOLUME		=337,
 PAGES		="369-386"}

@ARTICLE{Jefferys_and_Berger,
 KEY		="Jefferys and Berger",
 AUTHOR		="W.H. Jefferys and J.O. Berger",
 TITLE		="{O}ckham's razor and {B}ayesian analysis",
 JOURNAL	="American Scientist",
 YEAR		="1992",
 VOLUME		="80",
 PAGES		="64-72"}

% Has good examples including fitting a high polynomial to data, 
% 	detecting plagiarism, detecting that a coin has two heads, 
% 	Newton / GR, also they give bounds on the min Occam factor that 
% 	a model can suffer. 

@ARTICLE{Mark_and_Miller,
 KEY		="Mark and Miller",
 AUTHOR		="K.E. Mark and M.I. Miller",
 TITLE		="{B}ayesian model selection and minimum description length 
	estimation of auditory-nerve discharge rates",
 JOURNAL	="J. Acoust. Soc. Am.",
 YEAR		="1992",
 VOLUME		="91 ",
 NUMBER		="2",
 PAGES		="989--1002"}


% {B}ayes and Regularisation

% Iversen's {B}ayes Booklet: has several useful simple results, and typical lame philosophy.
@BOOK{Iversen,
 KEY		="Iversen",
 AUTHOR		="G. R. Iversen",
 TITLE		="{B}ayesian statistical inference",
 PUBLISHER	="Sage publications, Beverly Hills",
 YEAR		="1984"}

% He refers to Box and Tiao as containing inferences concerning robust models'
% parameters. Berger also discusses robustness, but I suspect not the inference
% of those params.  
@BOOK{Box_and_Tiao_text,
 KEY		="Box and Tiao",
 AUTHOR		="G. E. P. Box and G. C. Tiao",
 TITLE		="{B}ayesian  Inference in Statistical Analysis",
 PUBLISHER	="Addison--Wesley",
 YEAR		="1973"}
@book{box-tiao-73,
   author    = {Box, G. E. P. and Tiao, G. C.},
   title     = {{Bayesian Inference in Statistical Analysis}},
   year      = {1973},
   publisher = {Addison-Wesley},
   address   = {Reading, MA}
}



@ARTICLE{Box1,
 KEY		="Box and Tiao",
 AUTHOR		="G. E. P. Box and G. C. Tiao",
 TITLE		="A further look at robustness via {B}ayes' theorem",
 JOURNAL	="Biometrika",
 YEAR		="1962",
 VOLUME		="49",
 NUMBER		="",
 PAGES		="419--432"}

@ARTICLE{Box2a,
 KEY		="Box and Tiao",
 AUTHOR		="G. E. P. Box and G. C. Tiao",
 TITLE		="A {B}ayesian approach
 	to the importance of assumptions applied to the comparison of variances",
 JOURNAL	="Biometrika",
 YEAR		="1964",
 VOLUME		="51",
 NUMBER		="",
 PAGES		="153--167"}

@ARTICLE{Box2b,
 KEY		="Box and Tiao",
 AUTHOR		="G. E. P. Box and G. C. Tiao",
 TITLE		="A note on criterion robustness and inference robustness",
 JOURNAL	="Biometrika",
 YEAR		="1964",
 VOLUME		="51",
 PAGES		="169--173"}

@ARTICLE{Box3,
 KEY		="Box and Tiao",
 AUTHOR		="G. E. P. Box and G. C. Tiao",
 TITLE		="A {B}ayesian approach to some outlier problems",
 JOURNAL	="Biometrika",
 YEAR		="1968",
 VOLUME		="55",
 PAGES		="119--129"}


@ARTICLE{Dempster:EM,
	author		= {A.P. Dempster and N.M. Laird and D.B. Rubin},
	title		= {Maximum Likelihood from Incomplete Data via the {EM} 
						Algorithm},
	journal		= {Journal of the Royal Statistical Society {B}},
	year			= 1977,
	volume		= 39,
	pages			= {1-38},
	source		= {UL P.202.c.30}
}

% Lindley booklet: has strong detailed and simple arguments showing that 
% Fisher is bullshit inchoerent. He wrote this after lecturing for Dan Brunk!
@BOOK{Lindley-booklet,
 KEY		="Lindley",
 AUTHOR		="D. V. Lindley",
 TITLE		="{B}ayesian statistics, a review",
 PUBLISHER	="Society for Industrial and Applied Mathematics, Philadelphia",
 YEAR		="1972"}

% p.3: Unlike common procedure of proposing a procedure 
% 	and investigating its properties, we instead ask 
% 	what properties are required and then find procedures that have these properties. I like it!
% Lindley reviews Ramsey's gambling scenario that proves that you have 
% to have a utility function and a prob dist. Savage later did a rigorous 
% version of the same. 
% 	Assume that lotteries can be ordered. The ordering is transitive. 
% Lindley also mentions Wald. He knocks Dempster-Schafer. 
% He then states that any coherent inferences/decisions
% must be interpretable in terms of a prior. That prob distbn is a 
% subjective prob possessed by the decision maker. 
% `Objections to this attitude are numerous but none that I am aware of 
% have gone to the axioms and criticised those. Indeed, it is hard to see how 
% such criticism could be sustained since the requirements impoosed by coherence
% are so modest.'
% 	If the scientific community makes decisions, it must have a prior
% and a utility. In half a line he mentions the result in game theory that 
% e baum takes 50 pages to prove. 
% 	Lindley then distinguishes inference and decision theory nicely. 
% 	Then he attqacks sampling theory for incoherence by showing counter-
% examples.  Likelihood p. 
% The requirement of unbiasedness violates the l.p.
% eg, If sample r/n binomial, theta = r/n.
% But if sample n for fixed r, theta = r-1/n-1 is the unbiased estimator.
% 	A statistic t(x) is called ancillary if its P does not depend on theta.
% [That is , for example, it is the deviations of the samples from x_bar]
% Some crap sampling theory dicks base their methods on ancill stats. They 
% are wrong of course. counterexamples on p.11-12.
% 	Maximu likelihood couterexample: mixture model has singularity
% when sigma-> 0 with one component of the mixture on top of a particular 
% data point. Similarly sigma N-1 can be generalised to give examples 
% that don't converge. 
% 	Significance tests counterexamples.
% 	Minimax	counterexamples. 
% 	Examples where a rejected hypothesis has probability close to 1.
% 	Examples are citred of confidence intervals where the larger interval 
% doesn't include the smaller!
% 	Another example of a ludicrous unbiased estimator. 
% 	Later on p.42 he cites Edwards et al 1963 as the definitive (but long) paper on 
% the robustness of {B}ayesian inferences to the prior. 
% 	He distinguishes [Box and Tiao 62 64a 64b] Criterion robustness and inference
% robustness. The first is robustness of a fixed procedure to the distribution
% being different from the assumptions. THe latter is the {B}ayesian attitude. 
% [p.43]
% p.44 reviews the non-normal model studied by Box. He says more work is needed
% here. 
% 
% p. 46 -> outliers. Box 1968b uses a mixture model, same mean, two gaussians. 
% The outlier problem is discussed by Hartigan by seeing how influential each
% individual datum is. 

@INPROCEEDINGS{Proteins_with_Autoclass,
 AUTHOR		="L. Hunter and D. States",
 TITLE		="Applying {B}ayesian Classification to Protein Structure",
 YEAR		="1991",
 BOOKTITLE	="IEEE Conference on Applications of A.I. 1991",
 PAGES		=""
}
@UNPUBLISHED{Cheeseman_color,
 AUTHOR		="P. Cheeseman",
 TITLE		="Personal communication",
 YEAR		="1991",
 NOTE	="",
}
@INPROCEEDINGS{Cheeseman_hard,
 AUTHOR		="P. Cheeseman",
 TITLE		="Where  the {\em Really} Hard Problems Are",
 YEAR		="1991",
 BOOKTITLE	="IJCAI-91: Proc. 12th. International 
		Conference on Artificial Intelligence", 
 PAGES		="331-337"
}
% unfortunately the above paper does not contain his probabilistic mean
% field type algm. 
% it is a thorough study of the existence of phase transitions in "NP complete"
% problems. 

@INCOLLECTION{Cheeseman_on_Occam,
 KEY		="Cheeseman",
 AUTHOR		="P. Cheeseman",
 TITLE		="On finding the most probable model",
 BOOKTITLE	="Computational models of
	scientific discovery and theory formation",
 YEAR		="19XX",
 EDITOR		="J. Shrager and P. Langley",
 PAGES		="73--95",
 PUBLISHER	=""}

% % Quite a nice strong-wroded review of Occam, but with quite a lot of
% 	alternative free talk as well, I think. 



@ARTICLE{Titterington1,
 KEY		="Titterington",
 AUTHOR		="D. Titterington",
 TITLE		="General structure of regularization procedures in image reconstruction",
 JOURNAL	="Astron. Astrophys.",
 YEAR		="1985",
 VOLUME		="144",
 PAGES		="381-387"}

@ARTICLE{Titterington2,
 KEY		="Titterington",
 AUTHOR		="D. Titterington",
 TITLE		="Common structure of smoothing techniques in statistics",
 JOURNAL	="Int.\ Statist.\ Rev.",
 YEAR		="1985",
 VOLUME		="53",
 PAGES		="141-170"}

% these two papers are pretty similar, neither is that deep, or perhaps 
% I just don't understand. The int stat rev one is longer . 
% Both papers mention over-smoothing.
@TECHREPORT{Poggio3,
 KEY		="Poggio and Girosi",
 AUTHOR		="T. Poggio and F. Girosi",
 TITLE		="A theory of Networks for approximation and learning",
 YEAR		="1989",
 INSTITUTION	="MIT",
 NUMBER		="A.I. 1140"}

@ARTICLE{Poggio1,
 KEY		="Poggio et. al.",
 AUTHOR		="T. Poggio and V. Torre and C. Koch",
 TITLE		="Computational vision and regularization theory",
 JOURNAL	="Nature",
 YEAR		="1985",
 VOLUME		="317 ",
 NUMBER		="6035",
 PAGES		="314-319"}

% arguably this is a crap ref for CV, as there is plenty of Wahba before it.
% I copied use of this ref from SFG. I guess he uses it to refer to GML
@ARTICLE{CrossVal,
 KEY		="Davies and Anderssen",
 AUTHOR		="A. R. Davies and R. S. Anderssen",
 TITLE		="Optimization in the Regularization of Ill-posed Problems",
 JOURNAL	="J. Austral. Mat. Soc. Ser. B",
 YEAR		="1986",
 VOLUME		="28",
 NUMBER		="",
 PAGES		="114-133"}

% Wahba says that "ML" choice of alpha first appears in this: 
@ARTICLE{Anderssen_Bloomfield,
 KEY		="Anderssen",
 AUTHOR		="R. S. Anderssen and P. Bloomfield",
 TITLE		="A Time Series Approach to Numerical Differentiation",
 JOURNAL	="Technometrics",
 YEAR		="1974",
 VOLUME		="16",
 PAGES		="69-75"}


% This paper proves properties of alternative choices of alpha, 
% including I think that cross val is best. **
@BOOK{Eubank,
 KEY		="Eubank",
 AUTHOR		="R. L.  Eubank",
 TITLE		="Spline Smoothing and Non-parametric
	Regression",
 PUBLISHER	="Marcel Dekker",
 YEAR		="1988"}
% In this book they call GCV `the method of choice' p.255

@INPROCEEDINGS{Jaynes,
 KEY		="Jaynes",
 AUTHOR		="E. T. Jaynes",
 TITLE		="{B}ayesian Methods: General Background",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods in 
	applied statistics",
 EDITOR		="J. H.  Justice",
 PUBLISHER	="Cambridge University Press",
 YEAR		="1986",
 PAGES		="1--25"}

@article{Rose1992,
  title="Vector Quantization by Deterministic Annealing",
  author="Rose, K. and Gurewitz, E. and Fox, G. C.",
  journal="IEEE Trans. on Info. Theory",
  year="1992",
  volume="38",
  number="4",
  pages="1249-1257"
}

@book{Jaynes2003,
author={E. T. Jaynes},
title={Probability Theory: The Logic of Science},
publisher={Cambridge University Press},
address={Cambridge},
year={2003},
note={Edited by G.~Larry Bretthorst}
}


@Book{Rosenkrantz,
  author = 	 "R. D. Rosenkrantz",
  title = 	 "{E.T. Jaynes}. Papers on Probability,
        Statistics and Statistical Physics",
  publisher = 	 "Kluwer",
  year = 	 1983,
}
%   editor =	 "R. D. Rosenkrantz"

@INCOLLECTION{Jaynes.intervals,
 KEY		="Jaynes",
 AUTHOR		="E. T. Jaynes",
 TITLE		="{B}ayesian Intervals versus Confidence Intervals",
 BOOKTITLE	="{E.T. Jaynes}. Papers on Probability,
        Statistics and Statistical Physics",
 EDITOR		="R. D. Rosenkrantz",
 PUBLISHER	="Kluwer",
 YEAR		="1983",
 PAGES		="151"}
% PUBLISHER	="Kluwer Academic Publishers",
% reprinted in paperback 1989,
%  I just read utterly the best Jaynes essay ever. It is SO good; so even 
% handed and confrontational; rubbing the noses of the opposition in the 
% examples he gives, using the opponents of Galileo as analogy -- some of 
% his opponents refused to look through his telescope to see Jupiter's 
% moons, because they `already knew'. It's a very pragmatic argument he uses, 
% not philosophical -- just look at the results of the two approaches 
% and see where they give different answers, then magnify those differences 
% and ask your common sense which answer makes sense. 

@INPROCEEDINGS{Bryan,
 KEY		="Bryan",
 AUTHOR		="Bryan, R. K.",
 TITLE		="Solving Oversampled Data Problems by {M}aximum {E}ntropy",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, 
                         {D}artmouth, {U.S.A.}, 1989",
 EDITOR		="P. Fougere",
 PUBLISHER	="Kluwer",
 YEAR		="1990",
 PAGES		="221-232"}
 
@INPROCEEDINGS{Loredo,
 KEY		="Loredo",
 AUTHOR		="T. J.  Loredo",
 TITLE		="From {L}aplace to Supernova {SN} {1987A}: {B}ayesian Inference
	in Astrophysics",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {D}artmouth, {U.S.A.}, 1989",
 EDITOR		="P. Fougere",
 PUBLISHER	="Kluwer",
 YEAR		="1990",
 PAGES		="81--142"}
 
@INPROCEEDINGS{Gregory_Loredo,
 KEY		="Gregory and Loredo",
 AUTHOR		="P. C. Gregory and T. J. Loredo",
 TITLE		="A New Method for the
	Detection of a Periodic Signal of Unknown Shape and Period",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods,",
 EDITOR		="G.J. Erickson and C.R. Smith",
 PUBLISHER	="Kluwer",
 YEAR		="1992",
 NOTE		="Also in {\em Astrophysical Journal},  {\bf 398}, pp.\ 146--168, Oct 10, 1992",
annote={Gregory, P. C. and Thomas. J. Loredo, 1992, ``A New Method For The Detection Of A Periodic Signal Of Unknown Shape And Period,'' in The Astrophysical Journal, Astrophysical J., 398, p.146-168}
}

@INPROCEEDINGS{GS1,
 KEY		="Skilling",
 AUTHOR		="J. Skilling",
 TITLE		="Classic Maximum Entropy",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 EDITOR		="J. Skilling",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1989",
 PAGES		=""}

@ARTICLE{Gull.nature,
 KEY		="Gull",
 AUTHOR		="S. F.  Gull and G.J.~Daniell",
 TITLE		="Image reconstruction from incomplete and noisy data",
 JOURNAL	="Nature",
 VOLUME		="272",
 YEAR		="1978",
 PAGES		="686-690"}

@INPROCEEDINGS{GS2,
 KEY		="Gull",
 AUTHOR		="S. F.  Gull",
 TITLE		="Developments in Maximum entropy data analysis",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 EDITOR		="J. Skilling",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1989",
 PAGES		="53--71"}

@INPROCEEDINGS{Skilling2,
 KEY		="Skilling",
 AUTHOR		="J. Skilling",
 TITLE		="The eigenvalues of mega-dimensional matrices",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 EDITOR		="J. Skilling",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1989",
 PAGES		="455--466"}

@INPROCEEDINGS{GSdevelopments,
 KEY            ="Gull",
 AUTHOR         ="S. F.  Gull and J. Skilling",
 TITLE          ="Developments in {C}ambridge",
 BOOKTITLE      ="Maximum-Entropy and {B}ayesian Spectral Analysis and
		  Estimation Problems",
 EDITOR         ="C.R. Smith and G.J. Erickson",
 PUBLISHER      ="Reidel",
 ADDRESS        ="Dordrecht",
 YEAR           ="1987",
 PAGES          ="149-160",
annote="proc of wyoming meeting 1983"}
%  13 S 17           
%  21 ZM 21
		  

@INPROCEEDINGS{G1,
 KEY            ="Gull",
 AUTHOR         ="S. F.  Gull",
 TITLE          ="{B}ayesian inductive inference and 
        maximum entropy",
 BOOKTITLE      =" Maximum Entropy and {B}ayesian Methods in 
        Science and Engineering, vol. 1: Foundations",
 EDITOR         ="G.J. Erickson and C.R. Smith",
 PUBLISHER      ="Kluwer",
 ADDRESS        ="Dordrecht",
 YEAR           ="1988",
 PAGES          ="53-74"}

% Papers by Devinder Sivia on Bayesian methods for inference of
% 		  physics models:
% The introductory tutorial one is:
% 
% Sivia, David, Knight and Gull, Physica D 66 (1993) 234-242.
%
% The more detailed one, specifically to do with line-fitting, is:
%
% Sivia and Carlile, J. Chem. Phys. 96 (1992) 170-178.

 
@INPROCEEDINGS{Gull88,
 KEY		="Gull",
 AUTHOR		="S. F.  Gull",
 TITLE		="{B}ayesian data analysis: straight-line fitting",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 EDITOR		="J. Skilling",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1989",
 PAGES		="511--518"}

@INPROCEEDINGS{Sibisi1,
 KEY		="Sibisi",
 AUTHOR		="S. Sibisi",
 TITLE		="Regularization and inverse problems",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 EDITOR		="J. Skilling",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1989",
 PAGES		="389--396"}

% A comparison of cross val with {B}ayes choice of alpha. Not at all 
% conclusive. ** above is far more thorough. 

@INPROCEEDINGS{Skilling1,
 KEY		="Skilling",
 AUTHOR		="J. Skilling",
 TITLE		="On parameter estimation and quantified MaxEnt",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht",
 YEAR		="1991",
 PAGES		="267--273"}

% see also .JMR below
@Article{Bretthorst_decays,
  author = 	 "Bretthorst, G. L.",
  title = 	 "{B}ayesian Analysis {II}: Model Selection",
  journal =	 "J. Mag. Res.",
  year =	 1990,
  volume =	 88,
  pages =	 "552-570"
}

@INPROCEEDINGS{BubblingSusie,
 KEY		="Skilling et. al.",
 AUTHOR		="J. Skilling and D. R. T. Robinson and 
	S. F.  Gull",
 TITLE		="Probabilistic displays",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 YEAR		="1991",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht",
 PAGES		="365--368"}

@INPROCEEDINGS{Charter,
 KEY		="Charter",
 AUTHOR		="M.K. Charter",
 TITLE		="Quantifying drug absorption",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht",
 YEAR		="1991",
 PAGES		="245--252"}

@INPROCEEDINGS{JaynesME90,
 KEY		="Jaynes",
 AUTHOR		="E.T. Jaynes",
 TITLE		="",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 YEAR		="1991",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht",
 PAGES		=""}


@Article{Jaynes57I,
  author = 	 "E.T. Jaynes",
  title = 	 "Information Theory and Statistical Mechanics I",
  journal =	 "Phys Rev",
  year =	 1957,
  volume =	 106,
  pages =	 "620-630"
}

@Article{Jaynes57II,
  author = 	 "E.T. Jaynes",
  title = 	 "Information Theory and Statistical Mechanics {II}",
  journal =	 "Phys Rev",
  year =	 1957,
  volume =	 108,
  pages =	 "171-190"
}

@INPROCEEDINGS{Image.contest,
 KEY		="Bontekoe",
 AUTHOR		="T.R. Bontekoe",
 TITLE		="The image reconstruction contest",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 YEAR		="1991",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht"
}

@ARTICLE{Rubin84,
 KEY		="Rubin",
 AUTHOR		="D. B. Rubin",
 TITLE		="{B}ayesianly justifiable and relevant frequency 
	calculations for the applied statistician",
 JOURNAL	="Ann. Stat.",
 YEAR		="1984",
 VOLUME		="12",
 NUMBER		="4",
 PAGES		="1151--1172"}

@INPROCEEDINGS{Sibisi2,
 KEY		="Sibisi",
 AUTHOR		="S. Sibisi",
 TITLE		="{B}ayesian interpolation",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 YEAR		="1991",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht",
 PAGES		="349--355"}

% Studies non-noisy interpolation
@TECHREPORT{Skilling_and_Sibisi,
 KEY		="Skilling and Sibisi",
 AUTHOR		="J. Skilling and S. Sibisi",
 TITLE		="Maximum Entropy Data Analysis",
 YEAR		="1990",
 INSTITUTION	="University of Cambridge"}

@TECHREPORT{G1.tr,
 KEY		="Gull",
 AUTHOR		="S. F.  Gull",
 TITLE		="{B}ayesian inductive inference and maximum entropy",
 YEAR		="1985",
 INSTITUTION	="University of Cambridge Dept. of Physics",
 NUMBER		="1326"}
 
@MANUAL{GS3,
 KEY		="Gull and Skilling",
 AUTHOR		="S. F.  Gull and J. Skilling",
 TITLE		="Quantified Maximum Entropy. \verb+MemSys5+ User's manual",
 ORGANIZATION 	="M.E.D.C.",
 ADDRESS	="33 North End, Royston, SG8 6NR, England",
 YEAR		="1991"}

@Proceedings{Maxent90,
 KEY		="Grandy and Schick",
 EDITOR		="Grandy, Jr., W. T.  and L.H. Schick",
 TITLE		="Maximum Entropy and {B}ayesian Methods, {L}aramie 1990",
 PUBLISHER	="Kluwer",
 YEAR		="1991"}

@proceedings{Maxent88,
 KEY		="Skilling",
 EDITOR		="J. Skilling",
 YEAR	=        1989,
 TITLE		="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 PUBLISHER	="Kluwer"
}

% aka Skilling93
@INPROCEEDINGS{Skilling_clouds,
 KEY		="Skilling",
 AUTHOR		="J. Skilling",
 TITLE		="{B}ayesian numerical analysis",
 BOOKTITLE	="Physics and Probability",
 EDITOR		="Grandy, Jr., W. T.  and P. Milonni",
 PUBLISHER	="Cambridge University Press",
 ADDRESS	="Cambridge",
 YEAR		="1993"}

% Radford used to be used to denote Radford.mixture
@INPROCEEDINGS{Radford.mixture,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="{B}ayesian mixture modelling",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {S}eattle 1991",
 EDITOR		="C.R. Smith and G.J. Erickson and P.O. Neudorfer",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1992",
 PAGES		="197-211"}

@Article{Neal_belief_nets,
  author = 	 "R. M. Neal",
  title = 	 "Connectionist learning of belief networks",
  journal =	 "Artificial Intelligence",
  year =	 1992,
  volume =	 56,
  pages =	 "71-113"
}

@TECHREPORT{Radford.mixtureTR,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="{B}ayesian mixture modelling by 
	{M}onte {C}arlo simulation",
 YEAR		="1991",
 cutINSTITUTION		="Dept. of Computer Science, University	of Toronto",
 INSTITUTION		="Computer Science, Univ.	of Toronto",
 NUMBER	="CRG--TR--91--2",
 cutNUMBER	="Technical Report CRG--TR--91--2"
}

@inproceedings{ beagharas01,
author={M. J. Beal and Z. Ghahramani and C. E. Rasmussen},
title={The Infinite Hidden {Markov} Model},
booktitle={Advances in Neural Information Processing Systems 14},
publisher={MIT Press},
year=2002,
url = {citeseer.nj.nec.com/beal02infinite.html} }


@article{Radford.over.b,
year=1997,
author={R. M. Neal},
title={Suppressing Random Walks in {M}arkov chain {M}onte
		  {C}arlo using Ordered Overrelaxation},
note={this volume}
}
@TECHREPORT{Radford.over,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="Suppressing Random Walks in {M}arkov chain {M}onte
		  {C}arlo using Ordered Overrelaxation",
 YEAR		="1995",
 INSTITUTION	="Dept. of Statistics, University
	of Toronto",
 NUMBER	="9508"}

@TECHREPORT{PintoNeal_01,
 KEY		="Neal",
 AUTHOR		="R. L. Pinto and R. M. Neal",
title={Improving {M}arkov chain {M}onte {C}arlo Estimators
 by Coupling to an Approximating Chain},
 YEAR		="2001",
 INSTITUTION	="Dept. of Statistics, University
	of Toronto",
 NUMBER	="0101"}

@TECHREPORT{Neal_92,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="{B}ayesian Training of Backpropagation
	Networks by the Hybrid {M}onte {C}arlo method",
 YEAR		="1992",
 NUMBER		="CRG--TR--92--1",
 INSTITUTION	="Dept. of Computer Science, University
	of Toronto"}
% better to ref Neal_nips5

@article{Green1995,
 author={Green, P. J.},
year={1995},
title={Reversible Jump {M}arkov Chain {M}onte {C}arlo Computation 
and {B}ayesian Model Determination},
journal={Biometrika}, volume=82,pages={711-732}
}
@TECHREPORT{Neal_dop,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="Probabilistic Inference  using  
                    {M}arkov Chain {M}onte {C}arlo Methods",
 YEAR		="1993",
 NUMBER		="CRG--TR--93--1",
 INSTITUTION	="Dept. of Computer Science, University	of Toronto"}

@TECHREPORT{AutoClassTR,
 KEY		="Hanson, Stutz and Cheeseman",
 AUTHOR		="R. Hanson and J. Stutz and P. Cheeseman",
 TITLE		="{B}ayesian classification theory",
 YEAR		="1991",
 NUMBER		="FIA--90-12-7-01",
 INSTITUTION	="NASA Ames"}

@INPROCEEDINGS{AutoClass,
 KEY		="Hanson, Stutz and Cheeseman",
 AUTHOR		="R. Hanson and J. Stutz and P. Cheeseman",
 TITLE		="{B}ayesian classification with correlation and inheritance",
 YEAR		="1991",
 BOOKTITLE	="Proc. 12th Intern. Joint Conf. on
                  Artificial Intelligence, Sydney, Australia",
 cutBOOKTITLE	="Proceedings of the 12th International Joint Conference on
                  Artificial Intelligence, Sydney, Australia",
 publisher = 	 "Morgan Kaufmann",
 volume=2,
 pages="692-698",
 MONTH	="August"}

@Article{lauritzen-spiegelhalter-88,
   key =          "Lauritzen",
   author =       "S.~L. Lauritzen and D.~J. Spiegelhalter",
   title =        "Local computations with probabilities on graphical
                 structures and their application to expert systems",
   journal =      "Journal of the Royal Statistical Society B",
   volume =       "50",
   pages =        "157--224",
   year =         "1988"
}


@article{Shokrollahi1997,
  title={A remark on matrix rigidity},
  author={Shokrollahi, M. A. and Spielman, D. A. and Stemann, V.},
  journal={Information Processing Letters},
  year={1997},
  volume={64},
  number={6},
  pages={283-285},
  abstract={The rigidity of a matrix is defined to be the number of entries in 
    the matrix that have to be changed in order to reduce its rank below 
    a certain value. Using a simple combinatorial Lemma, we show that one
    must alter at least c(n(2)/r)log(n/r) entries of an (n x n)-Cauchy 
    matrix to reduce its rank below r, for some constant c. We apply our 
    combinatorial lemma to matrices obtained from asymptotically good 
    algebraic geometric codes to obtain a similar result for r satisfying
    2n/(root q -- 1) < r less than or equal to n/4. (C) 1997 Elsevier 
    Science B.V.}
}

@article{spielman-96,
  title={Linear-time encodable and decodable error-correcting codes},
  author={Spielman, D. A.},
  journal={IEEE Trans. on Info. Theory},
  year={1996},
  volume={42},
  number={6.1},
  annote={no. 6 (Part 1), November},
  month={November},
  pages={1723-1731},
  abstract={We present a new class of asymptotically good, linear error-
    correcting codes. These codes can be both encoded and decoded in 
    linear time. They can also be encoded by logarithmic-depth circuits 
    of linear size and decoded by logarithmic depth circuits of size O(n 
    log n). We present both randomized and explicit constructions of 
    these codes.}
}

@article{Sipser1996,
  title={Expander codes},
  author={Sipser, M. and Spielman, D. A.},
  journal={IEEE Trans. on Info. Theory},
  year={1996},
  volume={42},
  number={6.1},
  pages={1710-1722},
  abstract={Using expander graphs, we construct a new family of asymptotically 
    good, linear error-correcting codes, These codes have linear time 
    sequential decoding algorithms and logarithmic time parallel decoding
    algorithms that use a linear number of processors. We present both 
    randomized and explicit constructions of these codes, Experimental 
    results demonstrate the good performance of the randomly chosen 
    codes.}
}


@article{Luby2001a,
  author =       {M. G. Luby  and M. Mitzenmacher and M. Amin Shokrollahi and
D. A. Spielman},
  title =        {Efficient Erasure Correcting Codes},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={569-584},
  year =         {2001}
}

@article{Luby2001b,
  author =       {M. G. Luby  and M. Mitzenmacher and M. Amin Shokrollahi and
D. A. Spielman},
   title =        "Improved Low-Density
       Parity-Check Codes Using Irregular Graphs and Belief Propagation",
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={585-584},
  year =         {2001}
}

@InProceedings{SpielPLRC,
  author =       {M. G. Luby  and M. Mitzenmacher and M. Amin Shokrollahi and
D. A. Spielman and V. Stemann},
  title =        {Practical Loss-Resilient Codes},
  booktitle =    {Proceedings of the Twenty-Ninth Annual ACM Symposium on Theory of Computing (STOC)},
  key =          {Spielman},
  year =         {1997}
}

% aka SpielLDPC see Luby2001b, better reference
@InProceedings{spielman-98-ISIT,
   author =       "M.~G. Luby and M. Mitzenmacher and M. A. Shokrollahi and
                    D.~A. Spielman",
   title =        "Improved Low-Density
       Parity-Check Codes Using Irregular Graphs and Belief Propagation",
   booktitle =   {Proceedings of the IEEE International Symposium on Info. Theory},
   year =         "1998",
   pages =        "117"
}                       

@unpublished{spielman-98-old,
   key =          "Spielman",
   author =       "M.~G. Luby and M. Mitzenmacher and M. A. Shokrollahi and
                    D.~A. Spielman",
   title =        "Improved Low-Density
       Parity-Check Codes Using Irregular Graphs and Belief Propagation",
   note =         "Submitted to ISIT98",
   year =         "1998"
}

@Book{pearl,
  author = 	 "J. Pearl",
  title = 	 "Probabilistic  Reasoning in Intelligent Systems: Networks of
                 Plausible Inference",
  publisher = 	 "Morgan Kaufmann",
  year = 	 1988,
  address =	 "San Mateo",
annote="2Y123, CL"
}

@Book{pearl2000,
  author = 	 "J. Pearl",
  title = 	 "Causality",
  publisher = 	 "Cambridge University Press",
  year = 	2000,
  address =	 "Cambridge"
}

@INPROCEEDINGS{NW91,
 KEY		="Weir",
 AUTHOR		="N. Weir",
 TITLE		="Applications of maximum entropy techniques to {HST} data",
 BOOKTITLE	="Proceedings of the {ESO/ST--ECF} Data Analysis Workshop, {A}pril 1991",
ADDRESS = "Garching",
EDITOR = "P.J. Grosbol and R.H. Warmels",
PUBLISHER = "European Southern Observatory/Space Telescope -- European
              Coordinating Facility",
PAGES = "115-129",
 YEAR		="1991"}

@ARTICLE{Kashyap,
 KEY		="Kashyap",
 AUTHOR		="R. L.  Kashyap",
 TITLE		="A {B}ayesian comparison of different classes of dynamic
        models using empirical data",
 JOURNAL	="IEEE Trans. on Automatic Control",
 YEAR		="1977",
 VOLUME		="AC-22",
 NUMBER		="5",
 PAGES		="715--727"}

% This paper includes a rediscovery of {B}ayesian model comparison and the fact 
% that it embodies Occam's razor. -- In the context of models for time series. 
% It also includes a thorough discussion of how this is different from `Hypothesis
% testing'. At a few points I disagree with his statements but nearly all of it 
% gets full marks from me. 
@BOOK{Lempers,
 KEY		="Lempers",
 AUTHOR		="F. B. Lempers",
 TITLE		="Posterior probabilities of alternative linear models",
 PUBLISHER	="Rotterdam University Press",
 YEAR		="1971"}

% Has a lot of discussion of conjugate priors. No mention of Occam's razor. 
% Looks readable in parts. 

%	Active learning
%	Experimental design 

@ARTICLE{Lindley,
 KEY		="Lindley",
 AUTHOR		="D.V. Lindley",
 TITLE		="On a measure of the information provided 
	by an experiment",
 JOURNAL	="Ann.\ Math.\ Statist.",
 YEAR		="1956",
 VOLUME		="27",
 PAGES		="986-1005"}

@INPROCEEDINGS{Skilling92,
 KEY		="Skilling",
 AUTHOR		="J. Skilling",
 TITLE		="{B}ayesian solution of ordinary differential equations",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {S}eattle 1991",
 EDITOR		="C.R. Smith and G.J. Erickson and P.O. Neudorfer",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1992",
 PAGES		="23-37"}

@misc{hexproof,
year={2002},
author={David Gale and Jack van Rijswijck},
title={Hex cannot end in a draw -- {P}roof},
note={Electronic publication: {{\tt{http://www.cs.ualberta.ca/\verb+~+javhar/hex/hex-galeproof.html}}}}
}

@misc{ibmponderthisMay99challenge,
author={IBM},
title={Ponder {T}his},
note={{\tt{http://www.research.ibm.com/ponder/}}, May 1999 challenge},
url={http://domino.research.ibm.com/Comm/wwwr\verb+_+ponder.nsf/challenges/May1999.html},
year={1999}
}
@misc{ibmponderthisMay99solution,
author={IBM},
title={Ponder {T}his, {May} 1999 Solution},
note={{\tt{http://domino.research.ibm.com/Comm/wwwr\verb+_+ponder.nsf/solutions/May1999.html}}},
url={\verb+http://domino.research.ibm.com/Comm/wwwr_+ponder.nsf/solutions/May1999.html},
year={1999}
}

@BOOK{Fedorov,
 KEY		="Fedorov",
 AUTHOR		="V.V. Fedorov",
 TITLE		="Theory of optimal experiments",
 PUBLISHER	="Academic press",
 YEAR		="1972"}

@BOOK{Fukunaga,
 KEY		="Fukunaga",
 AUTHOR		="K. Fukunaga",
 TITLE		="Introduction to statistical pattern recognition",
 PUBLISHER	="Academic press",
 YEAR		="1972"}

@INPROCEEDINGS{El-Gamal,
 KEY		="El-Gamal",
 AUTHOR		="M. A. El-Gamal",
 TITLE		="The role of priors in active {B}ayesian learning in the 
	sequential statistical decision framework",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {L}aramie, 1990",
 YEAR		="1991",
 EDITOR		="W. T.  Grandy and L. Schick",
 PUBLISHER	="Kluwer", 
 ADDRESS	="Dordrecht",
 PAGES		="33--38"}

@ARTICLE{Baum,
 KEY		="Baum",
 AUTHOR		="E. B. Baum",
 TITLE		="Neural Net algorithms that learn in 
	polynomial time from examples and queries",
 JOURNAL	="IEEE Trans. on neural 
	networks",
 YEAR		="1991",
 VOLUME		="2",
 NUMBER		="1",
 PAGES		="5--19"}



@Article{viterbi,
  author = 	 "A. J. Viterbi",
  title = 	 "Error bounds for convolutional codes
        and an asymptotically optimum decoding algorithm",
  journal =	 "IEEE
        Trans. on Info. Theory",
  year =	 1967,
  volume =	 "IT-13",
  pages =	 "260-269"
}

% review of Baum Welch algm
@ARTICLE{Baum_Welch,
 KEY		="",
 AUTHOR		="S. E. Levinson and L. R. Rabiner and M. M. Sondhi",
 TITLE		="An Introduction to the Application 
		of the Theory of Probabilistic Functions 
		of a {M}arkov Process to Automatic Speech Recognition",
 JOURNAL	="Bell Sys. Tech. J.",
 YEAR		="1983",
 VOLUME		="62",
 PAGES		="1035"}

% a noddier intro
@ARTICLE{HMM_intro,
 KEY		="",
 AUTHOR		="L. R. Rabiner and B. H. Juang",
 TITLE		="An Introduction to Hidden {M}arkov Models",
 JOURNAL	="IEEE ASSP Magazine",
 YEAR		="1986",
 MONTH="Jan",
 PAGES		="4-16"}

@ARTICLE{Speech_HMM,
 KEY		="",
 AUTHOR		="D. B. Paul",
 TITLE		="Speech Recognition using Hidden {M}arkov Models",
 JOURNAL	="The Lincoln Laboratory Journal",
 YEAR		="1990",
 VOLUME="3",
 NUMBER = 1,
 PAGES		="41-62"}

@ARTICLE{Baum_Welch_orig,
 KEY		="Baum and Petrie",
 AUTHOR		="L. E. Baum and T. Petrie",
 TITLE		="Statistical Inference for Probabilistic Functions of
		  Finite-State {M}arkov Chains",
 JOURNAL	="Ann. Math. Stat.",
 YEAR		="1966",
 VOLUME		="37",
 NUMBER		="",
 PAGES		="1559-1563"}

@ARTICLE{Query91,
 KEY		="Hwang \etal",
 AUTHOR		="J-N. Hwang and J.J. Choi and S. Oh and R.J. Marks II",
 TITLE		="Query-based learning applied to partially trained 
	multilayer perceptrons",
 JOURNAL	="IEEE Trans. on Neural 
	networks",
 YEAR		="1991",
 VOLUME		="2",
 NUMBER		="1",
 PAGES		="131--136"}

@TECHREPORT{Plutowski_White,
 KEY		="Plutowski and White",
 AUTHOR		="M. Plutowski and H. White",
 TITLE		="Active selection of training examples for Network learning 
	in noiseless environments",
 YEAR		="1991",
 NUMBER		="TR 90-011",
 INSTITUTION	="Dept. Computer Science, UCSD"}


%	MDL 

All three of these make clear that MDL = {B}ayes
@ARTICLE{Wallace_Freeman,
 KEY		="Wallace and Freeman",
 AUTHOR		="C. S. Wallace and P. R. Freeman",
 TITLE		="Estimation and Inference by Compact Coding",
 JOURNAL	="J.\ R.\ Statist.\ Soc.\ B",
 YEAR		="1987",
 VOLUME		="49",
 NUMBER		="3",
 PAGES		="240-265"}
 
@book{Wallace_book,
 KEY		="Mosteller and Wallace",
 AUTHOR		="F. Mosteller and D. L. Wallace",
title={Applied {B}ayesian and Classical Inference. 
The case of {\em The {F}ederalist\/} papers},
year={1984},
publisher={Springer}
}

@INCOLLECTION{Patrick_Wallace,
 KEY		="Patrick and Wallace",
 AUTHOR		="J. D. Patrick and C. S. Wallace",
 TITLE		="Stone circle geometries: an information 
	theory approach",
 BOOKTITLE	="Archaeoastronomy in the {O}ld {W}orld",
 YEAR		="1982",
 EDITOR		="D. C. Heggie",
 PAGES		="231-264",
 PUBLISHER	="Cambridge University Press"}
 
@ARTICLE{Schwarz,
 KEY		="Schwarz",
 AUTHOR		="G. Schwarz",
 TITLE		="Estimating the dimension of a model",
 JOURNAL	="Ann. Stat.",
 YEAR		="1978",
 VOLUME		="6 ",
 NUMBER		="2",
 PAGES		="461--464"}

@ARTICLE{WB,
 KEY		="Wallace and Boulton",
 AUTHOR		="C.S. Wallace and D.M. Boulton",
 TITLE		="An information measure for classification",
 JOURNAL	="Comput. J.",
 YEAR		="1968",
 VOLUME		="11 ",
 NUMBER		="2",
 PAGES		="185--194"}
 
%	Marginalization

@ARTICLE{Spiegelhalter,
 KEY		="Spiegelhalter and Lauritzen",
 AUTHOR		="D. J. Spiegelhalter and S. L. Lauritzen",
 TITLE		="Sequential updating of conditional probabilities on 
	directed graphical structures",
 JOURNAL	="Networks",
 YEAR		="1990",
 VOLUME		="20",
 NUMBER		="",
 PAGES		="579--605"}



@Article{Spieg93,
  author = 	 "D. J. Spiegelhalter and A. P. Dawid and S. L.
		  Lauritzen and R. G. Cowell",
  title = 	 "{B}ayesian Analysis in Expert Systems",
  journal =	 "Statistical Science",
  volume =	 8,
  number =	 3,
  pages =	 "219-283",
 year=1993
}

@book{lauritzen96,
 author = 	 "S. L.		  Lauritzen",
  title = 	 "Graphical Models",
 publisher={Clarendon Press},
 address={Oxford},
 year={1996},
 series={Oxford Statistical Science Series},
 number={17}
}
% fundamental theory of graphical models

% Bayesian Monte Carlo methods

@incollection{LindleyLaplace,
 author="D. V. Lindley",
 TITLE		="Approximate {B}ayesian Methods",
  booktitle =	 "Bayesian Statistics",
  publisher =	 "Valencia University Press",
  year =	 1980,
  editor =	 "J. M. Bernardo and M. H. DeGroot and D. V. Lindley and
		  A. F. M. Smith",
  pages =	 "223-237",
  address =	 "Valencia"
}

@incollection{bugs,
 author="A. Thomas and D. J. Spiegelhalter and W. R. Gilks",
 TITLE		="{BUGS}: A Program to Perform {B}ayesian Inference Using
		  {G}ibbs Sampling",
  booktitle =	 "Bayesian Statistics 4",
  publisher =	 "Clarendon Press",
  year =	 1992,
  editor =	 "J. M. Bernardo and J. O. Berger and A. P. Dawid and
		  A. F. M. Smith",
  pages =	 "837-842",
  address =	 "Oxford"
}

@article{Adler1981,
  title={Over-Relaxation Method for the {M}onte-{C}arlo Evaluation of the 
    Partition Function for Multiquadratic Actions},
  author={Adler, S. L.},
  journal={Physical Review D -- Particles and Fields},
  year={1981},
  volume={23},
  number={12},
  pages={2901-2904}
}
% importance resampling
@article{ berzuini97dynamic,
    author = "Carlo Berzuini and Nicola G. Best and Walter R. Gilks and Cristiana Larizza",
    title = "Dynamic Conditional Independence Models and {Markov} Chain {Monte Carlo} Methods",
    journal = "Journal of the American Statistical Association",
    volume = "92",
    number = "440",
    pages = "1403-1412",
    year = "1997",
    url = "citeseer.nj.nec.com/berzuini97dynamic.html" }

% Gilks, WR, Berzuini, C (2001). Following a moving target -- Monte Carlo inference for dynamic Bayesian models. Journal of the Royal Statistical Society Series B-Statistical Methodology , 63, 127-146.
@article{BerzuiniGilks2001,
title={Following a moving target -- {M}onte {C}arlo inference for dynamic {B}ayesian models},
author= "Carlo Berzuini and  Walter R. Gilks",
journal={Journal of the Royal Statistical Society Series B -- Statistical Methodology},
Year=2001,
Volume=63,
Number=1,
Pages={127-146}
}
% http://www-sigproc.eng.cam.ac.uk/~ad2/arnaud_doucet.html
@article{Doucetetal2000,
title={On Sequential {M}onte {C}arlo Sampling Methods for {B}ayesian Filtering},
author={A. Doucet and  S.J. Godsill and C. Andrieu},
journal={Statistics and Computing}, volume={10}, number={3}, pages={197-208},
year={2000}
}

@Article{Gilks_Wild,
  author = 	 "Gilks, W.R. and Wild, P.",
  title = 	 "Adaptive Rejection Sampling for {G}ibbs Sampling",
  journal =	 "Applied Statistics",
  year =	 1992,
  volume =	 41,
  pages =	 "337-348"
}
@Article{Gilks_RG_ADS,
  author = 	 "Gilks, W.R. and Roberts, G.O. and George, E.I.",
  title = 	 "Adaptive Direction Sampling",
  journal =	 "Statistician",
  year =	 1994,
  volume =	 43,
  pages =	 "179-189"
}

%	neural net algorithm for MaxEnt:

@ARTICLE{MP2,
 KEY		="Marrian and Peckerar",
 AUTHOR		="C. R. K. Marrian and M. C. Peckerar",
 TITLE		="Electronic Neural Net Algorithm for Maximum Entropy Solutions of 
	Ill-Posed Problems",
 JOURNAL	="IEEE Trans. Circ. Sys.",
 YEAR		="1989",
 VOLUME		="36",
 NUMBER		="",
 PAGES		="288--294"}

@INPROCEEDINGS{MP1,
 KEY		="Marrian and Peckerar",
 AUTHOR		="C. R. K. Marrian and M. C. Peckerar",
 TITLE		="Electronic Neural Net Algorithm for Maximum Entropy Solutions of 
	Ill-Posed Problems",
 BOOKTITLE	="Maximum Entropy and {B}ayesian Methods, {C}ambridge 1988",
 EDITOR		="J. Skilling",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR		="1989"}


%	NEURAL NETS OPTIMISATION OF number parameters, regularisers, etc. 

@INCOLLECTION{Weigend,
 KEY		="Weigend et. al.",
 AUTHOR		="A. S. Weigend and D. E. Rumelhart 
	and B. A. Huberman",
 TITLE		="Generalization by weight-elimination 
	with applications to forecasting",
 BOOKTITLE	="Advances in Neural Information Processing Systems 3",
 YEAR		="1991",
 EDITOR		="R. P. Lippmann et. al.",
 PAGES		="875--882",
 PUBLISHER	="Morgan Kaufmann"}

@PHDTHESIS{Nowlan,
 KEY		="Nowlan",
 AUTHOR		="Steven J. Nowlan",
 TITLE		="Soft competitive adaptation:
	neural Network learning algorithms based on fitting statistical mixtures",
 YEAR		="1991",
type={PhD},
 NOTE		="CS--91--126",
 SCHOOL		="Carnegie Mellon University"}

@PHDTHESIS{GibbsPhD,
 AUTHOR		="M. N. Gibbs",
 TITLE		="{B}ayesian {G}aussian Processes for Regression and Classification",
 YEAR		="1997",
type={PhD},
 SCHOOL		="Cambridge University",
 note = 	 "{\tt http://www.inference.phy.cam.ac.uk/mng10/}",
}

@article{Williams1998,
  title={Computation with infinite neural networks},
  author={Williams, C. K. I.},
  journal={Neural Computation},
  year={1998},
  volume={10},
  number={5},
  pages={1203-1216},
  abstract={For neural networks with a wide class of weight priors, it can be 
    shown that in the limit of an infinite number of hidden units, the 
    prior over functions tends to a gaussian process. In this article, 
    analytic forms are derived for the covariance function of the 
    gaussian processes corresponding to networks with sigmoidal and 
    gaussian hidden units. This allows predictions to be made efficiently
    using networks with an infinite number of hidden units and shows, 
    somewhat paradoxically, that it may be easier to carry out {B}ayesian 
    prediction with infinite networks rather than finite ones.}
}

@INCOLLECTION{BM,
 KEY		="Hinton and Sejnowski",
 AUTHOR		="G. E. Hinton and T. J.  Sejnowski",
 TITLE		="Learning and relearning in {B}oltzmann machines",
 BOOKTITLE	="Parallel Distributed Processing",
 YEAR		="1986",
 EDITOR		="D. E. Rumelhart and J. E. McClelland",
 PAGES		="282--317",
 PUBLISHER	="MIT Press",
 ADDRESS        ="Cambridge MA"}

@ARTICLE{Ji,
 KEY		="Ji \etal",
 AUTHOR		="C. Ji and R. R.  Snapp and D. Psaltis",
 TITLE		="Generalizing smoothness constraints from discrete samples",
 JOURNAL	="Neural Computation",
 YEAR		="1990",
 VOLUME		="2 ",
 NUMBER		="2",
 PAGES		="188-197"}

@TECHREPORT{LT,
 KEY		="Lee and Tenorio",
 AUTHOR		="W. T.  Lee and M. F.  Tenorio",
 TITLE		="On Optimal Adaptive Classifier Design Criterion --
	How many hidden units are Necessary for an optimal Neural 
	network classifier?",
 YEAR		="1991",
 NUMBER		="TR-EE-91-5",
 INSTITUTION	="Purdue University"}

@ARTICLE{Abu1,
 KEY		="Abu-Mostafa",
 AUTHOR		="Y. S.  Abu-Mostafa",
 TITLE		="The {V}apnik-{C}hervonenkis
	dimension: information versus complexity in learning",
 JOURNAL	="Neural Computation",
 YEAR		="1990",
 VOLUME		="1 ",
 NUMBER		="3",
 PAGES		="312--317"}

@ARTICLE{Abu,
 KEY		="Abu-Mostafa",
 AUTHOR		="Y. S.  Abu-Mostafa",
 TITLE		="Learning from hints in Neural Networks",
 JOURNAL	="J. Complexity",
 YEAR		="1990",
 VOLUME		="6",
 NUMBER		="",
 PAGES		="192--198"}

% 	includes an example of a regulariser `hint'

@INPROCEEDINGS{Haussler,
 KEY		="Haussler \etal",
 AUTHOR		="D. Haussler and M. Kearns and R. Schapire",
 TITLE		="Bounds on the sample complexity of {B}ayesian learning using information 
	theory and the {VC} dimension",
 BOOKTITLE	="Proceedings of the fourth {COLT} workshop",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1991"
}

%	OTHER PAPERS ON OCCAM

@INPROCEEDINGS{Ponting,
 KEY		="Ponting",
 AUTHOR		="K. M.  Ponting",
 TITLE		="A statistical approach to the determination of
		  hidden {M}arkov model structure",
 BOOKTITLE	="7th {FASE} Symposium",
 YEAR		="1988",
 PUBLISHER	=""}


%---------------------------------
@ARTICLE{Angel,
 KEY		="Angel \etal",
 AUTHOR		="J. R. P. Angel and P. Wizinowich and  M. Lloyd-Hart and D. Sandler",
 TITLE		="Adaptive optics for array telescopes using Neural-network techniques",
 JOURNAL	="Nature",
 YEAR		="1990",
 VOLUME		="348",
 NUMBER		="",
 PAGES		="221--224"}
 % Nov 1990
% J. R. P. Angel
% Steward Observatory
% University of Arizona
% Tucson
% AZ 85721
% USA




@ARTICLE{Bayes,
 KEY		="Bayes",
 AUTHOR		="Thomas Bayes",
 TITLE		="An essay towards solving a problem in the 
                       doctrine of chances",
 JOURNAL	="Philos. Trans. R. Soc. London",
 YEAR		="1763",
 VOLUME		="53",
 NUMBER		="",
 PAGES		="370--418"}

% , reprinted in {\em Biometrika} (1958) {\bf 45}, 293--315

@BOOK{Bretthorst,
 KEY		="Bretthorst",
 AUTHOR		="G.L. Bretthorst",
 TITLE		="{B}ayesian Spectrum Analysis
	and Parameter Estimation",
 PUBLISHER	="Springer",
 YEAR		="1988",
 NOTE={Also available at {\tt http://bayes.wustl.edu}}
}
% In this book, he studies the inference of exponential functions
% from noisy data, and especially oscillatory decaying functions
% exp(-l x)*(A sin omega x + phi).
@ARTICLE{Bretthorst.JMR,
 KEY		="Bretthorst",
 AUTHOR		="G.L. Bretthorst",
 TITLE		="{B}ayesian Analysis. 
	{I}. Parameter Estimation Using Quadrature NMR Models. 
	{II}. Signal Detection and Model Selection.
	{III}. Applications to NMR.",
 JOURNAL	="J. Magnetic Resonance",
 YEAR		="1990",
 VOLUME		="88 ",
 NUMBER		="3",
 PAGES		="533--595"}

 
@INPROCEEDINGS{Gull:nonparam,
 KEY		="Gull and Fielden",
 AUTHOR		="S. F.  Gull and J. Fielden",
 TITLE		="{B}ayesian Non-Parametric Statistics",
 BOOKTITLE	=" Maximum Entropy and {B}ayesian Methods in 
	Applied Statistics,",
 EDITOR		="J. H.  Justice",
 PUBLISHER	="Cambridge University Press",
 ADDRESS	="Cambridge",
 YEAR		="1986",
 PAGES		="85-94"}
 
@BOOK{Jeffreys,
 KEY		="Jeffreys",
 AUTHOR		="H. Jeffreys",
 TITLE		="Theory of Probability",
 PUBLISHER	="Oxford Univ. Press",
 YEAR		="1939",
 NOTE="3rd edition reprinted 1985"}
 
@ARTICLE{Rissanen1,
 KEY		="Rissanen",
 AUTHOR		="J. Rissanen",
 TITLE		="Modeling by shortest data description",
 JOURNAL	="Automatica",
 YEAR		="1978",
 VOLUME		="14",
 NUMBER		="",
 PAGES		="465--471"}
  
@TECHREPORT{Seung,
 KEY		="Seung \etal",
 AUTHOR		="H. S.  Seung and H. Sompolinsky and N. Tishby",
 TITLE		="Statistical mechanics of learning from examples",
 YEAR		="1991",
 NUMBER		="",
 INSTITUTION	="preprint"}

@techreport{ holmes99perfect,
  author = "C. Holmes and B. Mallick",
  title = "Perfect simulation for {B}ayesian curve and surface fitting",
  text = "C C Holmes and B K Mallick, Perfect simulation for {B}ayesian curve and
    surface fitting, Tech. Rep., Imperial College, 1999.",
  year = "1999",
institution="Imperial College, London",
  url = "citeseer.nj.nec.com/holmes99perfect.html"
}
@techreport{ holmes98perfect,
  author = "C. Holmes and B. Mallick",
  title = "Perfect simulation for orthogonal model mixing",
  text = "Holmes, C. C. & Mallick, B. K. (1998). Perfect simulation for orthogonal
    model mixing. Technical report, Imperial College, London",
  institution="Imperial College, London",
  year = "1998",
  url = "citeseer.nj.nec.com/holmes98perfect.html" }


@article{LeeSeung,
title={Learning the parts of objects by non-negative matrix factorization},
author={Daniel D. Lee and H. S. Seung},
journal={Nature},
volume={401},
pages={788-791},
year={1999},
abstract={
Is perception of the whole based on perception of its parts? There is psychological and
physiological evidence for parts-based representations in the brain, and certain
computational theories of object recognition rely on such representations. But little is
known about how brains or computers might learn the parts of objects. Here we
demonstrate an algorithm for non-negative matrix factorization that is able to learn
parts of faces and semantic features of text. This is in contrast to other methods, such as
principal components analysis and vector quantization, that learn holistic, not
parts-based, representations. Non-negative matrix factorization is distinguished from
the other methods by its use of non-negativity constraints. These constraints lead to a
parts-based representation because they allow only additive, not subtractive,
combinations. When non-negative matrix factorization is implemented as a neural
network, parts-based representations emerge by virtue of two properties: the firing rates
of neurons are never negative and synaptic strengths do not change sign.
}
}
@BOOK{Szeliski,
 KEY		="Szeliski",
 AUTHOR		="R. Szeliski",
 TITLE		="{B}ayesian modeling of uncertainty in low level vision",
 PUBLISHER	="Kluwer",
 YEAR		="1989"}

@BOOK{Rao&Fujiwara,
 KEY		="Rao&Fujiwara",
 AUTHOR		="T. R. N. Rao and E. Fujiwara",
 TITLE		="Error-control Coding for Computer Systems",
 PUBLISHER	="Prentice-Hall",
 YEAR		="1989"}

% From haussler
% We just did a journal version as an invited paper to the special
% issue of MAchine Learning, on the COLT `91 conference. However, that
% paper is still being reviewed. This long version will appear also as
% tech rep UCSC-CRL-91-44. Right now though, the best references to this
% and related work are:
@inproceedings{OH.colt,
 author=   "Opper, M. and D. Haussler",
 title=    "Calculation of the learning curve of {B}ayes Optimal
 classification algorithm for learning a perceptron with noise",
 booktitle= "Computational Learning Theory: Proceedings of the
                        Fourth Annual Workshop",
 publisher= "Morgan Kaufmann",
 pages= "75-87",
 year=     1991
}
 
@inproceedings{HKS,
 author= "Haussler, D. and M. Kearns and R. Schapire",
 title=  "Bounds on the sample complexity of {B}ayesian learning
  using information theory and the {VC} dimension",
 booktitle= "Proceedings of the Fourth Workshop on Computational
  Learning Theory",
 pages= "61-74",
 year= 1991
}

@misc{surveyPropagation,
year={2003},
note={{\tt{cs.CC/0212002}}},title={Survey propagation: an algorithm for satisfiability},
Author={Braunstein, A. and M\'ezard, M. and R. Zecchina},
abstract={
We study the satisfiability of randomly generated formulas formed by
$M$ clauses of exactly $K$ literals over $N$ Boolean variables. For a
given value of $N$ the problem is known to be most difficult with
$\alpha=M/N$ close to the experimental threshold $\alpha_c$ separating
the region where almost all formulas are SAT from the region where all
formulas are UNSAT. Recent results from a statistical physics analysis
suggest that the difficulty is related to the existence of a
clustering phenomenon of the solutions when $\alpha$ is close to (but
smaller than) $\alpha_c$. We introduce a new type of message passing
algorithm which allows to find efficiently a satisfiable assignment of
the variables in the difficult region. This algorithm is iterative and
composed of two main parts. The first is a message-passing procedure
which generalizes the usual methods like Sum-Product or Belief
Propagation: it passes messages that are surveys over clusters of the
ordinary messages. The second part uses the detailed probabilistic
information obtained from the surveys in order to fix variables and
simplify the problem. Eventually, the simplified problem that remains
is solved by a conventional heuristic.  }
}
 
@article{OH.prl,
 author=   "Opper, M. and D. Haussler",
 title=    "Generalization performance of {B}ayes Optimal classification
  algorithm for learning a perceptron",
 journal= "Physical Review Letters",
 year=     1991,
 volume= 66,
 number= 20,
 month=    May,
 pages=   "2677-2680"
}

@misc{Postol,
 author={Michael S. Postol},
 title={A Proposed Quantum Low Density Parity Check Code},
 year={2001},
note={{\tt{quant-ph/0108131}}}
}

@article{Kitaev97,
author={A. Yu. Kitaev},
journal={Annals Phys.},
volume={303},
year={2003},
pages={2-30},
title={Fault-tolerant quantum computation by anyons},
note={{\tt{quant-ph/9707021}}}, eprint    = "quant-ph/9707021",
abstract={A two-dimensional quantum system with anyonic excitations can be considered as a quantum computer. Unitary transformations can be performed by moving the excitations around each other. Measurements can be performed by joining excitations in pairs and observing the result of fusion. Such computation is fault-tolerant by its physical nature.}
}

@misc{Dennis00,
note={{\tt{quant-ph/0007072}}},
year={2000},
author={Dennis, Eric},
annote={edennis@physics.ucsb.edu},
title={Quantum codes on high-genus surfaces},
abstract={   An economy of scale is found when storing many qubits in
one highly entangled block of a topological quantum code. The code is
defined by construction of a topologically convoluted 2-d surface and
does not work by compressing redundancy in the encoded information}
}

@article{DennisKitaevLandahlPreskill,
note={{\tt{quant-ph/0110143}}},
title={Topological quantum memory},
author={Dennis, Eric and  Kitaev, Alexei and  Landahl, Andrew and Preskill, John },
annote={CALT-68-2346},
journal={J. Math. Phys.},volume={43},pages={4452-4505},
year={2002},
abstract={
We analyze surface codes, the topological quantum error-correcting
codes introduced by Kitaev. In these codes, qubits are arranged in a
two-dimensional array on a surface of nontrivial topology, and encoded
quantum operations are associated with nontrivial homology cycles of
the surface. We formulate protocols for error recovery, and study the
efficacy of these protocols. An order-disorder phase transition occurs
in this system at a nonzero critical value of the error rate; if the
error rate is below the critical value (the accuracy threshold),
encoded information can be protected arbitrarily well in the limit of
a large code block. This phase transition can be accurately modeled by
a three-dimensional Z_2 lattice gauge theory with quenched
disorder. We estimate the accuracy threshold, assuming that all
quantum gates are local, that qubits can be measured rapidly, and that
polynomial-size classical computations can be executed
instantaneously. We also devise a robust recovery procedure that does
not require measurement or fast classical processing; however for this
procedure the quantum gates are local only if the qubits are arranged
in four or more spatial dimensions. We discuss procedures for
encoding, measurement, and performing fault-tolerant universal quantum
computation with surface codes, and argue that these codes provide a
promising framework for quantum computing architectures.  } }

@ARTICLE{dirichlet,
 KEY		="Zabell",
 AUTHOR		="S. L.  Zabell",
 TITLE		="{W. E. Johnson}'s `sufficientness'        postulate",
 JOURNAL	="Annals of Statistics",
 YEAR		="1982",
 VOLUME		="10 ",
 NUMBER		="4",
 PAGES		="1091-1099"}


% Smoothing method in compression:  was Cleary_compression
@ARTICLE{cleary84,
 KEY		="Cleary and Witten",
 AUTHOR		="Cleary, J. G.  and Witten, I. H.",
 TITLE		="Data compression using 
		     adaptive coding and partial string matching",
 JOURNAL	="IEEE Trans. on Communications",
 YEAR		="1984",
 VOLUME		="32",
 PAGES		="396-402"}
% The model used isn't phrased in quite the same way as you do.  For each
% symbol, they look at the longest context that is has occurred before,
% and try to predict on the basis of the statistics available for that,
% but with a certain probability of an "escape" to a lower-order context.
% The book _Text Compression_ by Bell and Witten also covers this stuff
% (and is more recent).  
% Bell, Timothy C.
%                 Cleary, John G.
%                 Witten, Ian H.

@book{Hebb49,
author = "D. O. Hebb",
title = "The Organization of Behavior",
year = 1949,
publisher = "Wiley"}

@article{ Grayetal89,
author = "Charles M. Gray and Peter Konig and Andreas K. Engel and Wolf Singer",
title = "Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties",
journal = "Nature",
year  = 1989,
month = mar,
volume = 338,
pages = "334--337"}


@BOOK{Bell_Compression,
 KEY		="Bell, Cleary and Witten",
 AUTHOR		="Bell, T. C. and 
                 Cleary, J. G. and 
                 Witten, I. H.",
 TITLE		="Text compression",
 ADDRESS	="Englewood Cliffs",
 PUBLISHER	="Prentice Hall",
 YEAR		="1990"}
% Location:       [Computer Laboratory] 2Y50                                     
% Arithmetic coding: Witten, Neal and Cleary
@ARTICLE{arith_coding,
 KEY		="Witten \etal",
 AUTHOR		="I. H. Witten and R. M. Neal and J. G. Cleary",
 TITLE		="Arithmetic Coding for Data Compression",
 JOURNAL	="Communications of the ACM",
 YEAR		="1987",
 VOLUME		="30",
 NUMBER		="6",
 PAGES		="520--540",
annote={Communications of the  Association for Computing Machinery}
}
@article{arith_coding_revisited,
author={Moffat, A., Neal, R. M., and Witten, I. H.},
year={1998},
title={Arithmetic coding revisited},
journal={ACM Transactions on Information Systems},
volume={16},
pages={256-294}
}

@article{Gallager78,
 author= {Gallager, R. G.},
title="Variations on a Theme by {H}uffman",
journal={IEEE Trans. on Info. Theory}, Volume={IT-24}, Number={6},
month={Nov.},
year={1978},
pages={668-674}} 

% Abstract:
% The state of the art in data compression is arithmetic coding, not the 
% better known Huffman method. Arithmetic coding gives greater compression,
% is faster for adaptive models, and clearly separates the model from the 
% channel encoding.

@ARTICLE{Rissanen_arith,
 KEY		="Rissanen",
 AUTHOR		="J. Rissanen",
 TITLE		="Generalized {K}raft Inequality and Arithmetic Coding",
 JOURNAL	="IBM J. Res. Dev.",
 YEAR		=1976,
 MONTH ="May",
 VOLUME		=20,
 PAGES		="198-203"}
  
@ARTICLE{Rissanen_Langdon,
 KEY		="Rissanen",
 AUTHOR		="J. Rissanen and G. G. Langdon",
 TITLE		="Universal Modeling and Coding",
 JOURNAL	="IEEE Trans. Info. Theory",
 YEAR		="1981",
 VOLUME		="27",
 NUMBER		="1",
 PAGES		="12-23"}

@ARTICLE{Rissanen_Langdon:79,
 KEY		="Rissanen and Langdon",
 AUTHOR		="J. Rissanen and G. G. Langdon",
 TITLE		="Arithmetic Coding",
 JOURNAL	="IBM Journal of Research and Development",
 YEAR		="1979",
 VOLUME		="23",
 PAGES		="149-162"}

% ``Smoothing" a la IBM

@ARTICLE{Bahl,
 KEY		="Bahl et. al.",
 AUTHOR		="L. R.  Bahl and F. Jelinek and R. L.  Mercer",
 TITLE		="A maximum likelihood approach to continuous speech 
	recognition",
 JOURNAL	="IEEE Trans",
 YEAR		="1983",
 VOLUME		="PAMI--5 ",
 NUMBER		="2",
 PAGES		="179-190"}

% coding theorists forward-backward
@ARTICLE{BCJR,
 KEY		="Bahl et. al.",
 AUTHOR		="L. R.  Bahl and J. Cocke and F. Jelinek and J. Raviv",
 TITLE		="Optimal Decoding of Linear Codes for Minimizing
		  Symbol Error Rate",
  journal =      {IEEE Trans. on Info. Theory},
 YEAR		="1974",
 VOLUME		="IT-20",
 NUMBER		="",
 PAGES		="284-287"}

@INPROCEEDINGS{Bahl2,
 KEY		="Bahl et. al.",
 AUTHOR		="L. R.  Bahl and P. F. Brown and de Souza, P. V. and  R. L.  Mercer and D. Nahamoo",
 TITLE		="A fast algorithm for deleted interpolation",
 BOOKTITLE	="Proc. Eurospeech '91 Genoa",
 YEAR		="1991",
 PAGES		="1209-1212"}

@article{hopfieldbrody2000,
author={Hopfield, J. J. and  Brody, C. D.},
 year={2000}, Title={What is a moment?
 ``{C}ortical" sensory integration over a brief interval},
 journal={{Proc. Natl. Acad. Sci}},
 volume={97},
pages={13919-13924}
}
@article{hopfieldbrody2001,
author={Hopfield, J. J. and  Brody, C. D.},
 year={2001}, Title={What is a moment? {T}ransient synchrony as a collective mechanism for spatiotemporal integration},
 journal={{Proc. Natl. Acad. Sci}},
 volume={98},
pages={1282-1287}
}

% What is a moment? 

@INPROCEEDINGS{Jelinek_Mercer,
 KEY		="Jelinek and Mercer",
 AUTHOR		="F. Jelinek and R. L.  Mercer",
 TITLE		="Interpolated estimation of {M}arkov source parameters
	from sparse data",
 BOOKTITLE	="Pattern recognition in practice", 
 EDITOR		="E. S.  Gelsema and L. N.  Kanal",
 PUBLISHER	="North--Holland publishing company",
 YEAR		="1980",
 PAGES		="381-402"}

@ARTICLE{Nadas,
 KEY		="Nadas",
 AUTHOR		="A. Nadas",
 TITLE		="Estimation of probabilities in the language model of the 
	{IBM} speech recognition system",
 JOURNAL	="IEEE Trans",
 YEAR		="1984",
 VOLUME		="ASSP--32 ",
 NUMBER		="4",
 PAGES		="859--861"}

% and a backing off paper: 
@ARTICLE{katz-backoff,
        AUTHOR             = {S. M. Katz},
        JOURNAL            = ASSP,
        PAGES              = {400-401},
        TITLE              = {Estimation of probabilities from sparse data for the language model component of a speech recognizer},
        VOLUME             = {35},
        NUMBER             = {3},
        MONTH              = {March},
        YEAR               = {1987}
}

@inproceedings{Brown:88a,
  author={Peter F. Brown and John Cocke and Stephen A. DellaPietra
          and Vincent J. DellaPietra and Frederick Jelinek
          and Robert L. Mercer and Paul S. Roossin},
  title={A Statistical Approach to Language Translation},
  booktitle={Proceedings of the 12th International Conference
             on Computational Linguistics},
  year={1988},
  pages={71-76},
  address={Budapest, Hungary},
  month      ={August}}


@inproceedings{lafferty-codes,
  author = "John Lafferty and Dan Rockmore",
  title = "Codes and Iterative Decoding on Algebraic Expander Graphs",
  booktitle= "International Symposium on Info. Theory and its Applications",
  year = "2000",
  month = "November",
  location = "Honolulu, HI",
  url = "citeseer.nj.nec.com/lafferty00code.html"
}  

@misc{ lafferty-codesB,
  author = "John D. Lafferty and Dan Rockmore",
  title = "Codes And Iterative Decoding on Algebraic Expander Graphs",
  url = "citeseer.nj.nec.com/lafferty00code.html",
note={International Symposium on Info. Theory and its Applications},
annote={Honolulu, Hawaii, USA, November 5-8},
year=2000}

@unpublished{MacKay_Lafferty,
 title={Codes from {C}ayley graphs},
 author={D. J. C.  MacKay and J. Lafferty},
 note={Work in progress},
 year={1997}
}

@article{Brown:90b,
  author={Peter F. Brown and John Cocke and Stephen A. DellaPietra and
          Vincent J. DellaPietra and Frederick Jelinek
          and John D. Lafferty
          and Robert L. Mercer and Paul S. Roossin},
  title={A Statistical Approach to Machine Translation},
  journal={Computational Linguistics},
  year={1990},
  month={June},
  volume={16},
  number={2},
  pages={79-85}}

@article{Brown:91g,
  author ={Peter F. Brown and Stephen A. DellaPietra
           and Vincent J. DellaPietra
           and Robert L. Mercer},
  title={The Mathematics of Statistical
         Machine Translation: Parameter Estimation},
  year={1993},
  journal={Computational Linguistics},
  month={June},
  volume={19},
  number={2},
  pages={263-311}}
% The most comprehensive paper is Brown:91g.

@inproceedings{Brown:91f,
  author ={Peter F. Brown and Stephen A. DellaPietra
           and Vincent J. DellaPietra
           and Robert L. Mercer},
  title={A Statistical Approach to Sense Disambiguation in
         Machine Translation},
  booktitle={Fourth DARPA Workshop on Speech and Natural Language},
  year={1991},
  publisher={Morgan Kaufmann},
  pages={146-151},
  address={Pacific Grove, CA},
  month={February}}

@inproceedings{Brown:92a,
  author ={Peter F. Brown and Stephen A. DellaPietra
           and Vincent J. DellaPietra
           and John Lafferty
           and Robert L. Mercer},
  title={Analysis, Statistical Transfer, and Synthesis in Machine
         Translation},
  booktitle={Proceedings of the Fourth International Conference
  on Theoretical and Methodological Issues in Machine Translation},
  year={1992},
  pages={83-100}}

@misc{Brown:92e,
  author ={Peter F. Brown and Stanley F. Chen and Stephen A. DellaPietra
           and Vincent J. DellaPietra and Andrew S. Kehler
           and Robert L. Mercer},
  title={Automatic Speech Recognition in Machine Aided Translation},
  year={1992},
  howpublished={Submitted to Computers Speech and Language}}



% Using spaker independent data aas a prior for a speaker dependent machine
@INPROCEEDINGS{Lee_Gauvain,
 KEY		="Lee and Gauvain",
 AUTHOR		="C. H. Lee and J. L. Gauvain",
 TITLE		="Speaker Adaptation Based on {MAP} Estimation of {HMM}
			Parameters",
 BOOKTITLE	="IEEE Proceedings",
 PAGES		="II-558-561",
 YEAR		="1993"}
 

@ARTICLE{Copas:83,
 KEY		="Copas",
 AUTHOR		="J. B. Copas",
 TITLE		="Regression, Prediction and Shrinkage (with Discussion)",
 JOURNAL	="J.\ R.\ Statist.\ Soc.\ B",
 YEAR		="1983",
 VOLUME		="45",
 NUMBER		="3",
 PAGES		="311-354"}
% This discusses ``Preshrunk predictors". 
% It does also give the Bayesian answer for one case, but then rambles
%		  off again to terrible
%		  all-predictions-fudged-by-factor-k
%                 methods. 

% This one is about including the possibility of incorrect binary labels
@ARTICLE{Copas:88,
 KEY		="Copas",
 AUTHOR		="J. B. Copas",
 TITLE		="Binary Regression Models for Contaminated Data
 (with Discussion)",
 JOURNAL	="J.\ R.\ Statist.\ Soc.\ B",
 YEAR		="1988",
 VOLUME		="50",
 NUMBER		="2",
 PAGES		="225-265"}


@INPROCEEDINGS{Nowlan.sunspot,
 KEY		="Nowlan and Hinton",
 AUTHOR		="Steven J. Nowlan and G. E. Hinton",
 TITLE		="Adaptive Soft Weight Tying using {G}aussian Mixtures",
 BOOKTITLE	="Advances in Neural Information Processing Systems 4",
 EDITOR		="J. E. Moody and S. J. Hanson and R. P. Lippmann",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1992",
 PAGES		="993--1000"}


@BOOK{Reif,
 KEY		="Reif",
 AUTHOR		="F. Reif",
 TITLE		="Fundamentals of Statistical and Thermal Physics",
 PUBLISHER	="McGraw--Hill",
 YEAR		="1965"}

@INPROCEEDINGS{Brain_Surgeon,
 KEY		="Hassibi and Stork",
 AUTHOR		="B. Hassibi and D. G. Stork",
 TITLE		="Second Order Derivatives for Network Pruning:
			Optimal Brain Surgeon",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		="164-171"}
% They use a cute iterative procedure for calculating the inverse
% (Hessian+alpha I) in a single pass through the data, with a large number of
% matrix multiplications. 

@INPROCEEDINGS{LSP:hessian,
 KEY		="LeCun et. al.",
 AUTHOR		="LeCun, Y. and P. Y. Simard and B. Pearlmutter",
 TITLE		="Automatic Learning Rate Maximization by On-line
			Estimation of the Hessian's Eigenvectors",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		="156-163"}

@INPROCEEDINGS{SLD:nips5,
 KEY		="Simard, LeCun and Denker",
 AUTHOR		="P. Simard and LeCun, Y. and J. Denker",
 TITLE		="Efficient Pattern Recognition Using a New
			Transformation Distance",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		="50-58"}

@INPROCEEDINGS{nips6,
 KEY		="",
 AUTHOR		="",
 TITLE		="",
 BOOKTITLE	="Advances in Neural Information Processing Systems 6",
 EDITOR		="J. D. Cowan and G. Tesauro and J. Alspector",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1994",
 PAGES		=""}

@article{HintonGhahramani97,
    author = "Geoffrey E. Hinton and Zoubin Ghahramani",
    title = "Generative Models for Discovering Sparse Distributed Representations",
    journal = "Philosophical Trans. Royal Society B",
    volume = "352",
    number = "1177--1190",
    year = "1997",
    url = "citeseer.nj.nec.com/article/hinton97generative.html" }

@INPROCEEDINGS{Hinton_Zemel:94,
 AUTHOR		="Hinton, G. E. and Zemel, R. S.",
 TITLE		="Autoencoders, Minimum Description Length and {H}elmholtz
				Free Energy",
 BOOKTITLE	="Advances in Neural Information Processing Systems 6",
 EDITOR		="J. D. Cowan and G. Tesauro and J. Alspector",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1994",
 PAGES		=""}

@PHDTHESIS{Zemel_thesis,
 AUTHOR		="Zemel, R. S.",
 TITLE		="A Minimum Description Length Framework for Unsupervised
				Learning",
 SCHOOL	="University of Toronto",
 YEAR		=1993}

@UNPUBLISHED{Steeg:94,
 AUTHOR		="E. Steeg",
 TITLE		="",
 NOTE		="Personal communication",
 YEAR		="1994"}

@INPROCEEDINGS{boosting,
 KEY		="",
 AUTHOR		="H. Drucker and R. Schapire and P. Simard",
 TITLE		="Improving Performance in Neural Networks Using a 
			Boosting Algorithm",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		="42-49"}
% I would call this a data selection procedure, plus a funky modelling
% rule. It depends theoretically on the assumption that the model can
% do better than 50% on any sub-ensemble from the training set. 

@INPROCEEDINGS{nips5,
 KEY		="",
 AUTHOR		="",
 TITLE		="",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		=""}

@INPROCEEDINGS{Wolpert_nips,
 KEY		="Wolpert",
 AUTHOR		="D. H.  Wolpert",
 TITLE		="On the use of evidence in Neural Networks",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		="539-546"}

@INPROCEEDINGS{Neal_nips5,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="{B}ayesian learning via stochastic dynamics",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		="475-482"}


@Book{jordan98:_learn_graph_model,
  editor =	 {M. I. Jordan},
  title = 	 {Learning in Graphical Models},
  publisher = 	 {Kluwer Academic Publishers},
  year = 	 1998,
  series =	 {NATO Science Series},
address={Dordrecht}
}

% A New View of the EM Algorithm
% that Justifies Incremental and
% Other Variants 
%
% R. M. Neal and Geoffrey E. Hinton, Dept. of Computer Science, University of Toronto

@Incollection{NealHinton98,
author="R. M. Neal and G. E. Hinton",
title="A New View of the {EM} Algorithm that Justifies Incremental, Sparse, and Other Variants",
  publisher = "Kluwer",
booktitle={Learning in Graphical Models},
  year = 	 "1998",
  editor = 	 "M. I. Jordan",
  pages = 	 "355-368",
series={NATO Science Series}
}
@article{NealHinton93,
author="R. M. Neal and G. E. Hinton",
title="A New View of the {EM} Algorithm that Justifies Incremental, Sparse, and Other Variants",
journal="Biometrika",
month=feb,
year=1993,
note="submitted"}
% see erice volume NealHinton98

@article{Thodberg1996,
  title={Review of {B}ayesian neural networks with an application to near 
    infrared spectroscopy},
  author={Thodberg, H. H.},
  journal={IEEE Trans. on Neural Networks},
  year={1996},
  volume={7},
  number={1},
  pages={56-72},
  abstract={MacKay's {B}ayesian framework for backpropagation is a practical and 
    powerful means to improve the generalization ability of neural 
    networks, It is based on a Gaussian approximation to the posterior 
    weight distribution, The framework is extended, reviewed, and 
    demonstrated in a pedagogical way, The notation Is simplified using 
    the ordinary weight decay parameter, and a detailed and explicit 
    procedure for adjusting several weight decay parameters is given, 
    {B}ayesian backprop is applied in the prediction of fat content in 
    minced meat from near infrared spectra, It out performs ''early 
    stopping'' as well as quadratic regression, The evidence of a 
    committee of differently trained networks is computed, and the 
    corresponding improved generalization is verified, The error bars on 
    the predictions of the fat content are computed. There are three 
    contributors: The random noise, the uncertainty in the weights, and 
    the deviation among the committee members, The {B}ayesian framework is 
    compared to Moody's GPE. Finally, MacKay and Neal's automatic 
    relevance determination, in which the weight decay parameters depend 
    on the input number, is applied to the data with improved results.}
}

@TECHREPORT{Thodberg,
 KEY		="Thodberg",
 AUTHOR		="H. H. Thodberg",
 TITLE		="Ace of {B}ayes: application 
			of Neural Networks with pruning",
 YEAR		="1993",
 NUMBER		="1132 E",
 INSTITUTION	="Danish meat research institute"}



@TechReport{Gold94,
  author = 	 "S. Gold and C. P. Lu and A. Rangarajan and S. Pappu
		  and E. Mjolsness",
  title = 	 "New Algorithms for {2D} and {3D} Point Matching: Pose
		  Estimation and Correspondence",
  institution =  "Yale",
  year = 	 1994,
  number =	 "YALEU/DCS/RR-1035"
}
% this paper makes use of the idea of turning energies E_{ij}
% into probabilities like the marginals of the posterior of a 
% permutation matrix by repeated carpet jumping over i then j.

@BOOK{HKP,
 KEY		="Hertz \etal",
 AUTHOR		="J. Hertz and A. Krogh and R. G. Palmer",
 TITLE		="Introduction to the Theory of Neural Computation",
 PUBLISHER	="Addison-Wesley",
 YEAR		="1991"}

@INPROCEEDINGS{strauss,
 KEY            ="Strauss \etal",
 AUTHOR         ="C. E. M. Strauss and D. H.  Wolpert and D. R.  Wolf",
 TITLE          ="Alpha, Evidence, and the Entropic Prior",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, {P}aris 1992",
 EDITOR 	="A. Mohammed-Djafari",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1993"}

@INPROCEEDINGS{Puetter,
 KEY            ="P",
 AUTHOR         ="Puetter",
 TITLE          ="The pixon model for image reconstruction",
 BOOKTITLE      ="Maximum Entropy and {B}ayesian Methods, {S}anta {B}arbara 1993",
 EDITOR 	="G. Heidbreder",
 PUBLISHER	="Kluwer",
 ADDRESS	="Dordrecht",
 YEAR           ="1996"}

@Article{NC:Bromley93,
     author =       "J. Bromley and J. S. Denker",
     title =        "Improving Rejection Performance on Handwritten Digits
                    by Training with `Rubbish'",
     type =         "Note",
     journal =      "Neural Computation",
     volume =       "5",
     number =       "3",
     pages =        "367--370",
     year =         "1993"
}


@TECHREPORT{Jervis_etal93,
        AUTHOR             = {T. T. Jervis and W. J. Fitzgerald},
        ADDRESS            = {Trumpington Street, Cambridge, England},
        INSTITUTION        = {Cambridge University Engineering Department},
        MONTH              = {August},
        NUMBER             = {CUED/F-INFENG/TR 144},
        TITLE              = {Optimization Schemes for Neural Networks},
        YEAR               = {1993},
        SOURCE             = {ftp://svr-ftp.eng.cam.ac.uk/pub/reports/jervis_tr144.ps.Z}
}


@ARTICLE{Gabor,
 KEY		="Gabor",
 AUTHOR		="D. Gabor",
 TITLE		="Theory of communication",
 JOURNAL	="J. Inst. Electr. Eng.",
 YEAR		="1946",
 VOLUME		="93",
 PAGES		="429--457"}

@ARTICLE{Daug1,
 KEY		="Daugman",
 AUTHOR		="John G. Daugman",
 TITLE		="Uncertainty relation for resolution in space, spatial frequency,
and orientation optimized by two-dimensional visual cortical filters",
 JOURNAL	="J. Opt. Soc. Am. A",
 YEAR		="1985",
 VOLUME		="2 ",
 NUMBER		="7",
 PAGES		="1160--1169"}

@ARTICLE{Daug2,
 KEY		="Daugman",
 AUTHOR		="John G. Daugman",
 TITLE		="Complete Discrete 2-D Gabor Transforms by Nearal Networks for
Image Analysis and Compression",
 JOURNAL	="IEEE Trans. Acoustics, Speech and Signal Proc.",
 YEAR		="1988",
 VOLUME		="36",
 NUMBER		="7",
 PAGES		="1169--1179"}

@ARTICLE{Wavelet1,
 KEY		="Strang",
 AUTHOR		="Gilbert Strang",
 TITLE		="Wavelets and Dilation Equations: A Brief Introduction",
 JOURNAL	="SIAM Review",
 YEAR		="1989",
 VOLUME		="31",
 NUMBER		="4",
 PAGES		="614--627"}

@ARTICLE{Wavelet2,
 KEY		="Heil and Walnut",
 AUTHOR		="C. E. Heil and D. F. Walnut",
 TITLE		="Continuous and Discrete Wavelet Transforms",
 JOURNAL	="SIAM Review",
 YEAR		="1989",
 VOLUME		="31",
 NUMBER		="4",
 PAGES		="628--666"}


@ARTICLE{ahb_me,
 KEY		="ahb",
 AUTHOR		="A. H. Barnett",
 TITLE		="Statistical modelling of rough crack surfaces in metals",
 JOURNAL	="Internal Report for Non-Destructive Testing
Applications Centre, Technology Division, Nuclear Electric plc",
 YEAR		="1993"}


% David Field (J. Opt Soc Am A, 4(12) 2379-2394 (1987)) analyzed a bunch of
%  natural images and decided that <|F(k)|^2> = k^{-2} on average, i.e. 
%  m = 1 in your notation.
%
@Article{field,
  author = 	 "D. Field",
  title = 	 "n/k",
  journal =	 "J. Opt Soc Am A",
  year =	 1987,
  volume =	 4,
  number =	 12,
  pages =	 "2379-2394"
}


@INPROCEEDINGS{tresp:nips5,
 AUTHOR		="S. Ahmad and  V. Tresp",
 TITLE		="Some Solutions to the Missing Feature Problem in Vision",
 BOOKTITLE	="Advances in Neural Information Processing Systems 5",
 EDITOR		="C. L. Giles and S. J. Hanson and J. D. Cowan",
 PUBLISHER	="Morgan Kaufmann",
 ADDRESS	="San Mateo, CA",
 YEAR		="1993",
 PAGES		=""}

@InProceedings{tresp:nips6,
  author = 	 "V. Tresp and S. Ahmad and R. Neuneier",
  title = 	 "Training Neural Networks with Deficient Data",
  editor =	 "Cowan, J. D. and Tesauro, G. and Alspector, J.",
  booktitle =	 "Advances in Neural Information Processing Systems 6",
  year =	 1994,
 ADDRESS	="San Mateo, CA",
  publisher =	 "Morgan Kaufmann",
 PAGES		=""
}

@InProceedings{tresp:nips7,
  author = 	 "V. Tresp  and R. Neuneier and S. Ahmad",
  title = 	 "Efficient Methods for Dealing with Missing Data in
		  Supervised Learning",
  editor =	 "G. Tesauro and D. Touretzky and T. Leen",
  booktitle =	 "Advances in Neural Information Processing Systems 7",
  year =	 1995,
 ADDRESS	="San Mateo, CA",
  publisher =	 "Morgan Kaufmann",
 PAGES		=""
}


@TECHREPORT{breiman,
 KEY            ="Breiman",
 AUTHOR         ="L. Breiman",
 TITLE          ="Stacked regressions",
 YEAR           ="1992",
 NUMBER         ="367",
 INSTITUTION    ="Dept. of Stat., Univ. of Cal. Berkeley"}

@TECHREPORT{Radford_infinite_nets,
 KEY            ="Neal",
 AUTHOR         ="R. M. Neal",
 TITLE          ="Priors for infinite Networks",
 YEAR           ="1994",
 NUMBER         ="CRG-TR-94-1",
 INSTITUTION    ="Univ. of Toronto"}
% best ref for this is radford's thesis.
% Slice Sampling
@TECHREPORT{Radford_slice,
 KEY            ="Neal",
 AUTHOR         ="R. M. Neal",
 TITLE          ={{M}arkov chain {M}onte {C}arlo methods based on `slicing' the density
function} ,
abstract={One way to sample from a distribution is to sample uniformly
from the region under the plot of its density function. A Markov chain
that converges to this uniform distribution can be constructed by
alternating uniform sampling in the vertical direction with uniform
sampling from the horizontal `slice' defined by the current vertical
position. Variations on such `slice sampling' methods can easily be
implemented for univariate distributions, and can be used to sample
from a multivariate distribution by updating each variable in
turn. This approach is often easier to implement than Gibbs sampling,
and may be more efficient than easily-constructed versions of the
Metropolis algorithm. Slice sampling is therefore attractive in
routine Markov chain Monte Carlo applications, and for use by software
that automatically generates a Markov chain sampler from a model
specification. One can also easily devise overrelaxed versions of
slice sampling, which sometimes greatly improve sampling efficiency by
suppressing random walk behaviour. Random walks can also be avoided in
some slice sampling schemes that simultaneously update all variables.
},
 YEAR ="1997",
 NUMBER ="9722",
 INSTITUTION ="Dept. of Statistics, Univ. of Toronto",
 url={http://www.cs.toronto.edu/~radford/slice.abstract.html} 
}
% Slice Sampling
@article{Radford_slice2001,
 KEY            ="Neal",
 AUTHOR         ="R. M. Neal",
 TITLE          ={Slice Sampling},
journal={Annals of Statistics},
Volume={31},number={3},
 YEAR ="2003",
 pages={705-767},
 url={http://www.cs.toronto.edu/~radford/slice.abstract.html} 
}
@TECHREPORT{Radford_ais,
 KEY            ="Neal",
 AUTHOR         ="R. M. Neal",
 TITLE          ={Annealed Importance Sampling},
abstract={Simulated annealing -- moving from a tractable distribution to a distribution of interest via a sequence of
intermediate distributions -- has traditionally been used as an inexact method of handling isolated modes in
Markov chain samplers. Here, it is shown how one can use the Markov chain transitions for such an annealing
sequence to define an importance sampler. The Markov chain aspect allows this method to perform acceptably
even for high-dimensional problems, where finding good importance sampling distributions would otherwise be
very difficult, while the use of importance weights ensures that the estimates found converge to the correct
values as the number of annealing runs increases. This annealed importance sampling procedure resembles the
second half of the previously-studied tempered transitions, and can be seen as a generalization of a
recently-proposed variant of sequential importance sampling. It is also related to thermodynamic integration
methods for estimating ratios of normalizing constants. Annealed importance sampling is most attractive when
isolated modes are present, or when estimates of normalizing constants are required, but it may also be more
generally useful, since its independent sampling allows one to bypass some of the problems of assessing
convergence and autocorrelation in Markov chain samplers. },
 YEAR ="1998",
 NUMBER ="9805",
 INSTITUTION ="Dept. of Statistics, Univ. of Toronto",
 url={http://www.cs.toronto.edu/~radford/ais.abstract.html} 
}

@PHDTHESIS{Radford_thesis,
 AUTHOR         ="R. M. Neal",
 TITLE          ="{B}ayesian Learning for Neural Networks",
 YEAR           ="1995",
 school    ="Dept. of Computer Science, Univ. of Toronto"}

@Book{Radford_book,
  author = 	 "R. M. Neal",
  title = 	 "{B}ayesian Learning for Neural Networks",
  publisher = 	 "Springer",
  year = 	 1996,
annote={  number =	 118,  series =	 "Lecture Notes in Statistics Series",},
  address =	 "New York"
}

@Book{Radford_book_full,
  author = 	 "R. M. Neal",
  title = 	 "{B}ayesian Learning for Neural Networks",
  publisher = 	 "Springer",
  year = 	 1996,
  number =	 118,
  series =	 "Lecture Notes in Statistics Series",
  address =	 "New York"
}

@TECHREPORT{Neal_gp,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="{M}onte {C}arlo Implementation of {G}aussian Process
		  Models for {B}ayesian Regression and Classification",
 YEAR		="1997",
 NUMBER		="CRG--TR--97--2",
 INSTITUTION	="Dept. of Computer Science, University	of Toronto"}


@TECHREPORT{Neal_infinite_trees,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="Defining priors for distributions using {D}irichlet diffusion trees",
 YEAR		="2001",
 NUMBER		="0104",
 INSTITUTION	="Dept. of Statistics, University	of Toronto"}
% aka 9702
@TECHREPORT{Neal_mcdecoder,
 KEY		="Neal",
 AUTHOR		="R. M. Neal",
 TITLE		="{M}onte {C}arlo  decoding of {LDPC} codes",
note={Presented at ICTP Workshop on Statistical Physics and Capacity-Approaching Codes},
 YEAR		="2001",
url={http://www.cs.toronto.edu/~radford/slides.html},
 INSTITUTION	="Dept. of Computer Science, University	of Toronto"}
% aka 9702

@Article        {Pearlmutter,
author  =       "B. A. Pearlmutter",
title   =       "Fast Exact Multiplication by the {H}essian",
journal =       "Neural Computation",
year    =       1994,
volume  =       6,
number  =       1,
pages   =       "147--160",
annote    =       "Also available by ftp archive.cis.ohio-state.edu:
                /pub/neuroprose/pearlmutter.hessian.ps.Z"
}
@inproceedings{PearlmutterICA,
author  =       "B. A. Pearlmutter and L. C. Parra",
title   =       "A context-sensitive generalization of {ICA}",
year    =       1996,
alternatepages={1235-1239},
pages={151-157},
booktitle={International Conference on Neural Information Processing, Hong Kong},
annote={International Conference on Neural Information Processing, Hong Kong, September 24--27, 1996} 
}
%note    =       " Also available at
%		  {\tt http://www.cnl.salk.edu/\verb+~+bap/papers/iconip-96-cica.ps.gz}"

@inproceedings{ pearlmutter97maximum,
    author = "Barak A. Pearlmutter and Lucas C. Parra",
    title = "Maximum Likelihood Blind Source Separation: {A} Context-Sensitive Generalization of {ICA}",
    booktitle = "Advances in Neural Information Processing Systems",
    volume = "9",
    publisher = "{MIT} Press",
    editor = "Michael C. Mozer and Michael I. Jordan and Thomas Petsche",
    pages = "613",
    year = "1997",
    url = "citeseer.nj.nec.com/pearlmutter97maximum.html" }

@inproceedings{AmariICA,
    author = "S. Amari and A. Cichocki and H. H. Yang",
    title = "A New Learning Algorithm for Blind Signal Separation",
    booktitle = "Advances in Neural Information Processing Systems",
    volume = "8",
    publisher = "{MIT} Press",
    editor = "David S. Touretzky and Michael C. Mozer and Michael E. Hasselmo",
    pages = "757--763",
    year = "1996",
    url = "citeseer.nj.nec.com/amari96new.html" }

@Book{Knuth_vol1,
  author = 	 "D. E. Knuth",
  title = 	 "The Art of Computer Programming. Volume 1: {F}undamental
                 Algorithms",
  publisher = 	 "Addison Wesley",
  year = 	 1968,
  address =	 "Reading, MA"
}
% [Univ. Lib.] 348:8.c.95.227 SF 4

@ARTICLE{mollon92,
 KEY		="Mollon and Bowmaker",
 AUTHOR		="Mollon, J. D. and Bowmaker, J. K.",
 TITLE		="The Spatial Arrangement of Cones in the Primate Fovea",
 JOURNAL	="Nature",
 YEAR		="1992",
 VOLUME		="360",
 NUMBER		="",
 PAGES		="677-679"}

@INCOLLECTION{Lee:Adapt,
	author		= {Chin-Hui Lee and Jean-Luc Gauvain},
	title			= {Adaptive Learning in Acoustic and Language Modeling},
	booktitle	= {Speech Recognition and Coding: {N}ew Advances and Trends},
	pages			= {14-31},
	crossref		= {NATO:95},
	source		= {Bill},
	status		= {Photocopied}
}

@InProceedings{Hinton_bb,
      author =       "G. E. Hinton and van Camp, D.",
      title =        "Keeping Neural Networks Simple by Minimizing the 
			Description Length of the Weights",
      booktitle =    "Proc.\ 6th Annual Workshop on Comput.\ Learning Theory",
      publisher =    "ACM Press, New York, NY",
      year =         "1993",
      pages =        "5-13",
    }

@BOOK{Draper,
 KEY          ="Draper, Norman Richard",
 AUTHOR       ="Draper, N. R.  and H. Smith",
 TITLE        ="Applied regression analysis",
 PUBLISHER	="Wiley",
 ADDRESS      ="New York",
 YEAR		="1966"
}

@Book{GrandyI,
  author = 	 "Grandy, W. T., Jr.",
  title = 	 "Foundations of Statistical Mechanics. Volume I:
		  Equilibrium Theory",
  publisher = 	 "D. Reidel",
  year = 	 1987,
  annote =	 "now Reidel is Kluwer"
}

@Book{GrandyII,
  author = 	 "Grandy, W. T., Jr.",
  title = 	 "Foundations of Statistical Mechanics. Volume II:
		  Nonequilibrium Phenomena",
  publisher = 	 "D. Reidel",
  year = 	 1987,
  annote =	 "now Reidel is Kluwer"
}

@Article{Eddy94,
  author =       "Sean R. Eddy and Richard Durbin",
  title =        "{RNA} Sequence Analysis Using Covariance Models",
  journal =      "Nucleic Acids Research",
  year =         1994,
  volume =       22,
  pages =        "2079-2088"
}

@Article{Krogh94,
  key =       "Anders Krogh and Michael Brown and I. Saira Mian and
                  Kimmen Sjolander and David Haussler",
  author =       "A. Krogh and M. Brown and I. S. Mian and
                  K. Sjolander and D. Haussler",
  title =        "Hidden {M}arkov Models in Computational Biology:
                  Applications to Protein Modeling",
  journal =      "Journal of Molecular Biology",
  year =         1994,
  volume =       235,
  pages =        "1501-1531"
}

@InProceedings{Sakakibara94a,
  key =       "Yasubumi Sakakibara and Michael Brown and Rebecca C.
                  Underwood and I. Saira Mian and D. Haussler",
  author =       "Y. Sakakibara and M. Brown and R. C.
                  Underwood and I. S. Mian and D. Haussler",
  title =        "Stochastic Context-Free Grammars for Modeling {RNA}",
  editor =       "Lawrence Hunter",
  volume =       "V",
  pages =        "284-293",
  booktitle = "Proceedings of the Twenty-Seventh Annual Hawaii
                  International Conference on System Sciences:
                  Biotechnology Computing",
  year =         1994,
  publisher = "IEEE Computer Society Press",
  address =      "Los Alamitos, CA"
}

@Unpublished{Sakakibara94b,
  key =       "Yasubumi Sakakibara and Michael Brown and Richard
                  Hughey and I. Saira Mian and Kimmen Sj{\"{o}}lander and
                  Rebecca C. Underwood and David Haussler",
  author =       "Yasubumi Sakakibara and M. Brown and R.
                  Hughey and I. S. Mian and K. Sj{\"{o}}lander and
                  R. C. Underwood and D. Haussler",
  title =        "The Application of Stochastic Context-Free Grammars
                  to Folding, Aligning and Modeling Homologous {RNA}
                  Sequences",
  year =         1994,
  note =         "unpublished manuscript"
}



@inproceedings  ( saund-86,
key     =       "Saund" ,
author  =       "Saund, E." ,
year    =       "1986" ,
title   =       "Abstraction and representation of continuous variables in
connectionist networks" ,
booktitle =     "Proceedings of the Fifth National Conference on Artificial
Intelligence" ,
publisher=      "Morgan Kaufmann",
address =       "Los Altos, CA" ,
pages   =       "638-644" 
)

@article        (saund-89a,
key     =       "Saund",
author  =       "Saund, E.",
title   =       "Dimensionality-reduction using connectionist networks",
journal =       "IEEE Trans. on Pattern Analysis and Machine
Intelligence",
volume  =       "11(3)",
pages   =       "304-314",
year    =       "1989"
)

@inproceedings  ( saund-89b,
key     =       "Saund" ,
author  =       "Saund, E.",
title   =       "Adding Scale to the Primal Sketch",
booktitle =     cvpr,
year    =       "1989" ,
pages   =       "70-78"
)

@inproceedings{RobinsonFallside88-nips,
        author=         "A. J. Robinson and F. Fallside",
        title=          "Static and Dynamic Error Propagation Networks with
                         Application to Speech Coding",
        editor=         "D. Z. Anderson",
        booktitle=      "Neural Information Processing Systems",
        publisher=      "American Institute of Physics",
        year=           1988}

@BOOK{Everitt,
 Author=        "Everitt, B. S.",
 Title=         "An Introduction to Latent Variable Models",
 Publisher=     "Chapman and Hall",
 Address=       "London", 
 Year=		"1984"
}
% Location:       [Univ. Lib.] 202.c.98.248                 South Wing 5

@Article{Muller_variable_bandwidth,
 Title          ="Variable Bandwidth Kernel Estimators of Regression-Curves",
 Author         ="Muller, H. G.  and Stadtmuller, U.",
 Journal        ="Annals of Statistics",
 Year           =1987,
 Volume         ="15",
 Number         ="1",
 Pages          ="182-201"
}

@Article{Freeman:1994,
 Title		="The Generic Viewpoint Assumption in a Framework for Visual-Perception",
 Author         ="Freeman, W. T.",
 Journal        ="Nature",
 Year           =1994,
 Volume         ="368",
 Number         ="6471",
 Pages          ="542-545"
}
% NA- MITSUBISHI ELECT RES LABS,201 BROADWAY/CAMBRIDGE//MA/02139
% DT- ARTICLE
% AB- A VISUAL system makes assumptions in order to interpret visual data. The
%     assumption of 'generic view'1-4 states that the observer is not in a special
%     position relative to the scene. Researchers commonly use a binary decision
%     of generic or accidental view to disqualify scene interpretations that
%     assume accidental viewpoints5-10. Here we show how to use the generic view
%     assumption, and others like it, to quantify the likelihood of a view, adding
%     a new term to the probability of a given image interpretation. The resulting
%     framework better models the visual world and reduces the reliance on other
%     prior assumptions. It may lead to computer vision algorithms of greater
%     power and accuracy, or to better models of human vision. We show
%     applications to the problems of inferring shape  surface reflectance
%     properties  and motion from images.

@article{Brown-et-al92b,
author = "Brown, Peter F. and {Della Pietra}, Stephen A. and {Della Pietra}, Vincent J. and Lai, Jennifer C. and Mercer, Robert L.",
title = "An Estimate of an Upper Bound for the Entropy of {E}nglish",
year = "1992",
journal = "Computational Linguistics",
volume = "18",
number = "1",
pages = "31-40"}

@inproceedings{Gale&Church91,
author = "Gale, William and Church, Kenneth",
title = "A program for aligning sentences in bilingual corpora",
year = "1991",
booktitle = "Proceedings of 29th Annual Meeting of the ACL",
pages = "177-184"}

@Book{Seneta,
  author = 	 "E. Seneta",
  title = 	 "Non-negative Matrices",
  publisher = 	 "Wiley",
  year = 	 1973,
  address =	 "New  York"
}
%  Title:          Non-negative matrices: an introduction to theory and
%                  applications/ E. Seneta
%                  London: George Allen and Unwin, 1973
%                  x,214p; 24cm
 
@INPROCEEDINGS{Saul_Jordan:BC,
 AUTHOR         ="L. Saul and M. Jordan",
 TITLE          ="{B}oltzmann Chains and Hidden {M}arkov Models",
 BOOKTITLE      ="Advances in Neural Information Processing Systems 7",
 EDITOR         ="G. Tesauro and D. Touretzky and T. Leen",
 PUBLISHER      ="MIT Press",
 YEAR           ="1995",
 PAGES          ="435-442"}

@MastersThesis{Williams:BC,
  author = 	 "C. K. I. Williams",
  title = 	 "Using Deterministic {B}oltzmann Machines to
		  Discriminate Temporally Distorted Strings",
  school = 	 "Dept. of Computer Science, Univ. of Toronto",
  year = 	 1990
}

@incollection  {williams-hinton-91,
author  =   "Williams, C. K. I and Hinton, G. E.",
title   =   "Mean field networks that learn to discriminate temporally
		  distorted strings",
year    =   "1991",
publisher  = "Morgan Kaufmann",
address={San Mateo, CA},
editor  =   "Touretzky, D. S. and Elman, J. L. and Sejnowski, T. J.",
booktitle = "{Connectionist Models: Proceedings of the 1990 Summer School}"
}


@Article{Freedman_M100,
  author = 	 "W. L. Freedman and B. F. Madore and J. R. Mould
                  and R. Hill and others",
  title = 	 "Distance to the {V}irgo Cluster Galaxy {M100} from 
                  {H}ubble Space Telescope Observations of {C}epheids",
  journal =	 "Nature",
  year =	 1994,
  volume =	 371,
  pages =	 "757-762",
  month =	 "Oct"
}

% Distance to the Leo cluster Galaxies M96 and UGC5889 from Hubble
% Space Telescope observations of Cepheids

@Article{shlyakhter_kammen_92,
  author = 	 "A. I. Shlyakhter and D. M. Kammen",
  title = 	 "Sea-level rise or fall?",
  journal =	 "Nature",
  year =	 1992,
  volume =	 357,
  pages =	 25,
  annote =	 "7 May 1992"
}

@TechReport{west.dirichlet,
  author = 	 "M. West",
  title = 	 "Hyperparameter Estimation in {D}irichlet 
         Process Mixture Models",
  institution =  "Duke Inst. of Stats. and Decision Sciences",
  year = 	 1992,
  type =	 "Working paper",
  number =	 "92-A03"
}
@article{West1984,
  title="Outlier Models and Prior Distributions in {B}ayesian Linear-Regression",
  author="West, M.",
  journal="Journal of the Royal Statistical Society Series B-Methodological",
  year="1984",
  volume="46",
  number="3",
  pages="431-439"
}

@article{Shephard1994,
  title="Partial Non-{G}aussian State-Space",
  author="Shephard, N.",
  journal="Biometrika",
  year="1994",
  volume="81",
  number="1",
  pages="115-131",
  abstract="In this paper we suggest the use of simulation techniques to extend 
    the applicability of the usual Gaussian state space filtering and 
    smoothing techniques to a class of non-Gaussian time series models. 
    This allows a fully {B}ayesian or maximum likelihood analysis of some 
    interesting models, including outlier models, discrete Markov chain 
    components, multiplicative models and stochastic variance models. 
    Finally we discuss at some length the use of a non-Gaussian model to 
    seasonally adjust the published money supply figures."
}

@article{Carter1994,
  title="On {G}ibbs Sampling for State-Space Models",
  author="Carter, C. K. and Kohn, R.",
  journal="Biometrika",
  year="1994",
  volume="81",
  number="3",
  pages="541-553",
  abstract="We show how to use the Gibbs sampler to carry out {B}ayesian inference 
    on a linear state space model with errors that are a mixture of 
    normals and coefficients that can switch over time. Our approach 
    simultaneously generates the whole of the state vector given the 
    mixture and coefficient indicator variables and simultaneously 
    generates all the indicator variables conditional on the state 
    vectors. The states are generated efficiently using the Kalman 
    filter. We illustrate our approach by several examples and 
    empirically compare its performance to another Gibbs sampler where 
    the states are generated one at a time. The empirical results suggest
    that our approach is both practical to implement and dominates the 
    Gibbs sampler that generates the states one at a time."
}


@Article{antoniak,
  author = 	 "Antoniak, C. E.",
  title = 	 "Mixtures of {D}irichlet
 processes with applications to non\-para\-met\-ric problems",
  journal =	 "Annals of Statistics",
  year =	 1974,
  volume =	 2,
  pages =	 "1152-1174"
}



@Article{kac47,
  author = 	 "M. Kac",
  title = 	 "Random Walk and the Theory of {B}rownian Motion",
  journal =	 "Amer. Math. Monthly",
  year =	 1947,
  volume =	 54,
  pages =	 "369-391",
  annote =	 "I have not read this paper but it is cited as the original"
}

@Article{letac_takacs79,
  author = 	 "G. Letac and L. Takacs",
  title = 	 "Random Walk on the $m$-dimensional cube",
  journal =	 "J. reine angew. Math.",
  year =	 1979,
  volume =	 310,
  pages =	 "187-195"
}

@Article{takacs79,
  author = 	 "L. Takacs",
  title = 	 "On an Urn Problem of {P}aul and {T}atiana {E}hrenfest",
  journal =	 "Math. Proc. Camb. Phil. Soc.",
  year =	 1979,
  volume =	 86,
  pages =	 "127-130"
}

@Article{DiaGraMor90,
      author =       "Diaconis and Graham and Morrison",
      title =        "Asymptotic Analysis of a Random Walk on a Hypercube
                     with Many Dimensions",
      journal =      "Random Structures & Algorithms",
      volume =       "1",
      year =         "1990",
    }
@Article{ChuDiaGra92,
      author =       "Chung and Diaconis and Graham",
      title =        "Universal Cycles for Combinatorial Structures",
      journal =      "Discrete Mathematics",
      volume =       "110",
      year =         "1992",
    }
@Article{DiaconisSaloffCoste93,
      author =       "Persi Diaconis and Laurent Saloff-Coste",
      title =        "Comparison techniques for random walk on finite
                     groups",
      journal =      "Ann. Probab.",
      volume =       "21",
      pages =        "2131--2156",
      year =         "1993",
    }
@Article{DiaconisSaloffCoste94,
      author =       "P.\ Diaconis and L. Saloff-Coste",
      title =        "Moderate growth and random walk on finite groups",
      journal =      "Geom. Funct. Anal.",
      volume =       "4",
      pages =        "1--36",
      year =         "1994",
    }

@article{bin91,
        author="N. H. Bingham",
        title="Fluctuation Theory for the {E}hrenfest Urn",
        journal=AAP,
        pages="598-611",
        volume=23,
        year=1991}

@article{DGM90,
        author="P. Diaconis and R.L. Graham and J.A. Morrison",
        title="Asymptotic Analysis of a Random Walk on a Hypercube
with Many Dimensions",
        journal=RSA,
        volume=1,
        pages="51-72",
        year=1990}

@article{KLY93,
        author="S. Karlin and B. Lindqvist and Y-C Yao",
        title="Markov Chains on Hypercubes: Spectral Representations
and Several Majorization Relations",
        journal=RSA,
        volume=4,
        pages="1-36",
        year=1993}

@article{Randall93,
        author="D. Randall",
        title="Efficient Generation of Random Nonsingular Matrices",
        journal=RSA,
        volume=4, number=1,
        pages="111-118",
        year=1993}



@article{Tsfasman1991,
  title="Algebraic-Geometric Codes and Asymptotic Problems",
  author="Tsfasman, M. A.",
  journal="Discrete Applied Mathematics",
  year="1991",
  volume="33",
  number="1-3",
  pages="241-256"
}

@article{Tsfasman1982,
  title="Modular Curves, {S}himura curves, and {G}oppa codes, better
		  than the {Varshamov-Gilbert} Bound",
  author="Tsfasman, M. A. and S. G. Vladut and T. Zink",
  journal="Math. Nachr.",
  year="1982",
  volume="109",
  pages="21-28"
}



@Article{Feng_Rao1993,
  author = 	 "G.-L. Feng and T. R. N. Rao",
  title = 	 "Decoding Algebraic-Geometric Codes up to  the
		  Designed Minimum Distance",
  journal =	 "IEEE Trans. on Info. Theory",
  year =	 1993,
  volume =	 39,
  number =	 1,
  pages =	 "37-45",
  month =	 "January"
}

@article{Coffey1990,
  title="Any Code of Which We Cannot Think Is Good",
  author="Coffey, J. T. and Goodman, R. M.",
  journal="IEEE Trans. on Info. Theory",
  year="1990",
  volume="36",
  number="6",
  pages="1453-1461"
}

@article{Delsarte1982,
  title="Algebraic Constructions of {S}hannon Codes for Regular Channels",
  author="Delsarte, P. and Piret, P.",
  journal="IEEE Trans. on Info. Theory",
  year="1982",
  volume="28",
  number="4",
  pages="593-599"
}

@article{Ahlswede1982,
  title="Good Codes Can Be Produced By A Few Permutations",
  author="Ahlswede, R. and Dueck, G.",
  journal="IEEE Trans. on Info. Theory",
  year="1982",
  volume="28",
  number="3",
  pages="430-443"
}

% a theory of how to _value_ information is found in :
@Book{Russell_Wefald,
  author = 	 "S. Russell and E. Wefald",
  title = 	 "Do the Right Thing: Studies in Limited Rationality",
  publisher = 	 "MIT Press",
  year = 	 1991
}

@article{Debuda1989,
 Author="Debuda, R.",
 Title="Some Optimal Codes have Structure",
 Journal="IEEE Journal on Selected Areas in Communications",
 Year=1989,
 volume=7,
 number=6,
 pages="893-899"
}

% hestenes: `new foundations for classical mechanics' published Kluwer

% Thanks for the message -- what an interesting application.  My
% immediate reaction is to shudder at not doing it all exactly (I
% suppose the networks are too complex to triangulate?), but I
% shouldn't be too purist.
% 
% The early work on MUNIN -- the very large application that drove
% the HUGIN work, used this approach of ignoring the cycles by 
% removing the `weak links' and hoping
% for the best, until they adopted the exact techniques.  And there
% is later work from the Danish group in which they study in more
% detail the approximation incurred by removing edges.  Some references are:
% 
@inproceedings{munin,
 author = " S. Andreassen and  M.  Woldbye and  B. Falck and  S. Andersen",
 title = " {MUNIN} --- a causal probabilistic network for the interpretation of electromyographic
 findings",
 booktitle =  "Proc. of the 10th {N}ational {C}onf. on {AI}, {AAAI}: {M}enlo {P}ark CA.",
 year = "1987",
 pages = "121-123",
}
% By the way the MUNIN article is actually in IJCAI 87 and not in AAAI, and
% it is on pages 366-372.


@Techreport{kjaerulff:93,
   author =  "Kj{\ae}rulff, U.",
  title =  "Approximation of {B}ayesian
   networks by edge removals",
  institution = "University of Aalborg, Denmark",
  year =  "1993",
  type =  "Technical Report",
  number = "R~93-2021",
 }

@Techreport{kjaerulff:94,
   author =  "Kj{\ae}rulff, U.",
  title =  "Reduction of complexity in {B}ayesian networks
through removal of weak dependencies",
  institution = "University of Aalborg, Denmark",
  year =  "1994",
  type =  "Technical Report",
  number = "R~93-2009",
 }
 
@article{ProSite, author={Amos Bairoch}, title="********************",
                  year=1993, journal=NAR, volume=21, pages={3097-3103} }
 
@article{Staden1989, journal=CABIOS, author={Rodger Staden}, volume=5,
                  title={Methods for calculating the probabilities of
                  finding patterns in sequences}, year=1989, number=2,
                  pages={89-96} }
 
@article{PevznerBorodovskyMironov1989, journal=JBSD, volume=6,
                  number=5, year=1989, pages={1013-1026},
                  author="Pavel A. Pevzner and Mark Yu. Borodovsky and
                  Anrey A. Mironov"}
 
@article{blocks, author="S. Henikoff and J.G. Henikoff", year=1991,
                  journal=NAR, volume=19, pages={6565-6572},
                  title={Automatic assembly of protein blocks for
                  database searching} }

@book{durbin1998,
title={Biological Sequence Analysis.
            Probabilistic Models of Proteins and Nucleic Acids},
author={Richard Durbin and Sean R. Eddy and Anders Krogh and Graeme Mitchison},
 publisher={Cambridge University Press},
year={1998}}
@book{Welsh1988,
title={Codes and Cryptography},
author={Dominic Welsh},
year={1988},
publisher={Clarendon press}}

@article{Matchprobs, author="Roger F. Sewell and Richard Durbin",
                  year=1995, title={Method for Calculation of
                  Probability of Matching a Bounded Regular Expression
                  in a Random Data String}, journal=JCB, volume=2,
                  number=1, pages={25-31}}
 
@unpublished{Sewell_Fragments, author="Roger F. Sewell", year=1995, title={A
full probabilistic model for finding fragment matches to {H}idden {M}arkov
{M}odels in a data string}}
 
 
@unpublished{Sewell_Methods, author="Roger F. Sewell", year=1995,
		  title={Methods for applying  {H}idden {M}arkov
{M}odels to sequence data: separation of score due to length and to
		  content; negative discriminative training; full
		  probability simulated annealing; site
		  discrimination; and multiple discriminative models
		  used successively}}
 
% see also bloj.bib
%
%  TURBO CODES, Gallager codes, etc.
%
@Article{berrou-glavieux-96,
   key =          "Berrou",
   author =       "C. Berrou and A. Glavieux",
   title =        "Near Optimum Error Correcting Coding and Decoding:
                 {T}urbo-Codes",
   journal =      "IEEE Trans. on Communications",
   volume =       "44",
   pages =        "1261--1271",
   month =        "October",
   year =         "1996"
 }

@inproceedings{Berrou93:Turbo,
 author = "C. Berrou and A. Glavieux and P. Thitimajshima",
  title = 	 "Near {S}hannon Limit Error-correcting Coding and
		  Decoding: {T}urbo-Codes",
  year = 	 1993,
  booktitle =	 "Proc. 1993 IEEE International Conference on
		  Communications, Geneva, Switzerland",
  pages =	 "1064-1070"
}
%   pages =	 "23-27"

% J. K. Wolf and P.H. Siegel, ``On two-dimensional arrays and crossword puzzles,'' Proc. 36th Allerton Conference on Communication, Control and Computing, Monticello, Illinois, pp. 366-371, September 1998. 
@inproceedings{wolf1998,
  title="On two-dimensional arrays and crossword puzzles",
  author="J. K. Wolf and P.H. Siegel",
 BOOKTITLE      ="Proceedings of the 36th Allerton Conference on Communication, Control, and Computing, Sept.\ 1998",
 EDITOR 	="",
 PUBLISHER	="Allerton House",
 ADDRESS	="Monticello, Illinois",
 YEAR           ="1998",
 PAGES		="366-371",
}
@inproceedings{Divsalar1998,
  title="Coding Theorems for `Turbo-Like' Codes",
  author="Divsalar, D. and Jin, H. and  McEliece, R. J.",
 BOOKTITLE      ="Proceedings of the 36th Allerton Conference on Communication, Control, and Computing, Sept.\ 1998",
 EDITOR 	="",
 PUBLISHER	="Allerton House",
 ADDRESS	="Monticello, Illinois",
 YEAR           ="1998",
 PAGES		="201-210",
}
@article{Divsalar1996,
  title="Effective Free Distance of Turbo Codes",
  author="Divsalar, D. and McEliece, R. J.",
  journal="Electronics Letters",
  year="1996",
  volume="32",
  number="5",
  pages="445-446",
  abstract="The authors define and study the effective free distance of a turbo 
    code. If a turbo code is constructed from a number of component 
    codes, they argue that the effective free distance can be maximised 
    by choosing the component codes to be IIR convolutional code 
    fragments with maximal input weight-2 free distance. They then 
    present some theoretical bounds for, and some numerical tables of; 
    IIR code fragments with maximal input weight-2 free distance."
}

@TechReport{Divsalar95,
  author = 	 "D. Divsilar and F. Pollara",
  title = 	 "On the Design of {T}urbo Codes",
  institution =  "Jet Propulsion Laboratory",
  year = 	 1995,
  number =	 "TDA 42-123",
  address =	 "Pasadena",
  month =	 "November"
}

@TechReport{Benedetto96,
  author = 	 "S. Benedetto and G. Montorsi and D. Divsilar and F. Pollara",
  title = 	 "Serial Concatenation of Interleaved Codes{:}
		  Performance Analysis, Design, and Iterative Decoding",
  institution =  "Jet Propulsion Laboratory",
  year = 	 1996,
  number =	 "TDA 42-126",
  address =	 "Pasadena",
  month =	 "August"
}

@InProceedings{divsalar-pollara-95,
  key =          "Divsalar",
  author =       "D. Divsalar and F. Pollara",
  title =        "Turbo-codes for {PCS} Applications",
  booktitle =    "Proceedings of ICC'95",
  year =         "1995",
  pages =        "54--59",
  place =        "Seattle WA."
}

@phdthesis{wiberg:phd,
 author = 	 "N. Wiberg",
  title = 	 "Codes and Decoding on General Graphs",
  school = 	 "Dept. of Electrical Engineering, Link{\"o}ping, Sweden",
  year = 	 1996,
  note = 	 "Link{\"o}ping Studies in Science and Technology No.\ 440"
}
@Article{wiberg95,
  key =          "Wiberg",
  author =       "N. Wiberg and H.-A. Loeliger and R. K{\"o}tter",
  title = 	 "Codes and Iterative Decoding on General Graphs",
  journal =      "European Trans. on Telecommunications",
  volume =       "6",
  pages =        "513--525",
  year =         "1995"
}

% national defence research establishment, linkoping sweden
@Inproceedings{koetter_nilsson94,
  author = 	 "R. K{\"o}tter and J. Nilsson",
  title = 	 "Interleaving Strategies for Product Codes",
  booktitle =	 "Proc. EIDMA, Veldhoven, Netherlands, Dec.\ 19--21, 1994",
  year =	 1994,
  pages =	 37
}

@Inproceedings{nilsson_koetter94,
  author = 	 "J. Nilsson and R. K{\"o}tter",
  title = 	 "Iterative Decoding of  Product Code Constructions",
  booktitle =	 "Proc.\ ISITA94, Sydney, Nov.\ 1994",
  year =	 1994,
  pages =	 {1059--1064}
}

@unpublished{jimenez-zigangirov97,
 author={Jimenez, A. and Zigangirov, K. Sh.},
 title={Time-varying Periodical Convolutional Codes with Low-Density
		  Parity-Check Matrix},
 note={preprint},
year={1997}
}



@Article{Sorokine98I,
  author = 	 "V. Sorokine and Kschischang, F. R. and S. Pasupathy",
  title = 	 "Gallager Codes for {CDMA} Applications I: Generalizations, Constructions and Performance Bounds",
  journal =	 "IEEE Trans. Communications",
  year =	 1998,
  volume =	 {},
  number =	 {},
  pages =	 "",
note={Submitted},
  annote =	 "www.comm.utoronto.ca/frank/"
}
@Article{Sorokine98II,
  author = 	 "V. Sorokine and Kschischang, F. R. and S. Pasupathy",
  title = 	 "Gallager Codes for {CDMA} Applications {II}: Implementations, Complexity and System Capacity",
  journal =	 "IEEE Trans. Communications",
  year =	 1998,
  volume =	 {},
  number =	 {},
  pages =	 "",
note={submitted},
  annote =	 "www.comm.utoronto.ca/frank/"
}

@article{Kschischang2001,
  author = 	 "Kschischang, F. R. and Frey, B. J. and Loeliger, H.-A.",
 TITLE          ="Factor Graphs and the Sum-Product Algorithm",
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={498-519}
} 

@Article{Kschischang_,
  author = 	 "Kschischang, F. R. and V. Sorokine",
  title = 	 "On the Trellis Structure of Block Codes",
  journal =      {IEEE Trans. on Info. Theory},
  year =	 1995,
  volume =	 41,
  number =	 6,
  pages =	 "1924-1937",
  month =	 "Nov",
  annote =	 "www.comm.utoronto.ca/frank/"
}

% papers on construction of sparse graphs
% Wong Cages a survey
% Benson

@Article{Jung-Nasshan94:turbo,
  author = 	 "P. Jung and M. Nasshan",
  title = 	 "Performance evaluations of turbo codes for short
		  frame transmission systems",
  journal =	 "Electronics Letters",
  year =	 1994,
  volume =	 30,
  number =	 2,
  pages =	 "111-113"
}

@Article{Bendetto-Montorsi95:turbo,
  author = 	 "S. Bendetto and G. Montorsi",
  title = 	 "Performance evaluations of turbo codes",
  journal =	 "Electronics Letters",
  year =	 1995,
  volume =	 31,
  number =	 3,
  pages =	 "163-165"
}

@Article{Bendetto-Montorsi95:turboRCC,
  author = 	 "S. Bendetto and G. Montorsi",
  title = 	 "Role of recursive convolutional codes in turbo codes",
  journal =	 "Electronics Letters",
  year =	 1995,
  volume =	 31,
  number =	 11,
  pages =	 "858-859"
}

@Article{Bendetto-Montorsi95:turboPCBC,
  author = 	 "S. Bendetto and G. Montorsi",
  title = 	 "Average performance of parallel concatenated block codes",
  journal =	 "Electronics Letters",
  year =	 1995,
  volume =	 31,
  number =	 3,
  pages =	 "156-159"
}

@article{Zyablov,
 author={V. V. Zyablov and M. S. Pinsker},
 title={Estimation of the Error-Correction Complexity for {G}allager
		  Low-Density Codes},
 journal={Problemy Peredachi Informatsii},
volume={11},
number={1},
pages={23-36},
year={1975}
}

@Article{TAP1977,
  author = 	 "D. J. Thouless and P. W. Anderson and R. G. Palmer",
  title = 	 "Solutions of `Solvable Models of a Spin Glass'",
  journal =	 "Philosophical Magazine",
  year =	 1977,
  volume =	 35,
 number = 3,
  pages =	 "593-601"}
%BTW, at your talk on codes at the Cavendish lab. last month I mentioned
%the TAP equations.  The reference is
%  D J Thouless, P W Anderson, and R G Palmer, 1977, Phil Mag v 35, p 3271
%The self-consistent equation they derive for the average magnetization
%at i is
%
%m_i = tanh[\beta (\sum_j J_{ij} m_j -- \beta \sum_j J_{ij}^2 (1-m_j^2)m_i)]
%
%which I found in the book "Spin glasses" by Fischer and Hertz
%(cambr univ. press 1994). Spin Glasses K H Fischer and J A Hertz


@Article{Bein89,
  author = 	 "F. Bein",
  title = 	 "Construction of Telephone Networks",
  journal =	 "Notices Amer. Math. Soc.",
  year =	 1989,
  volume =	 36,
  month =	 "Jan"
}

@Article{Lubotsky88,
  author = 	 "A. Lubotsky",
  title = 	 "Ramanujan Graphs",
  journal =	 "Combinatorica",
  year =	 1988,
  volume =	 8
}

@Book{Bishop95,
  author = 	 "C. M. Bishop",
  title = 	 "Neural Networks for Pattern Recognition",
  publisher = 	 "Oxford University Press",
  year = 	 1995
}
% 5000 sold first run

@InCollection{Battail93_cando,
  title = 	 "We Can Think of Good Codes, and Even Decode Them",
  year = 	 1993,
  author = 	 "G. Battail",
  booktitle =	 "Eurocode '92. Udine, Italy, 26-30 October",
  number =	 339,
  series =	 "CISM Courses and Lectures",
  publisher =	 "Springer",
  editor =	 "P. Camion and P. Charpin and S. Harari",
  pages =	 "353-368",
  address =	 "Wien"
}

@InCollection{Battail95,
  title = 	 "Can We Implement Random Coding?",
  year = 	 1995,
  author = 	 "G. Battail",
  booktitle =	 "Codes and Cyphers",
  publisher =	 "Formara",
  editor =	 "P. G. Farrell",
  pages =	 "1-15",
  address =	 "Southend"
}
@article{promhouse78,
 title={The Minimum Distance of
All Binary Cyclic Codes of Odd Lengths from 69 to 99},
 author={G. Promhouse and S. E. Tavares},
  journal =      {IEEE Trans. on Info. Theory},
 volume={24}, number={4}, year={1978}, 
 pages={438-442},
 annote={Gary Promhouse and Stafford E. Tavares, "The Minimum Distance of
All Binary Cyclic Codes of Odd Lengths from 69 to 99",  IT Trans.
Inform. Theory, Vol. IT-24, No. 4, July 1978, pp. 438-442.}
}

@article{Kou2001,
author={Y. Kou and S. Lin and M. P. C. Fossorier},
title={Low Density Parity Check Codes Based on Finite Geometries: A Rediscovery and New Results},
journal={IEEE Trans. on Info. Theory},
vol={47}, pages={2711-2736},
month={Nov.},
year=2001}

%Y. Kou, S. Lin, and M. P.C. Fossorier, ?Low Density Parity Check Codes Based on Finite Geometries: A Rediscovery and New Results?, IEEE Trans. on Info. Theory, vol. IT-47, pp. 2711-2736, Nov., 2001.

%2.      R. Lucas, M. P.C. Fossorier, Y. Kou and S. Lin, ?Iterative Decoding of One-Step Majority Logic Decodable Codes Based on Belief Propagation?. IEEE Trans. on Communication, Vol. 48, pp. 931-938, June 2000.

@article{Lucas99,
author={R. Lucas and M. Fossorier and Y. Kou and S. Lin},
title={Iterative Decoding of One-Step Majority Logic Decodable Codes
 based on Belief Propagation},
year={2000},
journal={IEEE Trans. on Communications}, volume={48}, pages={931-937}, month={June},
annote={Submitted 1999}
}



% http://www-ee.eng.hawaii.edu/~marc/bp_rel.html
@article{fossorier2001,
title={Iterative Reliability-Based Decoding of Low-Density Parity Check
Codes},
journal={IEEE Journal on Selected Areas in Communications},
volume={JSAC-19},   
pages={908-917},
month={May},
year={2001},
author={M. Fossorier},
annote={M. Fossorier, "Iterative Reliability-Based Decoding of Low-Density Parity Check Codes," IEEE Journal on Selected Areas in Communications, vol. JSAC- 19, pp. 908-917, May 2001.}
}

@article{Tanner1981,
  title="A Recursive Approach to Low Complexity Codes",
  author="Tanner, R. M.",
  journal="IEEE Trans. on Info. Theory",
  year="1981",
  volume="27",
  number="5",
  pages="533-547"
}
@article{Karplus1991,
 title={A Semi-systolic Decoder for the {PDSC--73} Error-Correcting Code},
 author={K. Karplus and H. Krit},
 journal={Discrete Applied Mathematics},
 year={1991},
 volume={33},
 pages={109-128},
 annote={Tanner chip}
}

@article{Margulis1982,
  title="Explicit Constructions of Graphs Without Short Cycles and Low-Density
    Codes",
  author="Margulis, G. A.",
  journal="Combinatorica",
  year="1982",
  volume="2",
  number="1",
  pages="71-78"
}

@article{Gacs1986,
  title="Reliable Computation with Cellular Automata",
  author="Gacs, P.",
  journal="Journal of Computer and System Sciences",
  year="1986",
  volume="32",
  number="1",
  pages="15-78"
}

@article{Thommesen1987,
  title="Error-Correcting Capabilities of Concatenated Codes with {MDS} Outer 
    Codes on Memoryless Channels with Maximum-Likelihood Decoding",
  author="Thommesen, C.",
  journal="IEEE Trans. on Info. Theory",
  year="1987",
  volume="33",
  number="5",
  pages="632-640"
}

@article{Gallager74,
author={R G Gallager},
title={Capacity and Coding for Degraded Broadcast Channels},
journal={Problemy Peredaci Informaccii},
vlume={10},
number={3},
pages={3-14},
year={1974}
}


@article{Gallager1988,
  title="Finding Parity in a Simple Broadcast Network",
  author="Gallager, R. G.",
  journal="IEEE Trans. on Info. Theory",
  year="1988",
  volume="34",
  number="2",
  pages="176-180"
}


@article{Pippenger1991a,
  title="On a Lower Bound for the Redundancy of Reliable Networks with Noisy 
    Gates",
  author="Pippenger, N. and Stamoulis, G. D. and Tsitsiklis, J. N.",
  journal="IEEE Trans. on Info. Theory",
  year="1991",
  volume="37",
  number="3",
  pages="639-643",
  abstract="A proof is provided that a logarithmic redundancy factor is necessary
    for the reliable computation of the parity function by means of a 
    network with noisy gates. This is the same as the main result of 
    Dobrushin and Ortyukov except that the analysis therein seems to be 
    not entirely correct."
}

@article{Voss1991,
  title="Asymptotically Good Families of Geometric {G}oppa Codes and the 
    {G}ilbert-{V}arshamov Bound",
  author="Voss, C.",
  journal="LNCS",
  year="1991",
  volume="514",
  pages="150-157",
  abstract="This note presents a generalization of the fact that most of the 
    classical Goppa codes lie arbitrarily close to the Gilbert-Varshamov 
    bound (cf.[2, p. 229])."
}

@article{Slinko1991,
  title="Design of Experiments to Detect Nonnegligible Variables in a Linear
    Model",
  author="Slinko, A. M.",
  journal="Cybernetics",
  year="1991",
  volume="27",
  number="3",
  pages="433-442",
  abstract="The design of sifting experiments is considered. The properties of 
    'superoptimal' designs discovered by Meshalkin [3, 4] are 
    investigated."
}

@article{Radosavljevic1992,
  title="Sequential-Decoding of Low-Density Parity-Check Codes by Adaptive 
    Reordering of Parity Checks",
  author="Radosavljevic, B. and Arikan, E. and Hajek, B.",
  journal="IEEE Trans. on Info. Theory",
  year="1992",
  volume="38",
  number="6",
  pages="1833-1839",
  abstract="Decoding algorithms are investigated in which unpruned codeword trees
    are generated from an ordered list of parity checks. The order is 
    computed from the received message, and low-density parity-check 
    codes are used to help control the growth of the tree. Simulation 
    results are given for the binary erasure channel. They suggest that 
    for small erasure probability, the method is computationally feasible
    at rates above the computational cutoff rate."
}

@article{Mihaljevic1991,
  title="A Comparison of Cryptanalytic Principles Based on Iterative Error-
    Correction",
 AUTHOR		="M. J. Mihaljevi\'c and J. D. Goli\'c",
  key="Mihaljevic, M. J. and Golic, J. D.",
  journal="Lecture Notes in Computer Science Series",
  year="1991",
  volume="547",
  pages="527-531",
  abstract="A cryptanalytic problem of a linear feedback shift register initial 
    state reconstruction using a noisy output sequence is considered. The
    main underlying principles of three recently proposed cryptanalytic 
    procedures based on the iterative error-correction are pointed out 
    and compared."
}

@article{Chepyzhov1991,
  title="On a Fast Correlation Attack on Certain Stream Ciphers",
  author="Chepyzhov, V. and Smeets, B.",
  journal="Lecture Notes in Computer Science Series",
  year="1991",
  volume="547",
  pages="176-185",
  abstract="In this paper we present a new algorithm for the recovery of the 
    initial state of a linear feedback shift register when a noisy output
    sequence is given. Our work is focussed on the investigation of the 
    asymptotical behaviour of the recovery process rather than on the 
    construction of an optimal recovery procedure. Our results show the 
    importance of low-weight checks and show also that the complexity of 
    the recovery problem grows less than exponentially with the length of
    the shift register, even if the number of taps grows linearly with 
    the register length. Our procedure works for shift register with 
    arbitrary feedback polynomial."
}

@article{Zemor1995,
  title="The Threshold Probability of a Code",
  author="Zemor, G. and Cohen, G. D.",
  journal="IEEE Trans. on Info. Theory",
  year="1995",
  volume="41",
  number="2",
  pages="469-477",
  abstract="We define and estimate the threshold probability theta of a linear 
    code, using a theorem of Margulis originally conceived for the study 
    of the probability of disconnecting a graph. We then apply this 
    concept to the study of the erasure and Z-channels, for which we 
    propose linear coding schemes that admit simple decoding. We show 
    that theta is particularly relevant to the erasure channel since 
    linear codes achieve a vanishing error probability as long as p less 
    than or equal to theta, where p is the probability of erasure. In 
    effect, theta can be thought of as a capacity notion designed for 
    codes rather than for channels. Binomial codes have highest possible 
    theta (and achieve capacity). As for the Z-channel, a subcapacity is 
    derived with respect to the linear coding scheme. For a transition 
    probability in the range ]log (3/2); 1[, we show how to achieve this 
    subcapacity. As a by-product we obtain improved constructions and 
    existential results for intersecting codes (linear Sperner families) 
    which are used in our coding schemes."
}

@article{Caves1990,
  title="Quantitative Limits on the Ability of a Maxwell Demon to Extract Work
    From Heat",
  author="Caves, C. M.",
  journal="Physical Review Letters",
  year="1990",
  volume="64",
  number="18",
  pages="2111-2114"
}
% does not cite {G}allager codes in fact

@article{Pippenger1991b,
  title="The Expected Capacity of Concentrators",
  author="Pippenger, N.",
  journal="SIAM Journal on Discrete Mathematics",
  year="1991",
  volume="4",
  number="1",
  pages="121-129",
  abstract="The expected capacity of a class of sparse concentrators called 
    modular concentrators is determined. In these concentrators, each 
    input is connected to exactly two outputs, each output is connected 
    to exactly three inputs, and the girth (the length of the shortest 
    cycle in the connexion graph) is large. Two definitions of expected 
    capacity are considered. For the first (which is due to Masson and 
    Morris), it is assumed that a batch of customers arrive at a random 
    set of imputs and that a maximum matching of these customers to 
    servers at the outputs is found. The number of unsatisfied requests 
    is negligible if customers arrive at fewer than one-half of the 
    inputs, and it grows quite gracefully even beyond this threshold. The
    situation in which customers arrive sequentially is considered, and 
    the decision as to how to serve each is made randomly, without 
    knowledge of future arrivals. In this case, the number of unsatisfied
    requests is larger but still quite modest."
}

@article{Zivkovic1991,
  title="On Two Probabilistic Decoding Algorithms for Binary Linear Codes",
  author="Zivkovic, M.",
  journal="IEEE Trans. on Info. Theory",
  year="1991",
  volume="37",
  number="6",
  pages="1707-1716",
  abstract="A generalization of the Sullivan inequality on the ratio of the 
    probability of a linear code to that of any of its cosets is proved. 
    Starting from this inequality, a sufficient condition for successful 
    decoding of linear codes by a probabilistic method is derived. A 
    probabilistic decoding algorithm for 'low-density parity-check codes'
    is also analyzed. The results obtained allow one to estimate 
    experimentally the probability of successful decoding using these 
    probabilistic algorithms."
}

@Book{Golomb1994,
  author = 	 "Golomb, S. W. and Peile, R. E. and Scholtz, R. A.",
  title = 	 "Basic Concepts in Information Theory and Coding: {T}he
		  Adventures of Secret Agent {00111}",
  publisher = 	 "Plenum Press",
  year = 	 1994,
  address =	 "New York",
  annote =	 "On p.369 'there are many...codes and the optimal
		  code for a given set of channel conditions may not
		  resemble the optimal code for another'. On p.309,
		  this book is well aware that decoding beyond the
		  minimum distance is possible"
}

@Book{Duff,
  author = 	 "Duff, I.S. and Erisman, A. M. and Reid, J. K.",
  title = 	 "Direct Methods for Sparse Matrices",
  publisher = 	 "Clarendon",
  year = 	 1986,
  address =	 "Oxford"
}



@article{Comon1991,
  title="Blind Separation of Sources. 2.~{P}roblems Statement",
  author="Comon, P. and Jutten, C. and Herault, J.",
  journal="Signal Processing",
  year="1991",
  volume="24",
  number="1",
  pages="11-20",
  abstract="Though it arouses more and more curiosity, the HJ iterative algorithm
    has never been derived in mathematical terms to date. We attempt in 
    this paper to describe it from a statistical point of view. For 
    instance the updating term of the synaptic efficacies matrix cannot 
    be the gradient of a single C2 functional contrary to what is 
    sometimes understood. In fact, we show that the HJ algorithm is 
    actually searching common zeros of n functionals by pipelined 
    stochastic iterations. Based on simulation results, advantages and 
    limitations as well as possible improvements are pointed out after a 
    short theoretical analysis."
}

@article{Jutten1991,
  title="Blind Separation of Sources. 1. {A}n Adaptive Algorithm Based on 
    Neuromimetic Architecture",
  author="Jutten, C. and Herault, J.",
  journal="Signal Processing",
  year="1991",
  volume="24",
  number="1",
  pages="1-10",
  abstract="The separation of independent sources from an array of sensors is a 
    classical but difficult problem in signal processing. Based on some 
    biological observations, an adaptive algorithm is proposed to 
    separate simultaneously all the unknown independent sources. The 
    adaptive rule, which constitutes an independence test using non-
    linear functions, is the main original point of this blind 
    identification procedure. Moreover, a new concept, that of 
    INdependent Components Analysis (INCA), more powerful than the 
    classical Principal Components Analysis (in decision tasks) emerges 
    from this work."
}

@article{Bell_Sejnowski,
  title="An Information Maximization Approach to Blind Separation and Blind 
    Deconvolution",
  author="Bell, A. J. and Sejnowski, T. J.",
  journal="Neural Computation",
  year="1995",
  volume="7",
  number="6",
  pages="1129-1159",
  abstract="We derive a new self-organizing learning algorithm that maximizes the
    information transferred in a network of nonlinear units. The 
    algorithm does not assume any knowledge of the input distributions, 
    and is defined here for the zero-noise limit. Under these conditions,
    information maximization has extra properties not found in the linear
    case (Linsker 1989). The nonlinearities in the transfer function are 
    able to pick up higher-order moments of the input distributions and 
    perform something akin to true redundancy reduction between units in 
    the output representation. This enables the network to separate 
    statistically independent components in the inputs: a higher-order 
    generalization of principal components analysis. We apply the network
    to the source separation (or cocktail party) problem, successfully 
    separating unknown mixtures of up to 10 speakers. We also show that a
    variant on the network architecture is able to perform blind 
    deconvolution (cancellation of unknown echoes and reverberation in a 
    speech signal). Finally, we derive dependencies of information 
    transfer on time delays. We suggest that information maximization 
    provides a unifying framework for problems in `blind' signal 
    processing."
}

% Helmholtz95

@article{Dayan1995,
  title="The {H}elmholtz Machine",
  author="Dayan, P. and Hinton, G. E. and Neal, R. M. and Zemel, R. S.",
  journal="Neural Computation",
  year="1995",
  volume="7",
  number="5",
  pages="889-904",
  abstract="Discovering the structure inherent in a set of patterns is a 
    fundamental aim of statistical inference or learning. One fruitful 
    approach is to build a parameterized stochastic generative model, 
    independent draws from which are likely to produce the patterns. For 
    all but the simplest generative models, each pattern can be generated
    in exponentially many ways. It is thus intractable to adjust the 
    parameters to maximize the probability of the observed patterns. We 
    describe a way of finessing this combinatorial explosion by 
    maximizing an easily computed lower bound on the probability of the 
    observations. Our method can be viewed as a form of hierarchical 
    self-supervised learning that may relate to the function of bottom-up
    and top-down cortical processing pathways."
}
@inproceedings{NealHarvey2000,
 author = {Harvey, M. and Neal, R. M.},
title={Inference for Belief Networks using Coupling From the Past},
annote={Harvey, M. and Neal, R. M. (2000) ``Inference for Belief Networks
       Using Coupling From the Past'', in C. Boutilier and M. Goldszmidt
       (editors), Uncertainty in Artificial Intelligence: Proceedings of the
       Sixteenth Conference (2000), pp. 256-263.},
editors={C. Boutilier and M. Goldszmidt},
booktitle={Uncertainty in Artificial Intelligence: Proceedings of the
       Sixteenth Conference},
pages={256-263},
year={2000}
}

@article{Hinton1995,
  title="The Wake-Sleep Algorithm for Unsupervised Neural Networks",
  author="Hinton, G. E. and Dayan, P. and Frey, B. J. and Neal, R. M.",
  journal="Science",
  year="1995",
  volume="268",
  number="5214",
  pages="1158-1161",
  abstract="An unsupervised learning algorithm for a multilayer network of 
    stochastic neurons is described. Bottom-up `recognition'
    connections convert the input into representations in successive 
    hidden layers, and top-down `generative' connections reconstruct 
    the representation in one layer from the representation in the layer 
    above. In the `wake' phase, neurons are driven by recognition 
    connections, and generative connections are adapted to increase the 
    probability that they would reconstruct the correct activity vector 
    in the layer below. In the `sleep' phase, neurons are driven by 
    generative connections, and recognition connections are adapted to 
    increase the probability that they would produce the correct activity
    vector in the layer above."
}

@article{Montgomery1993,
 title=  "Navier-Stokes relaxation to sinh-Poisson states at finite
		  Reynolds numbers",
 author= "D. Montgomery and X. Shan and W. H. Matthaeus",
 journal= "Phys. Fluids A",
 vol= "5",
 number = "9",
 year = "1993",
 abstract =  "A math. framework is proposed in which it seems
		  possible to justify the computationally-observed
		  relaxation of a two-dimensional N-S fluid to a ...
		  maximum entropy state..... "
}

@INPROCEEDINGS{Ripley94,
 KEY		="Ripley",
 AUTHOR		="B. D. Ripley",
 TITLE		="Flexible Non-linear Approaches to Classification",
 BOOKTITLE      ="From Statistics to Neural Networks. Theory and
		  Pattern Recognition Applications",
  editor =	 "V. Cherkassky and J. H. Friedman and H. Wechsler",
  series =	 "ASI Proceedings (F)",
 YEAR		=1994,
  publisher =	 "Springer",
}

%Ripley95
@Book{Ripley96,
  author = 	 "B. D. Ripley",
  title = 	 "Pattern Recognition and Neural Networks",
  publisher = 	 "Cambridge University Press",
  year = 	 1996,
  annote =	 "ISBN 0-521-46086-7"
}
% obsolete:
@Book{Ripley95,
  author = 	 "B. D. Ripley",
  title = 	 "Pattern Recognition and Neural Networks",
  publisher = 	 "Cambridge University Press",
  year = 	 1996,
  annote =	 "ISBN 0-521-46086-7"
}

% critical phenomena, Ising models
@book{binney92,
 title="The theory of critical phenomena: an introduction to the
                 renormalization group",
 publisher="Oxford", 
 year=1992,
 author="Binney, J.J. and Dowrick, N.J. and Fisher, A.J.",
 annote ="[Rayleigh Lib.] 31 B 28"}

@phdthesis      ( steeg-phd,
key     =       "Steeg" ,
author  =       "Steeg, E.W." ,
title   =       "Automated Motif Discovery in Protein Structure Prediction",
school  =       "Department of Computer Science, University of Toronto",
year    =       "1997"
)


@book{yeomans92,
 author="Yeomans, J.M.",
 title = "Statistical mechanics of phase transitions",
 publisher="Clarendon Press",
address="Oxford",
 year= 1992,
 annote="[Rayleigh Lib.] 31 Y 2"}
% this is a very nice book... chapter 5 describes the transfer matrix

@book{Cardy96,
 author={Cardy, J. L.},
 publisher="Cambridge University Press",
address="Cambridge",
 Year= 1996,
 Title={Scaling and renormalization in statistical physics},
 annote="[Rayleigh Lib.] 31 C 12"}

@article{Propp1996,
  title={Exact Sampling with Coupled {M}arkov Chains and Applications to 
    Statistical Mechanics},
  author={Propp, J. G. and Wilson, D. B.},
  journal={Random Structures and Algorithms},
  year={1996},
  volume={9},
  number={1-2},
  pages={223-252}
}

@InCollection{Temperley,
  author = 	 "Temperley",
  title = 	 "Two-dimensional {I}sing Models",
  booktitle =	 "Phase Transitions and Critical Phenomena",
  publisher =	 "Academic Press",
  year =	 1972,
  editor =	 "C. Domb and M. S. Green",
  volume =	 "1. Exact Results",
  chapter =	 6,
  pages =	 "227-267",
  address =	 "London",
  annote =	 "Gives Historical review of Ising model"
}
% Plane triangular lattice, anit-ferromagnetic -- frustruations -> the
%		  transition temperature is decreased to zero.
% the entropy per site is finite at absolute zero.

@InCollection{Binder,
  author = 	 "Binder",
  title = 	 "{M}onte {C}arlo Investigations of Phase Transitions and
		  Critical Phenomena",
  booktitle =	 "Phase Transitions and Critical Phenomena",
  publisher =	 "Academic Press",
  year =	 1972,
  editor =	 "C. Domb and M. S. Green",
  volume =	 "1. Exact Results",
  chapter =	 6,
  pages =	 "1-105",
  address =	 "London",
  annote =	 "Gives Historical review of Ising model"
}
% Plane triangular lattice, anit-ferromagnetic -- frustruations -> the
%		  transition temperature is decreased to zero.
% the entropy per site is finite at absolute zero.

@Unpublished{heckerman,
  author = 	 "D. M. Chickering and D. Heckerman",
  title = 	 "Efficient Approximations for the Marginal Likelihood of
                    {B}ayesian Networks With Hidden Variables",
  note = 	 "Microsoft Research Technical Report MSR-TR-96-08",
  year =	 1996,
url={http://www.research.microsoft.com/research/dtg/heckerma/TR-96-08.htm}
}
%To appear in Machine Learning
% was Efficient Approximations for Learning {B}ayesian
%		  Networks given Incomplete Data",

@InCollection{kanerva:spatter,
  author = 	 "P. Kanerva",
  title = 	 "Binary Spatter-Coding of $K$-tuples",
  booktitle =	 "Artifical Neural Networks -- ICANN 96 Proceedings
		  (Bochum, Germany)",
  publisher =	 "Springer",
  year =	 1996,
  OPTeditor = 	 "von der Malsburg, C. and von Seelen, W. and J. B.
		  Vorbr\uggen and B. Sendhoff",
  pages =	 "869-873",
  address =	 "Berlin"
}

@Book{Sivia:96,
  author = 	 "D. S. Sivia",
  title = 	 "Data Analysis. A {B}ayesian Tutorial",
  publisher = 	 "Oxford University Press",
  year = 	 1996,
annote="ISBN 0-19-851889-7"
}

@article{jaakkola_jordan:logistic,
  author = 	 "T. S. Jaakkola and M. I. Jordan",
  title = 	 "{B}ayesian Logistic Regression: a Variational Approach",
 journal={Statistics and Computing},
 volume=10,
 pages={25-37},
 annote={Tech report 1996 MIT},
  year = 	 2000,
 annote={T. S. Jaakkola and M. I. Jordan. Statistics and Computing, 10, 25-37, 2000}
}

@article{jaakkola_jordan:logistic00,
title={{B}ayesian parameter estimation via variational methods},
author={T. S. Jaakkola and M. I. Jordan},
journal={Statistics and Computing},
volume={10},number={1},pages={25-37},month={January},year={2000}
}

@TechReport{jaakkola_jordan:recursive,
  author = 	 "T. S. Jaakkola and M. I. Jordan",
  title = 	 "Recursive Algorithms for Approximating Probabilities
		  in Graphical Models",
  institution =  "MIT",
  year = 	 1996,
  OPTtype = 	 "Computational Cognitive Science",
  OPTnumber = 	 "9604"
}

@InCollection{jaakkola_jordan:bounds,
  author = 	 "T. S. Jaakkola and M. I. Jordan",
  title = 	 "Computing Upper and Lower Bounds on Likelihoods in
		  Intractable Networks",
  booktitle =	 "Proceedings of the Twelfth Conference on Uncertainty
		  in {AI}",
  publisher =	 "Morgan Kaufman",
  year =	 1996
}


@InCollection{williams_rasmussen:96,
  author = 	 "C. K. I. Williams and C. E. Rasmussen",
  title = 	 "Gaussian Processes for Regression",
  booktitle =	 "Advances in Neural Information Processing Systems 8",
  publisher =	 "MIT Press",
  year =	 1996,
  editor =	 "D. S. Touretzky and M. C. Mozer and M. E. Hasselmo.",
  annote =	 "The {B}ayesian analysis of neural networks is difficult because a simple prior over weights implies a
     complex prior distribution over functions. In this paper we investigate the use of Gaussian process priors over
     functions, which permit the predictive {B}ayesian analysis for fixed values of hyperparameters to be carried out
     exactly using matrix operations. Two methods, using optimization and averaging (via Hybrid Monte Carlo) over
     hyperparameters have been tested on a number of challenging problems and have produced excellent results. 
"
}


@unpublished{williams:95,
  author = 	 "C. K. I. Williams",
  title = 	 "Regression with {G}aussian Processes",
  note =	 "To appear in Annals of
     Mathematics and Artificial Intelligence.",
  year =	 1995
}

%{B}ayesian Classification with Gaussian Processes gzipped postscript 
%     C. K. I. Williams and David Barber 
%     In: IEEE Trans Pattern Analysis and Machine Intelligence , 20(12) 1342-1351, (1998).

@Inproceedings{williams:96,
  author = 	 "D. Barber and C. K. I. Williams",
  title = 	 "{G}aussian Processes for {B}ayesian Classification via
		  Hybrid {M}onte {C}arlo",
  booktitle =	 "Neural Information Processing Systems 9",
  publisher =	 "MIT Press",
  editor =	 "M. C. Mozer and M. I. Jordan and T. Petsche",
  pages =	 "340-346",
  year =	 1997
}
@unpublished{williams:01,
  author = 	 "C. K. I. Williams",
  title = 	 "Personal communication",
  year =	 2001
}
@mastersthesis{Agakov-2000,
   author = "F. Agakov",
   title = {{Investigations of Gaussian Products-of-Experts Models}},
   school = "Division of Informatics, The University of Edinburgh", 
   note = "Available at \url{http://www.dai.ed.ac.uk/homes/felixa/all.ps.gz}",
   year = 2000}


@PhdThesis{rasmussen:phd,
  author = 	 "C. E. Rasmussen",
  title = 	 "Evaluation of {G}aussian Processes and Other Methods
		  for Non-Linear Regression ",
  school = 	 "University of Toronto",
  year = 	 1996
}

@article{Herz1995,
  title="Earthquake Cycles and Neural Reverberations -- Collective Oscillations
    in Systems with Pulse-Coupled Threshold Elements",
  author="Herz, A. V. M. and Hopfield, J. J.",
  journal="Physical Review Letters",
  year="1995",
  volume="75",
  number="6",
  pages="1222-1225",
  abstract="Driven systems of interconnected blocks with stick-slip friction 
    capture main features of earthquake processes. The microscopic 
    dynamics closely resemble those of spiking nerve cells. We analyze 
    the differences in the collective behavior and introduce a class of 
    solvable models. We prove that the models exhibit rapid phase 
    locking, a phenomenon of particular interest to both geophysics and 
    neurobiology. We study the dependence upon initial conditions and 
    system parameters, and discuss implications for earthquake modeling 
    and neural computation."
}

@article{Hopfield_Herz1995,
  title="Rapid Local Synchronization of Action-Potentials -- Toward Computation
    with Coupled Integrate-And-Fire Neurons",
  author="Hopfield, J. J. and Herz, A. V. M.",
  journal="Proc.\ Natl.\ Acad.\ Sci.\ USA",
  year="1995",
  volume="92",
  number="15",
  pages="6655-6662",
  abstract="The collective behavior of interconnected spiking nerve cells is 
    investigated. It is shown that a variety of model systems exhibit the
    same short-time behavior and rapidly converge to (approximately) 
    periodic firing patterns with locally synchronized action potentials.
    The dynamics of one model can be described by a downhill motion on an
    abstract energy landscape, Since an energy landscape makes it 
    possible to understand and program computation done by an attractor 
    network, the results will extend our understanding of collective 
    computation from models based on a firing-rate description to 
    biologically more realistic systems with integrate-and-fire neurons."
}

@article{RoweisSaul2000,
title={Nonlinear dimensionality reduction by locally linear embedding},
author={Sam Roweis and Lawrence Saul},
journal={Science},
volume={290},
number={5500},
annote={Dec.22, 2000},
year={2000},
pages={2323--2326}
}

@inproceedings{HintonRoweis2003,
author={Geoffrey Hinton and Sam Roweis},
title={Stochastic Neighbour Embedding},
conference={Neural Information Processing Systems 15 (NIPS'02)},
year={2003},
note={to appear}
}


@article{Hopfield1995,
  title="Pattern-Recognition Computation Using Action-Potential Timing for 
    Stimulus Representation",
  author="Hopfield, J. J.",
  journal="Nature",
  year="1995",
  volume="376",
  number="6535",
  pages="33-36",
  abstract="A computational model is described in which the sizes of variables 
    are represented by the explicit times at which action potentials 
    occur, rather than by the more usual 'firing rate' of neurons. The 
    comparison of patterns over sets of analogue variables is done by a 
    network using different delays for different information paths. This 
    mode of computation explains how one scheme of neuroarchitecture can 
    be used for very different sensory modalities and seemingly different
    computations. The oscillations and anatomy of the mammalian olfactory
    systems have a simple interpretation in terms of this representation,
    and relate to processing in the auditory system. Single-electrode 
    recording would plot detect such neural computing. Recognition 
    'units' in this style respond more like radial basis function units 
    than elementary sigmoid units."
}

@article{Hopfield1994,
  title="Physics, Computation, and Why Biology Looks So Different",
  author="Hopfield, J. J.",
  journal="Journal of Theoretical Biology",
  year="1994",
  volume="171",
  number="1",
  pages="53-60",
  abstract="The biological world is a physical system whose properties and 
    behaviors seem entirely foreign to physics. The origins of this 
    discrepancy lie in the very high information content in biological 
    systems (the large amount of dynamically broken symmetry) and the 
    evolutionary value placed on predicting the future (computation) in 
    an environment which is inhomogeneous in time and in space; Within 
    this context, 'free will' can be described as a useful predictive 
    myth."
}
@article{Hopfield1974,
title={Kinetic Proofreading: A New Mechanism for Reducing Errors in Biosynthetic Processes Requiring High Specificity},
author={        J. J. Hopfield},
journal={Proc.\ Natl.\ Acad.\ Sci.\ USA},
volume={71},
number={10},
month={October},
year={1974},
pages={4135-4139},  
annote={        J. J. Hopfield,
  Kinetic Proofreading: A New Mechanism for Reducing Errors in Biosynthetic Processes Requiring High Specificity.
        Proceedings of the National Academy of Sciences of the United States of America, Vol. 71, No. 10. (Oct., 1974), pp. 4135-4139.
},
  URL={http://links.jstor.org/sici?sici=0027-8424%28197410%2971%3A10%3C4135%3AKPANMF%3E2.0.CO%3B2-Y},
    Abstract={
    The specificity with which the genetic code is read in protein synthesis, and with which other highly specific biosynthetic reactions take place, can be increased above the level available from free energy differences in intermediates or kinetic barriers by a process defined here as kinetic proofreading. A simple kinetic pathway is described which results in this proofreading when the reaction is strongly but nonspecifically driven, e.g., by phosphate hydrolysis. Protein synthesis, amino acid recognition, and DNA replication, all exhibit the features of this model. In each case, known reactions which otherwise appear to be useless or deleterious complications are seen to be essential to the proofreading function.
}
}
@article{Hendin1994,
  title="Decomposition of a Mixture of Signals in a Model of the Olfactory Bulb",
  author="Hendin, O. and Horn, D. and Hopfield, J. J.",
  journal="Proc.\ Natl.\ Acad.\ Sci.\ USA",
  year="1994",
  volume="91",
  number="13",
  pages="5942-5946",
  abstract="We describe models for the olfactory bulb which perform separation 
    and decomposition of mixed odor inputs from different sources. The 
    odors are unknown to the system; hence this is an analog and 
    extension of the engineering problem of blind separation of signals. 
    The separation process makes use of the different temporal 
    fluctuations of the input odors which occur under natural conditions.
    We discuss two possibilities, one relying on a specific architecture 
    connecting modules with the same sensory inputs and the other 
    assuming that the modules (e.g., glomeruli) have different receptive 
    fields in odor space. We compare the implications of these models for
    the testing of mixed odors from a single source."
}
@article{Hopfield1999,
Title={		     Odor Space and Olfactory Processing: Collective Algorithms
		     and Neural Implementation},
Author={	     Hopfield, J. J.},
journal={ 	     Proc.\ Natl.\ Acad.\ Sci.\ USA},
Vol= 96, Number= 22,
year={		     1999},
pages={12506-12511},
annote={ 	     Proceedings of the National Academy of Sciences of the
		     United States of America, Vol. 96, No. 22. (Oct. 26,
		     1999), pp. 12506-12511.},
 URL={     http://links.jstor.org/sici?sici=0027-8424%2819991026%2996%3A22%3C12506%3AOSAOPC%3E2.0.CO%3B2-M},
Abstract={	     Several basic olfactory tasks must be solved by highly
		     olfactory animals, including background suppression,
		     multiple object separation, mixture separation, and source
		     identification. The large number N of classes of olfactory
		     receptor cells -- hundreds or thousands -- permits the use of
		     computational strategies and algorithms that would not be
		     effective in a stimulus space of low dimension. A model of
		     the patterns of olfactory receptor responses, based on the
		     broad distribution of olfactory thresholds, is
		     constructed. Representing one odor from the viewpoint of
		     another then allows a common description of the most
		     important basic problems and shows how to solve them when
		     N is large. One possible biological implementation of
		     these algorithms uses action potential timing and
		     adaptation as the "hardware" features that are
		     responsible for effective neural computation.
}
}

@article{Hopfield1991,
Title={		     Olfactory Computation and Object Perception},
Author={	     Hopfield, J. J. },
note={ 	     Proc.\ Natl.\ Acad.\ Sci.\ USA, Vol. 88, No. 15. (Aug. 1, 1991),
		     pp. 6462-6466.},
 URL={          http://links.jstor.org/sici?sici=0027-8424%2819910801%2988%3A15%3C6462%3AOCAOP%3E2.0.CO%3B2-I},
Abstract={	     Animals that are primarily dependent on olfaction must
		     obtain a description of the spatial location and the
		     individual odor quality of environmental odor sources
		     through olfaction alone. The variable nature of turbulent
		     air flow makes such a remote sensing problem solvable if
		     the animal can make use of the information conveyed by the
		     fluctuation with time of the mixture of odor sources.
		     Behavioral evidence suggests that such analysis takes
		     place. An adaptive network can solve the essential
		     problem, isolating the quality and intensity of the
		     components within a mixture of several individual unknown
		     odor sources. The network structure is an idealization of
		     olfactory bulb circuitry. The dynamics of synapse change
		     is essential to the computation. The synaptic variables
		     themselves contain information needed by higher processing
		     centers. The use of the same axons to convey intensity
		     information and quality information requires time-coding
		     of information. Covariation defines an individual odor
		     source (object), and this may have a parallel in
		     vision.
}
}

@article{Hopfield1980,
Title={		     The Energy Relay: A Proofreading Scheme Based on Dynamic
		     Cooperativity and Lacking All Characteristic Symptoms of
		     Kinetic Proofreading in {DNA} Replication and Protein
		     Synthesis},
Author={	     Hopfield, J. J. },
journal= 	     {Proc.\ Natl.\ Acad.\ Sci.\ USA},
Volume= 77,
Number= 9,
part={ 2:		     Biological Sciences},
month={Sep},
year={1980},
pages={5248-5252},
annote={Proceedings of the National Academy of Sciences of the
		     United States of America, Vol. 77, No. 9, [Part 2:
		     Biological Sciences]. (Sep., 1980), pp. 5248-5252.},
 URL={   http://links.jstor.org/sici?sici=0027-8424%28198009%2977%3A9%3C5248%3ATERAPS%3E2.0.CO%3B2-D},
Abstract=	{    A mechanism for proofreading biosynthetic processes
		     requiring high accuracy is described. The previously
		     understood ``kinetic proofreading'' mechanism of enhancing
		     accuracy has distinguishing characteristics such as the
		     nonstoichiometric use of substrate or cosubstrate that
		     have allowed its identification in aspects of DNA and
		     protein synthesis. The proofreading scheme developed here,
		     though generically related, lacks all the previous
		     identifying features. A DNA polymerase proofreading in
		     this manner need neither generate dNMP nor have a
		     $3^{\prime}\rightarrow 5^{\prime}$ exonuclease activity.
		     Protein synthesis could be proofread even with
		     stoichiometric GTP consumption or without elongation
		     factor Tu$\cdot $GTP. The kinetic scheme that generates
		     this proofreading makes use of an ``energy relay'' from
		     previous substrate molecules and is a representative of a
		     class of nonequilibrium processes displaying dynamic
		     cooperativity. This proofreading mechanism has its own
		     identifying characteristics, which are sufficiently subtle
		     that they would have generally escaped notice or defied
		     interpretation.}
}

@article{Hopfield1978,
Title={		     Origin of the Genetic Code: A Testable Hypothesis Based on
		     t{RNA} Structure, Sequence, and Kinetic Proofreading},
Author={	     Hopfield, J. J.},
journal={ 	     Proc.\ Natl.\ Acad.\ Sci.\ USA},
Volume={75}, Number={9},
year={1978},
month={Sep},
	     pages={4334-4338},
annote={ 	     Proceedings of the National Academy of Sciences of the
		     United States of America, Vol. 75, No. 9. (Sep., 1978),
		     pp. 4334-4338.},
 URL={      http://links.jstor.org/sici?sici=0027-8424%28197809%2975%3A9%3C4334%3AOOTGCA%3E2.0.CO%3B2-8 },
Abstract={	     We hypothesize that the origin of the genetic code is
		     associated with the structure of the tRNA that existed in
		     primal cells. The sequences of modern tRNA contain
		     correlations which can be understood as ``fossil''
		     evidence of the secondary structure of primal tRNA.
		     Kinetic proofreading through diffusion can amplify a low
		     level of intrinsic selectivity of tRNA for its amino acid.
		     Experimental tests of the theory are suggested.
}
}

%   Chib, S. (1995) Marginal likelihood from the Gibbs output, Journal
%     of the American Statistical Association, v. 90, pp. 1313-1321.
%
% search for this string
%%%%%%%% changed since last publication list %%%%%%%%%%%
@Article{Gelman96,
  author = 	 "A. Gelman",
  title = 	 "{B}ayesian Model-Building by Pure Thought: Some
		  Principles and Examples",
  journal =	 "Statistica Sinica",
  year =	 1996,
  volume =	 6,
  pages =	 "215-232"
}

% Bernardo, J. M. and Smith, A. F. M. (1994) {B}ayesian Theory, New
%		  York: John Wiley. 
% 13 B 27
% 
@book{gelman1995,
 author={Gelman, A. and Carlin, J.B. and Stern, H.S. and Rubin, D.B.},
 year={1995},
 title={{B}ayesian Data Analysis},
 address={London},
 publisher={Chapman and Hall},
 ISBN={0-412-03991-5},
annote={cav   13 G 25}}

@ARTICLE{OHagan78,
 AUTHOR         = "A. O'Hagan",
 TITLE          = "On curve fitting and optimal design for regression",
 JOURNAL        = "Journal of the Royal Statistical Society, B",
 YEAR           = 1978,
 VOLUME         = 40,
 PAGES          = "1-42"
}

@ARTICLE{Matheron63b,
 AUTHOR         = "G. Matheron",
 TITLE          = "Principles of Geostatistics",
 JOURNAL        = "Economic Geology",
 YEAR           = 1963,
 VOLUME         = 58,
 PAGES          = "1246-1266"
}

@ARTICLE{Omre87,
 AUTHOR         = "H. Omre",
 TITLE          = "{B}ayesian kriging -- merging observations and
		  qualified guesses in kriging",
 JOURNAL        = "Mathematical Geology",
 YEAR           = 1987,
 VOLUME         = 19,
 PAGES          = "25-39"
}

@ARTICLE{Kitanidis86,
 AUTHOR         = "P. K. Kitanidis",
 TITLE          = "Parameter uncertainty in estimation of spatial
		  functions: {B}ayesian analysis",
 JOURNAL        = "Water Resources Research",
 YEAR           = 1986,
 VOLUME         = 22,
 PAGES          = "499-507"
}

@ARTICLE{Lowe95,
 AUTHOR         = "D. G. Lowe",
 TITLE          = "Similarity Metric Learning for a Variable Kernel 
		  Classifier",
 JOURNAL        = "Neural Computation",
 YEAR           = 1995,
 VOLUME         = 7,
 PAGES          = "72-85"
}
		  
@BOOK{Cressie,
   author = "N.A.C. Cressie",
   title = "Statistics for Spatial Data",
   publisher = "Wiley",
   year = 1993 }

@BOOK{Barnett,
   author = "S. Barnett",
   title = "Matrix Methods for Engineers and Scientists",
   publisher = "McGraw-Hill",
   year = 1979 }

% 
@book{ohagan94,
 author = {O'Hagan, A.},
title="{B}ayesian Inference",
volume={2B},
series={{K}endall's Advanced Theory of Statistics},
publisher={Edward Arnold},
year={1994}}

% O'Hagan, A. (1987). Monte Carlo is fundamentally unsound,
@article{ohagan87,
 author = {O'Hagan, A.},
year={1987},
title={{M}onte {C}arlo is fundamentally unsound},
 journal={The Statistician},
 volume={36}, pages={247-249}
}
%
%     O'Hagan, A. (1994) {B}ayesian Inference (Volume 2B in Kendall's Advanced Theory of Statistics), ISBN
%     0-340-52922-9. 
%  13 K 29 
% 
%     Robert, C. P. (1995) The {B}ayesian Choice, New York: Springer. 

@Article{drugowich,
  author = 	 "Drugowich de Felicio, J. R. and Libero, V. L.",
  title = 	 "Updating {M}onte {C}arlo Algorithms",
  journal =	 "Am. J. Phys.",
  year =	 1996,
  volume =	 64,
  number =	 10,
  pages =	 "1281-1285",
  month =	 "October"
}

%  Swendsen, R. H., Wang, J-S., and Ferrenberg, A. M. (1992) ``New
%  Monte Carlo methods for improved efficiency of computer simulations
%  in statistical mechanics'', in K. Binder (editor) {\em The Monte
%  Carlo Method in Condensed Matter Physics}, Berlin: Springer.

@Article{Swendsen1987,
  author = 	 "Swendsen, R. H. and Wang, J-S",
  title = 	 "Nonuniversal critical dynamics
  in {M}onte {C}arlo simulations",
  journal =	 "Physical Review Letters",
  year =	 1987,
  volume =	 58,
  pages =	 "86-88"
}
@InCollection{Swendsen1992,
  author = 	 "Swendsen, R. H. and Wang, J-S. and Ferrenberg, A. M.",
  title = 	 "New {M}onte {C}arlo
   methods for improved efficiency of computer simulations
  in statistical mechanics",
  publisher =	 "Springer",
  year =	 1992,
  editor =	 "K. Binder",
  booktitle = 	 "The {M}onte {C}arlo Method in Condensed Matter Physics",
  address =	 "Berlin"
}

@article{Welch84,
author={Terry Welch},
title={A Technique for High-Performance Data Compression},
journal={IEEE Computer},
volume={17}, number={6}, 
month={June},
year={1984},
pages={},
annote={ Welch, Terry A., "A Technique for High Performance Data Compression," IEEE Computer, vol. 17, no. 6, June 1984.  }
}

@Article{Ziv_Lempel77,
  author = 	 "J. Ziv and A. Lempel",
  title = 	 "A Universal Algorithm for Sequential Data
Compression",
  journal =	 "IEEE Trans. on Info. Theory",
  year =	 1977,
  volume =	 23,
  number =	 3,
  pages =	 "337-343",
  month =	 "May"
}


@Article{Ziv_Lempel78,
  author = 	 "J. Ziv and A. Lempel",
  title = 	 "Compression of Individual Sequences via Variable-Rate Coding",
  journal =	 "IEEE Trans. on Info. Theory",
  year =	 1978,
  volume =	 24,
  number =	 5,
  pages =	 "",
  month =	 "September",
  annote={Ziv, J., and A. Lempel, "Compression of Individual Sequences via Variable-Rate Coding," IEEE Transactions on Information Theory, vol. 24, no. 5, September 1978. }
}

@Book{Gardner:Carnival,
  author = 	 "M. Gardner",
  title = 	 "Mathematical Carnival",
  publisher = 	 "Random House Vintage Books",
  year = 	 1977,
  annote =	 "orig pub Alred Knopf Inc Oct 1975"
}% the ch 9 puzzle on the glass was first in
% Barr's 'Second Miscellany of Puzzles'
@book{EliasACmentionedpages61to62,
author={N. Abramson},
title={Information Theory and Coding},
address={New York},
publisher={McGraw-Hill},
year={1963}
}

@Article{Elias75,
  author = 	 "P. Elias",
  title = 	 "Universal Codeword Sets and Representations of the Integers",
  journal =	 "IEEE Trans. on Info. Theory",
  year =	 1975,
  volume =	 21,
  number =	 2,
  pages =	 "194--203",
  month =	 "March"
}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%
% evolution
@Article{EWK99,
  author = 	 {Eyre--Walker, A. and Keightley, P.},
  title = 	 {High genomic deleterious mutation rates in hominids},
  journal = 	 {Nature},
  year = 	 1999,
 volume= 397,
  pages =	 {344-347}
}

% should the mtn rate be close as pos to zero?
%13 Maynard Smith J. (1989), "The limitations of evolutionary theory", in Did Darwin Get It Right?,
%     J. M. Smith (Ed.), New York: Chapman and Hall, pp. 180-191.
% 16 Williams G. C. (1966), Adaptation and Natural Selection, Princeton: Princeton University Press.
%
% E.B. Baum and W.D. Smith. A bayesian approach to relevance in game playing.
%Artificial Intelligence, 97(1--2):195--242, 1997.
@article{ baum97bayesian,
    author = "Eric B. Baum and Warren D. Smith",
    title = "A {B}ayesian Approach to Relevance in Game Playing",
    journal = "Artificial Intelligence",
    volume = "97",
    number = "1-2",
    pages = "195-242",
    year = "1997",
    url = "citeseer.nj.nec.com/baum97bayesian.html" }
@techreport{ baum93best,
    author = "Eric B. Baum and Warren D. Smith",
    title = "Best Play for Imperfect Players and Game Tree Search",
    address = "Princeton, NJ",
    year = "1993",
institution={NEC},
    url = "citeseer.nj.nec.com/baum95best.html" }

@unpublished{Baum96,
title = "Where Genetic Algorithms Excel",
author={E.B. Baum and Dan Boneh and  C. Garrett},
year={1996},
note={To appear in {\em Evolutionary Computation}},
annote={Jul 10  1996},
url={http://www.neci.nj.nec.com/homepages/eric/eric.html},
address={NEC Research Institute, Princeton}
}
@inproceedings{Baum95,
title = "On Genetic Algorithms",
author={E.B. Baum and Dan Boneh and  C. Garrett},
year={1995},
booktitle={Proceedings of the Eighth Annual Conference on Computational
Learning Theory},
pages={230-239},
publisher={ACM},
address={New York},
url={http://www.neci.nj.nec.com/homepages/eric/eric.html},
authoraddress={NEC Research Institute, Princeton}
}
@article{Worden95,
title={A speed limit for evolution},
author={R. P. Worden},
journal={Journal of Theoretical Biology}, volume={176}, number={1},
month={Sep},
year={1995}, pages={137-152}
}
@book{Bulmer1985,
author={M.G. Bulmer},year={1985},title={The Mathematical Theory of Quantitative Genetics},
publisher={Oxford University Press},
address={Oxford}
}


@Article{Muhlenbein93,
  author = 	 {H. M\"uhlenbein and D. Schlierkamp--Voosen},
  title = 	 {Predictive Models for the Breeder Genetic Algorithm {I.}
 {C}ontinuous Parameter Optimization},
  journal = 	 {Evolutionary Computation},
  year = 	 1993,
  volume =	 1,
  pages =	 {25-50}
}

% what is the mutation rate?:

%Li, W.-H., C.-I. Wu, and C.-C. Luo. 1985. A new method
%for estimating synonymous and nonsynonymous rates
%in nucleotide substitution considering the relative
%likelihood of nucleotide and codon changes. Mol. Biol. Evol. 2:
%150-174.

%Li, W.-H., M. Tanimura, and P. Sharp. 1987. An evaluation
%of the molecular clock hypothesis using mammalian
%DNA sequences. J. Mol. Evol. 25: 330-342.

%Blackman, R.K., and M. Meselson. 1986. Interspecific nucleotide
%
%sequence comparisons used to identify
%regulatory and structural features of the Drosophila hsp82 gene.
%J. Mol. Biol. 188: 499-515.

% what is the E coli mutation rate? 
% from http://proks.bio.cmu.edu/term-papers/mutator/
% due to the
%editing function of the e subunit of DNA polymerase III, the error
%rate of an incorrect base incorporation is 10^-7 -- 10^-6
% /bp/cell/generation (For bacteria the unit of which the mutation rate
%for a particular trait is expressed is measured in
%mutations/bacterium/cell division and the observable quantities are
%total number of bacteria at the beginning and end of the experiment as
%well as total number of mutant cells) (Miller, 112) However, if a
%mutation were to occur at the e subunit of DNA Polymerase III, it will
%result in communication loss between this subunit and other subunits
%of the Polymerase III (especially subunit a) (Fijalkowska, 5979-5985)
%, altering the capability of the enzyme's proofreading. This effect
%will be further discussed in the mutD.
%
%%%%%%%%%%%%%%5 %
%%%%%%%%%%%%%%

@Book{Ridley1993,
  author =	 {Ridley, M},
  title = 	 {The Red Queen},
  publisher = 	 {Penguin},
  year = 	 1993,
  address =	 {London}
}

@book{Fisher1930,
author={Fisher, Ronald A.},
title={The genetical theory of natural selection},
address={Oxford},
publisher={Clarendon},
year={1930}}

@article{Fersht1988,
  title={Relationships Between Apparent Binding-Energies Measured in Site-
    Directed Mutagenesis Experiments and Energetics of Binding and 
    Catalysis},
  author={Fersht, A. R.},
  journal={Biochemistry},
  year={1988},
  volume={27},
  number={5},
  pages={1577-1580}
}

@article{Fersht1987,
  title={Structure-Activity-Relationships in Engineered Proteins -- Analysis Of
    Use of Binding-Energy by Linear Free-Energy Relationships},
  author={Fersht, A. R. and Leatherbarrow, R. J. and Wells, T. N. C.},
  journal={Biochemistry},
  year={1987},
  volume={26},
  number={19},
  pages={6030-6038}
}
@article{Wells1987,
  title={Using Protein Engineering to Understand Catalytic Yield},
  author={Wells, T. N. C. and Fersht, A. R.},
  journal={Protein Engineering},
  year={1987},
  volume={1},
  number={3},
  pages={261}
}

@article{Fersht1986,
  title={Quantitative-Analysis of Structure-Activity-Relationships in 
    Engineered Proteins by Linear Free-Energy Relationships},
  author={Fersht, A. R. and Leatherbarrow, R. J. and Wells, T. N. C.},
  journal={Nature},
  year={1986},
  volume={322},
  number={6076},
  pages={284-286}
}



@Book{JMSES95,
  author =	 {Maynard Smith, John and Sz\'athmary, E\"ors},
  title = 	 {The Major Transitions in Evolution},
  publisher = 	 {Freeman},
  year = 	 1995,
  address =	 {Oxford}
}

@Book{JMSES99,
  author =	 {Maynard Smith, John and Sz\'athmary, E\"ors},
  title = 	 {The Origins of Life},
  publisher = 	 {Oxford University Press},
  year = 	 1999,
  address =	 {Oxford}
}

@Book{JMS88,
  author =	 {Maynard Smith, John},
  title = 	 {Games, Sex and Evolution},
  publisher = 	 {Harvester--Wheatsheaf},
  year = 	 1988,
  address =	 {Hertfordshire},
  annote =	 {379:5.c.95.333 U.L. SF 5}
}

@Book{JMS58,
  author =	 {Maynard Smith, John},
  title = 	 {The  Theory of Evolution},
  publisher = 	 {Cambridge University Press},
  year = 	 1958,
  address =	 {Cambridge},
  annote =	 {}
}

@Book{JMS78,
  author =	 {Maynard Smith, John},
  title = 	 {The Evolution of Sex},
  publisher = 	 {Cambridge University Press},
  year = 	 {1978},
  address =	 {Cambridge},
  annote =	 {379:5.c.95.131 U.L. SF 5, W.465 in Whipple, GGE in Eth (arch and anth, haddon)}
}

% mud theory?
@book{CairnsSmith1985,
annote={Cairns-Smith, A. G. Seven Clues to the Origin of Life, Cambridge University Press, 1985.},
author={Cairns-Smith, A. G.},
title={Seven Clues to the Origin of Life},
publisher={Cambridge University Press},
year=1985
}

@book{Dyson1985,
author={Dyson, Freeman J.},
title={Origins of Life},
publisher={Cambridge University Press},
year=1985,
annote={Dyson, Freeman J. Origins of Life, Cambridge University Press, 1985.
}
}

@InCollection{Felsenstein85,
  author = 	 {Felsenstein, J.},
  title = 	 {Recombination and sex: is {M}aynard {S}mith necessary?},
  booktitle = 	 {Evolution. Essays in Honour of {J}ohn {M}aynard {S}mith},
  pages =	 {209-220},
  publisher =	 {Cambridge University Press},
  year =	 1985,
  editor =	 {P. J. Greenwood and P. H. Harvey and M. Slatkin},
  address =	 {Cambridge}
}

@article{Goebel1995,
  title="The 11-Micron Emissions of Carbon Stars",
  author="Goebel, J. H. and Cheeseman, P. and Gerbault, F.",
  journal="Astrophysical Journal",
  year="1995",
  volume="449",
  number="1Pt1",
  pages="246-257",
  abstract="A new classification scheme of the IRAS LRS carbon stars is 
    presented. It comprises the separation of 718 probable carbon stars 
    into 12 distinct self-similar spectral groupings. Continuum 
    temperatures are assigned and range from 470 to 5000 K. Three 
    distinct dust species are identifiable: SiC, alpha:C-H, and MgS. In 
    addition to the narrow 11+ mu m emission feature that is commonly 
    attributed to SiC, a broad 11+ mu m emission feature, that is 
    correlated with the 8.5 and 7.7 mu m features, is found and 
    attributed to alpha:C-H. SiC and alpha:C-H band strengths are found 
    to correlate with the temperature progression among the Classes. We 
    find a spectral sequence of Classes that reflects the carbon star 
    evolutionary sequence of spectral types, or alternatively 
    developmental sequences of grain condensation in carbon-rich 
    circumstellar shells. If decreasing temperature corresponds to 
    increasing evolution, then decreasing temperature corresponds to 
    increasing C/O resulting in increasing amounts of carbon rich dust, 
    namely alpha:C-H. If decreasing the temperature corresponds to a 
    grain condensation sequence, then heterogeneous, or induced 
    nucleation scenarios are supported. SiC grains precede alpha:C-H and 
    form the nuclei for the condensation of the latter material. At still
    lower temperatures, MgS appears to be quite prevalent. No 11.3 mu m 
    PAH features are identified in any of the 718 carbon stars. However, 
    one of the coldest objects, IRAS 15048-5702, and a few others, 
    displays an 11.9 mu m emission feature characteristic of laboratory 
    samples of coronene. That feature corresponds to the C-H out of plane
    deformation mode of aromatic hydrocarbon. This band indicates the 
    presence of unsaturated, sp(3), hydrocarbon bonds that may 
    subsequently evolve into saturated bonds, sp(2), if, and when, the 
    star enters the planetary nebulae phase of stellar evolution. The 
    effusion of hydrogen from the hydrocarbon grain results in the 
    evolution in wavelength of this 11.9 mu m emission feature to the 
    11.3 mu m feature."
}

% Cheeseman, P., Stutz, J., Self, M., Taylor, W., Goebel, J., Volk, K., and Walker, H. 1989. Automatic Classification of Spectra From the Infrared Astronomical Satellite (IRAS), NASA Reference Publication #1217, National Technical Information Service, Springfield, Virginia.

@article{Goebel1989,
  title="A {B}ayesian Classification of the {IRAS} {LRS} Atlas",
  author="Goebel, J. and Volk, K. and Walker, H. and Gerbault, F. and Cheeseman, P. and Self, M. and Stutz, J. and    Taylor, W.",
  journal="Astronomy and Astrophysics",
  year="1989",
  volume="222",
  number="1-2",
  pages="L5-L8"
}
@book{goldie91,
 author={Goldie, C. M. and  R. G. E. Pinch},
title={Communication theory}, 
address={Cambridge},
publisher={Cambridge University Press},
year= 1991
}
% Series title:   London Mathematical Society student texts; 20
% Subjects:       Communication
% Other entries:  Pinch, Richard G. E.
% Location:       [Univ. Lib.] 351:5.c.95.185                South Front 4
%
% currently available at paperback price.

%COMMUNICATION THEORY           -- Social Sciences title
%D Crowley
%Binding: Hardback
%ISBN: 0804723486
%Published: January 1995
%Format: pages; 
%UK Price: 33.75

%There is also a Paperback available
%ISBN: 0804723478
%UK Price: 11.96

@Book{applebaum,
  author = 	 "D. Applebaum",
  title = 	 "Probability and Information. And Integrated Approach",
  publisher = 	 "Cambridge University Press",
  year = 	 1996,
  address =	 "Cambridge"
}


@Book{Ripley91,
  author = 	 "B. D. Ripley",
  title = 	 "Statistical Inference for Spatial Processes",
  publisher = 	 "Cambridge University Press",
  year = 	 1991
}

% Statistical Inference for Spatial Processes
% 
% B D Ripley
% 
% Title Details
% 
% Binding: Paperback
% ISBN: 0521424208
% Published: July 1991
% Format: 154 pp pages; 229 x 153mm 
% UK Price: 14.95
% 
% There is also a Hardback available
% ISBN: 0521352347
% UK Price: £22.5

% MIT press
% Neural Network Learning and Expert
%                Systems 
%                by Stephen I. Gallant
%  1993 
%  ISBN 0-262-07145-2 
%  364 pp. 156 illus.
%  $50.00 (cloth)
% 
%
search for this string
%%%%%%%% changed since last publication list %%%%%%%%%%%

@article{Marinari1992,
  title={Simulated Tempering -- a New {M}onte-{C}arlo Scheme},
  author={Marinari, E. and Parisi, G.},
  journal={Europhysics Letters},
  year={1992},
  volume={19},
  number={6},
  pages={451-458},
  abstract={We propose a new global optimization method (Simulated Tempering) for
    simulating effectively a system with a rough free-energy landscape 
    (i.e., many coexisting states) at finite nonzero temperature. This 
    method is related to simulated annealing, but here the temperature 
    becomes a dynamic variable, and the system is always kept at 
    equilibrium. We analyse the method on the Random Field Ising Model, 
    and we find a dramatic improvement over conventional Metropolis and 
    cluster methods. We analyse and discuss the conditions under which 
    the method has optimal performances.}
}

@article{Kerler1994,
  title={Simulated-Tempering Procedure for Spin-Glass Simulations},
  author={Kerler, W. and Rehberg, P.},
  journal={Physical Review E},
  year={1994},
  volume={50},
  number={5},
  pages={4220-4225}
}

@article{Hansmann1996,
  title={{M}onte-{C}arlo Simulations in Generalized Ensemble 
    -- Multicanonical 
    Algorithm Versus Simulated Tempering},
  author={Hansmann, U. H. E. and Okamoto, Y.},
  journal={Physical Review E},
  year={1996},
  volume={54},
  number={5},
  pages={5863-5865},
  abstract={It is shown that two Monte Carlo methods in generalized ensemble, 
    multicanonical algorithm and simulated tempering, are closely 
    related. The equivalence and effectiveness of the two methods 
    illustrated by taking an energy function for the protein folding 
    problem as an example.}
}


@article{Besag1993,
  title={Spatial Statistics and {B}ayesian Computation},
  author={Besag, J. and Green, P. J.},
  journal={Journal of the Royal Statistical Society Series B-Methodological},
  year={1993},
  volume={55},
  number={1},
  pages={25-37},
  abstract={Markov chain Monte Carlo (MCMC) algorithms, such as the Gibbs 
          sampler, have provided a {B}ayesian inference machine in image analysis
          and in other areas of spatial statistics for several years, founded 
          on the pioneering ideas of Ulf Grenander. More recently, the 
          observation that hyperparameters can be included as part of the 
          updating schedule and the fact that almost any multivariate 
          distribution is equivalently a Markov random field has opened the way
          to the use of MCMC in general {B}ayesian computation. In this paper, we
          trace the early development of MCMC in {B}ayesian inference, review 
          some recent computational progress in statistical physics, based on 
          the introduction of auxiliary variables, and discuss its current and 
          future relevance in {B}ayesian applications. We briefly describe a 
          simple MCMC implementation for the {B}ayesian analysis of agricultural 
          field experiments, with which we have some practical experience.}
}

@article{zheng1999,
author={Zheng, Q.},year={1999},
title={Progress of a half century in the study of the {L}uria-{D}elbr\"uck distribution},
journal={Mathematical Biosciences},
volume={162},
pages={1-32},
abstract={
The Luria--Delbr?ck mutation model has been mathematically formulated in a number of ways. This review article examines four most important formulations, focusing on important practical issues closely linked with the distribution of the number of mutants. These issues include the probability generating functions, moments (cumulants), computational methods and asymptotics. This review emphasizes basic principles which not only help to unify existing results but also allow for a few useful extensions. In addition, the review offers a historical perspective and some new explanations of divergent moments.
},
keywords={Luria-Delbr?ck model; Luria-Delbr?ck distribution; Estimation of mutation rate; Poisson-stopped-sum distribution; Filtered Poisson process
}
}
@article{luriadelbruck43,
 journal={Genetics},
author={S. E. Luria and M. Delbr\"uck},
title={Mutations of bacteria from virus sensitivity to virus resistance},
volume={28},
 pages={491-511},
year=1943,
 note={Reprinted in {\em Microbiology: A Centenary Perspective},    Wolfgang K. Joklik, ed.,
 1999, ASM Press, and available from
 {\tt{http://www.esp.org/}}
}
}
%Microbiology: A Centenary Perspective
%1999. 576 pages.
%Collector's hardcover edition. (ISBN 1-55581-162-0)
%List and ASM member price, $115.95
%Paperback. (ISBN 1-55581-169-8)

%
@article{kepleroprea01a,
author={Kepler, T.B. and Oprea, M.},
title={Improved inference of mutation rates: {I}. {A}n integral representation of the {L}uria-{D}elbr\"uck distribution.},
journal={Theoretical Population Biology},
volume={59}, pages={41-48}, year={2001},
annote={Kepler, T.B. & Oprea, M. Improved inference of mutation rates: I. An integral representation of the Luria--Delbr\"uck distribution. Theoretical Population Biology 59, 41-48 (2001).}
}
%

@article{Cowles1996a,
  title={{M}arkov-Chain {M}onte-{C}arlo Convergence Diagnostics --
           a Comparative     Review},
  author={Cowles, M. K. and Carlin, B. P.},
  journal={Journal of the American Statistical Association},
  year={1996},
  volume={91},
  number={434},
  pages={883-904},
  abstract={A critical issue for users of Markov chain Monte Carlo (MCMC) methods
    in applications is how to determine when it is safe to stop sampling 
    and use the samples to estimate characteristics of the distribution 
    of interest. Research into methods of computing theoretical 
    convergence bounds holds promise for the future but to date has 
    yielded relatively little of practical use in applied work. 
    Consequently, most MCMC users address the convergence problem by 
    applying diagnostic tools to the output produced by running their 
    samplers. After giving a brief overview of the area, we provide an 
    expository review of 13 convergence diagnostics, describing the 
    theoretical basis and practical implementation of each. We then 
    compare their performance in two simple models and conclude that all 
    of the methods can fail to detect the sorts of convergence failure 
    that they were designed to identify. We thus recommend a combination 
    of strategies aimed at evaluating and accelerating MCMC sampler 
    convergence, including applying diagnostic procedures to a small 
    number of parallel chains, monitoring autocorrelations and cross-
    correlations, and modifying parameterizations or sampling algorithms 
    appropriately. We emphasize, however, that it is not possible to say 
    with certainty that a finite sample from an MCMC algorithm is 
    representative of an underlying stationary distribution.}
}

@article{Cowles1996b,
  title={{B}ayesian Tobit Modeling of Longitudinal Ordinal Clinical-Trial 
    Compliance Data with Nonignorable Missingness},
  author={Cowles, M. K. and Carlin, B. P. and Connett, J. E.},
  journal={Journal of the American Statistical Association},
  year={1996},
  volume={91},
  number={433},
  pages={86-98},
  abstract={In the Lung Health Study (LHS), compliance with the use of inhaled 
    medication was assessed at each follow-up visit both by self-report 
    and by weighing the used medication canisters. One or both of these 
    assessments were missing if the participant failed to attend the 
    visit or to return all canisters. Approximately 30% of canister-
    weight data and 5% to 15% of self-report data were missing at 
    different visits. We use Gibbs sampling with data augmentation and a 
    multivariate Hastings update step to implement a {B}ayesian 
    hierarchical model for LHS inhaler compliance. Incorporating 
    individual-level random effects to account for correlations among 
    repeated measures on the same participant, our model is a 
    longitudinal extension of the Tobit models used in econometrics to 
    deal with partially unobservable data. It enables (a) assessment of 
    the relationships among visit attendance, canister return, self-
    reported compliance level, and canister weight compliance, and (b) 
    determination of demographic, physiological, and behavioral 
    predictors of compliance. In addition to addressing the estimation 
    and prediction questions of substantive interest, we use sampling-
    based methods for covariate screening and model selection and 
    investigate a range of informative priors on missing data.}
}
@book{Tanner96,
title={Tools for Statistical Inference: Methods for
               the Exploration of Posterior Distributions and
               Likelihood Functions},
series={Springer Series in Statistics},
author={M. A. Tanner},
edition={3rd},
publisher={Springer},
year={1996},
isbn={0387946888}
}
% cav ordered

@article{Richardson98,
title={The Capacity of Low-Density Parity Check Codes under Message-Passing Decoding},
author={T. Richardson and R. Urbanke},
annote={Submitted to IEEE Trans.\ on Info. Theory 1998},
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={599-618}
} 
@article{Richardson2001b,
title={Design of  Capacity-Approaching Irregular  Low-Density Parity Check Codes},
author={T. Richardson and M. A. Shokrollahi and R. Urbanke},
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={619-637}
} 
@article{Urbanke00,
title={Efficient Encoding  of Low-Density  Parity-Check Codes},
author={T. Richardson and R. Urbanke},
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={638-656}
}

@article{Chung2001,
title={Analysis of Sum-Product Decoding of Low-Density  Parity-Check Codes Using a {G}aussian Approximation},
 author={Chung, Sae-Young  and  Richardson, Thomas J. and  Urbanke,  R\"udiger L.},
 year={2001},
journal={IEEE Trans. on Info. Theory},
volume={47},
number={2},
pages={657-670}
}

@book{Spiegel,
 title={Statistics},
 author={Murray R. Spiegel},
edition={2nd},
 publisher={McGraw-Hill},
address={New York},
series={Schaum's outline series},
 year={1988}
}
@book{MCMC96,
title={{M}arkov Chain {M}onte {C}arlo in  Practice},
author={W. R. Gilks and S. Richardson and D. J. Spiegelhalter},
publisher={Chapman and Hall},
year={1996}, 
isbn={0412055511}
}
% cav ordered
%%  RUBIN_DB, 1988 Vol.3 p.385, BAYESIAN STAT (OUP)
%%           RUBIN_DB, 1987 Vol.82 p.543, J AM STAT ASSOC
%%           TI- THE CALCULATION OF POSTERIOR DISTRIBUTIONS BY DATA AUGMENTATION -- 
%%           COMMENT
%%       AU- RUBIN, DB
%%       NA- HARVARD UNIV,DEPT STAT,CAMBRIDGE,MA,02138
%%       JN- JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
%%       PY- 1987
%%       VO- 82
%%       NO- 398
%%       PG- 543-546
%%       DT- Note
%%       CR- COCHRAN_WG, 1977, SURVEY TECHNIQUES
%%           RUBIN_DB, 1985 Vol.12 p.1151, ANN STATISTICS
%%           RUBIN_DB, 1976 Vol.63 p.581, BIOMETRIKA
%%           RUBIN_DB, 1986 Vol.81 p.366, J AM STATISTICAL ASS
%%           RUBIN_DB, 1987, MULTIPLE IMPUTATION
%%           RUBIN_DB, 1983, PROGR REPORT PROJECT
%%           WILKS_SS, 1932 Vol.2 p.163, ANN MATH STATISTICS

@book{Mehta,
title={Random Matrices},
author={M. L. Mehta},
publisher={Academic Press},
year={1991},
edition={2},
isbn={0124880517}
}
% first               Publication date: November 1967
%               ISBN: 0124880509 

@book{Haake91,
title={Quantum Signatures of Chaos},
author={F. Haake},
publisher={Springer},
Cavendish={60 H 22},
year={1991}
}
%de Finetti's (famous?) prediction
%that {B}ayesian approaches would dominate science by the year 2020.
%
%The reference is: de Finetti, B. (1974) Theory of Probability: a critical
%introductory treatment. Vol 1. Wiley, New York.
%

@Article{turin96,
  author = 	 "L. Turin",
  title = 	 "A Spectroscopic Mechanism for Primary Olfactory Reception",
  journal =	 "Chem. Senses",
  year =	 1996,
  volume =	 21,
  number =	 "773-791"
}

@article{Schell97,
  title={D-Serine as a Neuromodulator: Regional and developmental 
          Localizations in Rat Brain Glia Resemble {NMDA} Receptors},
  author={Schell, M. J., Brady, R. O., Molliver, M. E., Snyder, S. H.},
  journal={Journal of Neuroscience},
 year={1997},
 volume={17},
 number={5},
 pages={1604-1615}
}

@Article{Lauritzen81,
  author = 	 {S. L. Lauritzen},
title ={Time Series Analysis in 1880, a Discussion of Contributions made
by {T.~N.\ Thiele}},
journal={ISI Review}  ,volume ={49},year={1981}, pages={319-333}}

@TechReport{Abrahamsen97,
  author = 	 "Abrahamsen, P.",
  title = 	 "A Review of {G}aussian Random Fields and
		  Correlation Functions",
  institution =  "Norwegian Computing Center",
  year = 	 1997,
  number =	 917,
 address={Blindern, N-0314 Oslo, Norway},
 fulladdress={Box 114, Blindern, N-0314 Oslo, Norway},
  note =	 "2nd edition"
}

@Book{Cybernetics,
  author = 	 "N. Wiener",
  title = 	 "Cybernetics",
  publisher = 	 "Wiley",
  year = 	 "1948"
}

@inproceedings{scholkopf95,
 author={B. Scholkopf and C. Burges and V. Vapnik},
 title ={Extracting support data for a given task},
 editor={U. M. Fayyad and R. Uthurusamy},
 booktitle= {Proceedings First
  International Conference on Knowledge Discovery and Data Mining},
 publisher={AAAI Press},
 address={Menlo Park, CA},
 year= 1995
}


@book{vapnik95,
author={V. Vapnik},
title={The Nature of Statistical Learning Theory},
publisher={Springer},
address={New York},
year= 1995
}

@book{jensen96,
 author={Jensen, F. V.},
 title={An Introduction to {B}ayesian Networks},
 year={1996},
 publisher={UCL press},
 address={London}
}

@incollection{deSa1997b,
author={de Sa, V. R., and Ballard, D.},
title={Perceptual Learning from Cross-Modal Feedback},
editors={R. L. Goldstone, P. G. Schyns, and D. L. Medin},
booktitle={Psychology of Learning and Motivation, Vol 36.},
address={San  Diego, CA}, 
publisher={Academic Press}
}

%McRae, K., de Sa V.R., & Seidenberg, M.S. (1997). On the nature and scope of featural
%representations of word meaning. Journal of Experimental Psychology: General, Jun, 126(2),
%99-130. abstract.

% Caruana, R., & de Sa, V.R. (1997). Promoting Poor Features to Supervisors: Some Inputs Work
% Better as Outputs. To appear in M.C. Mozer, M.I. Jordan & T. Petsche (Eds.), Advances in Neural
% Information Processing Systems 9. MIT Press. postscript.
% 
% de Sa, V.R. (1994). Unsupervised Classification Learning from Cross-Modal Environmental
% Structure. Doctoral dissertation, Department of Computer Science, University of Rochester, 96
% pages. 

% Combining Uni-Modal Classifiers to Improve Learning: Taking Advantage of Cross-Modal
% Environmental Structure. Presented at the conference on Integration of Elementary Functions into
% Complex Behavior, Zentrum für interdisziplinäre Forschung, Universität Bielefeld, Bielefeld,
% Germany, July 12-15 1994. postscript.

@incollection{deSa1994a,
author={de Sa, V. R.},
year={1994},
title={Learning Classification with Unlabeled Data},
  editor =	 "Cowan, J. D. and Tesauro, G. and Alspector, J.",
  booktitle =	 "Advances in Neural Information Processing Systems 6",
  year =	 1994,
 ADDRESS	="San Mateo, CA",
  publisher =	 "Morgan Kaufmann",
 PAGES		="112-119"
}
@incollection{deSa1994b,
author={de Sa, V. R.},
year={1994},
title={Minimizing Disagreement for Self-Supervised Classification},
  editor =	 "M.C. Mozer, P.
Smolensky, D.S. Touretzky and J.L. Elman",
  booktitle =	 "Proceedings of the 1993 Connectionist Models
Summer School",
  year =	 1994,
 ADDRESS	="San Mateo, CA",
  publisher =	 "Erlbaum Associates",
 PAGES		="300-307"
}

% de Sa, V.R., & Ballard, D.H. (1993). A Note on Learning Vector Quantization. In C.L. Giles, S.J.
% Hanson & J.D. Cowan (Eds.), Advances in Neural Information Processing Systems 5, (pp.
% 220---227). Morgan Kaufmann. postscript.

% McRae, K., de Sa, V.R., & Seidenberg, M.S. (1993). Modeling Property Intercorrelations in
% Conceptual Memory. In Proceedings of the 15th Annual Meeting of the Cognitive Science Society
% (pp. 729---734). 
@Article{BeckerHinton92,
  author =       "Suzanna Becker and Geoffrey E. Hinton",
  title =        "Self-organizing neural network that discovers surfaces
                 in random-dot stereograms",
  journal =      "Nature",
  year =         "1992",
  volume =       "355",
  pages =        "161--163",
  ref =          "VV25",
}
@InProceedings{Hinton90CX40,
  author =       "G. E. Hinton and S. Becker",
  title =        "An Unsupervised Learning Procedure that
                 Discovers Surfaces in Random-dot Stereograms",
  booktitle =    "Proceedings of the International Joint Conference on
                 Neural Networks",
  year =         "1990",
  address =      "Washington, DC",
  month =        jan,
  ref =          "CX40",
}
@TechReport{becker-hinton-89,
  key =          "becker",
  author =       "S. Becker and G.~E. Hinton",
  title =        "Spatial coherence as an internal teacher for a neural
                 network",
  type =         "Technical Report",
  number =       "CRG-TR-89-7",
  institution =  "University of Toronto",
  year =         "1989",
  annote =       "In CRG Library",
}
@InProceedings{Luttrell89b,
  author =       "Stephen P. Luttrell",
  title =        "Hierarchical self-organizing networks",
  booktitle =    "Proc.\ 1st IEE Conf.\ of Artificial Neural Networks",
  year =         "1989",
  pages =        "2--6",
  publisher =    "British Neural Network Society",
  address =      "London, UK",
}
@Article{Luttrell89c,
  author =       "S. P. Luttrell",
  title =        "Image compression using a multilayer neural network",
  journal =      "Pattern Recognition Letters",
  year =         "1989",
  volume =       "10",
  pages =        "1--7",
}@Article{Luttrell89d,
  author =       "S. P. Luttrell",
  title =        "Hierarchical vector quantisation",
  journal =      "Proc. IEE Part I",
  year =         "1989",
  volume =       "136",
  pages =        "405--413",
}
@InProceedings{Luttrell91b,
  author =       "S. P. Luttrell",
  title =        "Self-supervised training of hierarchical vector
                 quantisers",
  booktitle =    "Proc. 2nd IEE Conf. on Artificial Neural Networks",
  year =         "1991",
  pages =        "5--9",
  publisher =    "British Neural Network Society",
  address =      "London, UK",
}@TechReport{Luttrell91c,
  author =       "S. P. Luttrell",
  title =        "Self-supervision in multilayer adaptive networks",
  institution =  "RSRE",
  year =         "1991",
  number =       "4467",
  address =      "Malvern, UK",
}
@Misc{Luttrell92a,
  author =       "S. P. Luttrell",
  title =        "Image anomaly detector",
  howpublished = "British Patent Application 9202752.3",
  year =         "1992",
}
@Article{Luttrell92b,
  author =       "S. P. Luttrell",
  title =        "Self-supervised adaptive networks",
  journal =      "IEE Proc. F [Radar and Signal Processing]",
  year =         "1992",
  volume =       "139",
  number =       "6",
  pages =        "371--377",
  month =        dec,
}
@TechReport{luttrell-90,
  key =          "Luttrell",
  author =       "S. P. Luttrell",
  title =        "A Trainable Texture Anomaly Detector Using the
                 Adaptive Cluster Expansion ({ACE}) Method",
  type =         "Technical Report",
  number =       "{RSRE} Memorandum Number 4437",
  institution =  "Royal Signals and Radar Establishment",
  year =         "1990",
}
@Article{Dushuang95,
  author =       "Huang Dushuang",
  title =        "An analysis of the statistical properties on the
                 self-supervised learning subspaces for pattern
                 recognition",
  journal =      "Acta Electronica Sinica",
  year =         "1995",
  volume =       "23",
  number =       "9",
  pages =        "99--102",
}
@InProceedings{Ossen93,
  author =       "Arnfried Ossen",
  title =        "Learning Topology-Preserving Maps Using
                 Self-Supervised Backpropagation",
  booktitle =    "Proc. ICANN'93, Int. Conf. on Artificial Neural
                 Networks",
  year =         "1993",
  editor =       "Stan Gielen and Bert Kappen",
  pages =        "586--591",
  publisher =    "Springer",
  address =      "London, UK",
}
@TechReport{MIT-AILab//AITR-1086,
  bibdate =      "February 27, 1995",
  type =         "Technical Report",
  number =       "AITR-1086",
  title =        "Optimal Unsupervised Learning in Feedforward Neural
                 Networks",
  year =         "1989",
  month =        jan,
  institution =  "Massachusetts Institute of Technology, Artificial
                 Intelligence Laboratory",
  pages =        "130",
  author =       "Terence D. Sanger",
  abstract =     "We investigate the properties of feedforward neural
                 networks trained with Hebbian learning algorithms. A
                 new unsupervised algorithm is proposed which produces
                 statistically uncorrelated outputs. The algorithm
                 causes the weights of the network to converge to the
                 eigenvectors of the input correlation with largest
                 eigenvalues. The algorithm is closely related to the
                 technique of Self-supervised Backpropagation, as well
                 as other algorithms for unsupervised learning.
                 Applications of the algorithm to texture processing,
                 image coding, and stereo depth edge detection are
                 given. We show that the algorithm can lead to the
                 development of filters qualitatively similar to those
                 found in primate visual cortex.",
  notes =        "Keywords: neural networks, learning, connectionism,
                 vision, eigenvector analysis Cost: \$8.00 AD-A207961",
}
@TechReport{Schmidhuber:1990c,
  title =        "Making the world differentiable: On Using
                 Self-Supervised Fully Recurrent Neural Networks for
                 Dynamic Reinforcement Learning and Planning in
                 Non-Stationary Environments",
  author =       "J{\"u}rgen H. Schmidhuber",
  institution =  "Institut f{\"u}r Informatik, Technische
                 Universit{\"a}t M{\"u}nchen",
  year =         "1990",
  type =         "Forschungsberichte K{\"u}nstliche Intelligenz",
  number =       "FKI-126-90(revised)"
}
@TechReport{Sa94,
  author =       "Virginia R. de Sa",
  title =        "Unsupervised Classification Learning from Cross-Modal
                 Environmental Structure",
  institution =  "University of Rochester, Computer Science Department",
  number =       "TR536",
  month =        nov,
  year =         "1994",
  keywords =     "cross-modal; classification; connectionist; learning
                 vector quantization (LVQ); neural networks;
                 self-supervised; unsupervised learning",
  url =          "ftp://ftp.cs.rochester.edu/pub/papers/ai/94.tr536.Unsupervised_classification_learning.ps.Z",
  abstract =     "This dissertation addresses the problem of
                 unsupervised learning for pattern classification or
                 category learning. A model that is based on gross
                 cortical anatomy and implements biologically plausible
                 computations is developed and shown to have
                 classification power approaching that of a supervised
                 discriminant algorithm. .pp The advantage of supervised
                 learning is that the final error metric is available
                 during training. Unfortunately, when modeling human
                 category learning, or in constructing classifiers for
                 autonomous robots, one must deal with not having an
                 omniscient entity labeling all incoming sensory
                 patterns. We show that we can substitute for the labels
                 by making use of structure between the pattern
                 distributions to different sensory modalities. For
                 example the co-occurrence of a visual image of a cow
                 with a ``moo'' sound can be used to simultaneously
                 develop appropriate visual features for distinguishing
                 the cow image and appropriate auditory features for
                 recognizing the moo. .pp We model human category
                 learning as a process of minimizing the disagreement
                 between outputs of sensory modalities processing
                 temporally coincident patterns. We relate this
                 mathematically to the optimal goal of minimizing the
                 number of misclassifications in each modality and apply
                 the idea to derive an algorithm for piecewise linear
                 classifiers in which each network uses the output of
                 the other networks as a supervisory signal. .pp Using
                 the Peterson-Barney vowel dataset we show that the
                 algorithm finds appropriate placement for the
                 classification boundaries. The algorithm is then
                 demonstrated on the task of learning to recognize
                 acoustic and visual speech from images of lips and
                 their emanating sounds Performance on these tasks is
                 within 1-7$\backslash$\% of the related supervised
                 algorithm (LVQ2.1). .pp Finally we compare the
                 algorithm to Becker's IMAX algorithm and give
                 suggestions as to how the algorithm may be implemented
                 in the brain using physiological results concerning the
                 relationship between two types of neural plasticity,
                 LTP and LTD, observed in visual cortical cells. We also
                 show how the algorithm can be used as an efficient
                 method for dealing with learning from data with missing
                 values.",
  note =         "Thu, 17 Jul 97 09:00:00 GMT",
}
% Hinton, G. E. and Nowlan, S. J. (1987) How learning can guide evolution. Complex Systems, 1,
%     495--502.
@Article{Smith87,
  author =       "Maynard Smith, J.",
  title =        "When learning guides evolution.",
  journal =      "Nature",
  volume =       "329",
  pages =        "761--762",
  year =         "1987",
  keywords =     "machine learning, AI",
  abstract =     "via enews",
}
@article{HintonNowlan87,
 author={Hinton, G.E. and Nowlan, S.J.},
 year={1987},
 title={How learning can guide evolution},
 journal={Complex Systems},
 volume={1},
 pages={495-502}
}
@article{Baldwin1896,
 author={Baldwin, J.M.},
year={1896},
title={A new factor in evolution},
 journal={American Naturalist},
volume={30},
pages={441-451}
}
@article{mayley1996,
author={G. Mayley},
year={1996},
title={Landscapes, Learning Costs and Genetic Assimilation},
note={In Evolution, Learning, and Instinct:
100 Years of the Baldwin Effect,  Special Issue},
journal={Evolutionary Computation},
volume={4},
number={3},
editor={P. Turney, D. Whitley and R. Anderson},
url={http://www.cogs.susx.ac.uk/users/gilesm/index.html}
}
@TechReport{87aHint,
  author =       "Geoffrey E. Hinton",
  file =         "nn.bib",
  index =        "NN Review",
  title =        "Connectionist learning procedures",
  number =       "Computer Science Technical Report",
  publisher =    "Carnegie-Mellon University",
  address =      "Pittsburgh, PA",
  year =         "1987",
  month =        jun,
  ordernumber =  "CMU-CS-87-115",
  status =       "In hand",
  equations =    "26",
  figures =      "10",
  refs =         "83",
  pagecount =    "46",
  annote =       "The author reviews learning procedures under a number
                 of network paradigms. He defines the description of
                 knowledge representation in a network to be {"}local{"}
                 if a concept in the external descriptive language maps
                 to one or a small, fixed number of units in the
                 network, and {"}distributed{"} otherwise. He notes that
                 the classification of a network as one or the other
                 depends upon the descriptive language chosen. Each
                 output of a linear associator computes a linear
                 functions of the input. Hebbian learning consists of
                 adding to the weights on each connection the product of
                 the input and output activites for that association.
                 There are also nonlinear single-layer associative
                 memories. A common deficiency of single-layer networks
                 is that they can only perfectly encode inputs which are
                 linearly independent. Supervised learning amounts to
                 changing each weight by an amount proportional to the
                 local partial derivative of the error with respect to
                 that weight. This solution is optimal in the Least Mean
                 Square sense, and so is called LMS. In a multilayer
                 network, LMS is implemented by back-propagation. If the
                 outputs are binary-valued, then the outputs as a whole
                 can be taken to represent the probability distribution
                 of correctness for each output, given the
                 representation the network can achieve, i.e. the
                 network models a maximum likelihood estimator. Back
                 propagation can be applied to iterative (lattice)
                 networks. Reinforcement has also been used with
                 back-prop networks. A major drawback of back-prop is
                 that (on a sequential processor) its execution time
                 scales at least as order $N squared$. Back propagation
                 is probably not a good model of biological systems.
                 Boltzmann machines optimally adjust the weights in the
                 middle layer in a kind of stochastic physical model.
                 The information storage capabilities of Boltzmann
                 machines are well understood, by physical analog. Other
                 learning procedures include maximizing mutual
                 information between pairs of input classes,
                 unsupervised Hebbian learning, competitive learning,
                 and reinforcement learning. Unsupervised Hebbian
                 learning maximizes the covariances of the weighted
                 inputs to each unit. This maximizes the information
                 sent forward by each unit. Competitive learning is a
                 degenerate case of self-supervised back-propagation. A
                 version of competitive learning called genetic learning
                 produces new configurations by 'cross-breeding' good
                 ones in the current generation, and then re-running the
                 iteration toward a final state.",
  audience =     "Tutorial",
}
@InProceedings{Mel88,
  author =       "Bartlett W. Mel",
  title =        "{MURPHY}: {A} Robot that Learns by Doing",
  booktitle =    "Proc. First IEEE Conf. on Neural Information
                 Processing Systems",
  editor =       "Dana Z. Anderson",
  year =         "1988",
  publisher =    "IEEE Service Center",
  address =      "Piscataway, NJ",
  pages =        "544--553",
}
@TechReport{Mel??,
  author =       "B. Mel",
  title =        "The Sigma-Pi Column: {A} Model of Associative Learning
                 in Cerebral Neocortex",
  institution =  "Neuroprose",
  type =         "Technical Report",
  pages =        "44",
  url =          "ftp://archive.cis.ohio-state.edu/pub/neuroprose/mel.sigmapi?.ps.Z",
}
@InProceedings{Mel88V4,
  author =       "B. W. Mel",
  title =        "Building and Using Mental Models in a Sensory-Motor
                 Domain: {A} Connectionist Approach",
  booktitle =    "Proceedings of the Fifth International Conference on
                 Machine Learning",
  year =         "1988",
  month =        jun,
  address =      "Univerity of Michigan, Ann Arbor",
  pages =        "207--213",
  ref =          "V4",
}
@TechReport{Mel90HH12,
  author =       "B.~W. Mel",
  title =        "The Sigma-Pi Column",
  institution =  "California Institute of Technology, Pasadena",
  year =         "1990",
  number =       "CNS 216-76",
  month =        apr,
  ref =          "HH12",
}
@Article{barlow-72,
  key =          "Barlow",
  author =       "H.~B. Barlow",
  year =         "1972",
  title =        "Single units and sensation: {A} neuron doctrine for
                 perceptual psychology?",
  journal =      "Perception",
  volume =       "1",
  annote =       "In CRG Library",
  pages =        "371--394",
}
@inproceedings{berkmannisit,
 AUTHOR		={J. Berkmann and F. Burkert},
 TITLE		={Turbo-decoding of nonbinary codes},
 YEAR		=1997,
booktitle={Proceedings of ISIT 1997. Ulm, Germany.},
 PAGES		=""}

%George K. Zipf, Human Behavior and the Principle of least Effort,Addison-Wesley (1949).

% George K. Zipf, The Psycho-Biology of language, An introduction to Dynamic Philology, Cambridge MA, MIT Press (1965).

% Benoit Mandelbrot, Information Theory and Psycholinguistics: A Theory of Words Frequencies, in Readings in Mathematical Social Science. P. Lazafeld and N. Henry, Editors, Cambridge MA, MIT Press (1966).
% This should also be called the Pareto's law because Pareto observed this at the end of the last century.
% Zipf's law, named after the Harvard linguistic professor George Kingsley Zipf (1902-1950), is the observation that frequency of occurrence of some event ( P ), as a function of the rank ( i) when the rank is determined by the above frequency of occurrence, is a power-law function Pi ~ 1/ia with the exponent a close to unity
% http://myhome.hanafos.com/~philoint/phd-data/Zipf's-Law-2.htm
% # W Li (1992), "Random texts exhibit Zipf's-law-like word frequency distribution", IEEE Trans. on Info. Theory , 38(6):1842-1845.

@BOOK{Frac,
 KEY		="Mandelbrot",
 AUTHOR		="Benoit Mandelbrot",
 TITLE		="The Fractal Geometry of Nature",
 PUBLISHER	="W.H. Freeman",
 longPUBLISHER	="W.H. Freeman and Co",
 YEAR		="1982"}

@book{zipf,
author={Zipf, G. K.},
title={Human Behavior and the Principle of Least Effort},
publisher={Addison-Wesley},
year={1949},
}

@article{KeelingRand95,
title={A Spatial Mechanism for the Evolution and Maintenance of Sexual
 Reproduction},
author={Kelling, M. J. and Rand, D. A.},
journal={Oikos},
volume={74},
year={1995},
pages={414-424}
}
@article{Kimura61,
 author={M. Kimura},
 year={1961},
 title={Natural Selection as the Process of Accumulating Genetic
 Information in Adaptive Evolution},
 journal={Genetical Research Cambridge}
}
@book{MarkRidley,
title={Mendel's Demon: gene justice and the complexity of life},
publisher={Phoenix},
address={London},
year={2000},
author={Mark Ridley},
isbn={0753814102}
}
@article{Kondrashov1988,
  title={Deleterious Mutations and the Evolution of Sexual Reproduction},
  author={Kondrashov, A. S.},
  journal={Nature},
  year={1988},
  volume={336},
  number={6198},
  pages={435-440}
}
@Article{Smith68,
  author =       "Maynard Smith, J.",
  title =        {`{H}aldane's Dilemma' and the Rate of Evolution},
  journal =      "Nature",
  volume =       "219",
number={5159},
  pages =        "1114-1116",
  year =         "1968"
}



@article{bdelloidsize98,
journal={Hydrobiologia},
volume={387/388},
pages={395-402},
year=1998,
publisher={Kluwer},
title={Measurements of the genome size of the
            monogonont rotifer {Brachionus plicatilis} and of
            the bdelloid rotifers {Philodina roseola} and
            {Habrotrocha constricta}},
author={Mark Welch,            David B. and             Matthew Meselson}
}


@article{Yeung1991,
  title={A New Outlook on {S}hannon-Information Measures},
  author={Yeung, R. W.},
  journal={IEEE Trans. on Info. Theory},
  year={1991},
  volume={37},
  number={3.1},
  pages={466-474},
  abstract={Let X(i), i = 1,...,n, be discrete random variables, and X 
    approximately (i) be a set variable corresponding to X(i). Define the
    universal set OMEGA to be union i(n) = 1X approximately (i) and let 
    the sigma-field generated by {X approximately (i), i = 1,...,n}. It 
    is shown that Shannon's information measures on the random vairables 
    X(i), i = 1,...,n, constitute a unique measure mu* on F, which is 
    called the I-Measure. In other words, the Shannon information measure
    (i.e., Shannon's information measures as a whole) is a measure on F, 
    thus establishing the analogy between information theory and set 
    theory. Therefore each information theoretic operation can formally 
    be viewed as a set theoretic operation, and vice versa. This point of
    view, which we believe is of fundamental importance, has apparently 
    been overlooked in the past by information theorists. As a 
    consequence the I-Diagram is introduced, which is a geometrical 
    representation of the relationship among the information measures. 
    The J-Diagram is analogous to the Venn Diagram in set theory. The use
    of the I-Diagram is discussed; some applications of which reveal 
    results that may otherwise be difficult to discover. A formula is 
    also derived for the value of the I-Measure of the atoms of F and its
    sub-sigma-fields generated by some subsets of the basic set 
    variables.}
}

@Article{Wolf92,
  author =       {B. H. Marcus and P. H. Siegel and J. K. Wolf},
  title =        {Finite-State Modulation Codes for Data Storage},
  journal =      {IEEE Journal on Selected Areas in Communication},
  year =         {1992},
  volume =       {10},
  number =       {1},
  pages =        {5--38},
  month =        {January},
}


@unpublished{LubyDF0,
 author={M. Luby},
 year={1998},
 title={Digital fountain},
 note={Unpublished work, patents pending}
}

@inproceedings{LubyDF,
title={A Digital Fountain Approach to Reliable Distribution of Bulk Data},
url={http://www.dfountain.com/tech/techpapers/index.html},
author={John Byers and Michael Luby and Michael Mitzenmacher and Ashu Rege},
booktitle={Proceedings of ACM SIGCOMM '98, September 2--4, 1998},
annote={ACM SIGCOMM '98, September 2--4, 1998},
year={1998}
}
@inproceedings{LubyTC, 
                     title={Accessing Multiple Mirror Sites in Parallel: Using Tornado Codes to Speed Up Downloads},
url={http://www.dfountain.com/tech/techpapers/index.html},
author={John Byers and Michael Luby and Michael Mitzenmacher},
booktitle={Proceedings of IEEE INFOCOMM '99, March
                     21-25, 1999, New York},
annote={IEEE INFOCOMM '99, March
                     21-25, 1999, New York},
year={1999}
}
@book{AliceLookingGlass,
 author={Lewis Carroll},
 title={Alice's Adventures in Wonderland; and, Through the
                 Looking-glass: and what Alice Found There},
address={London},
publisher={Macmillan Children's Books},
year={1998}
}

@article{saad99,
 author={Kanter, I. and Saad, D.},
 journal={Physics Review Letters},
title={Error-correcting Codes that Nearly Saturate {S}hannon's Bound},
volume={83},
number={13},
pages={2660-2663},
 year={1999}
}


@article{schulman-zuckerman99,
author={L. J. Schulman and D. Zuckerman},
title={Asymptotically Good Codes Correcting Insertions, Deletions, and Transpositions},
journal={IEEE Trans. on Info. Theory},
volume={45},
number={7},
year={1999},
pages={2552-2557}
}
@PhdThesis{bours-phd94,
  author = 	 {P. A. H. Bours},
  title = 	 {Codes for Correcting Insertion and Deletion Errors},
  school = 	 {Eindhoven Technical University},
  year = 	 {1994},
  month =        {June},
  annote =         {Available from {\tt http://www.win.tue.nl/math/dw/pp/wsdwpb/thesis.html}},
}
@Article{Bours:1995:CPD,
  author =       "Patrick A. H. Bours",
  title =        "On the Construction of Perfect Deletion-Correcting
                 Codes using Design Theory",
  journal =      "Designs, Codes, and Cryptography",
  volume =       "6",
  number =       "1",
  pages =        "5--20",
  month =        jul,
  year =         "1995",
  coden =        "DCCREC",
  ISSN =         "0925-1022",
  mrclass =      "94B60 (05B05)",
  mrnumber =     "96c:94007",
  bibdate =      "Wed Feb 10 09:30:50 MST 1999",
  url =          "http://www.wkap.nl/oasis.htm/85445",
  acknowledgement = ack-nhfb,
  journalabr =   "Des Codes Cryptography",
}

% people give all sorts of rubbish reasons for usaccades!
% Average saccade size is about 10' of arc. (Ratliff, F., and Riggs. L.A. (1950) Involuntary motions of the eye during monocular fixation. J Exptl. Psychol 40 687-701
@article{SaccadeSize1950,
 author={Ratliff, F. and Riggs, L. A.},  
 year={1950},
 title={Involuntary motions of the eye during monocular fixation},
 journal={J. Exptl. Psychol.} ,
 volume={40},
 pages={687-701}
}

% MacKay, D. M., & MacKay, V. (1975). Dichoptic induction of McCollough-type effects. Quarterly Journal of Experimental Psychology, 27, 225-233.
%
@article{MacKayMacKay1974,
author={MacKay, D. M. and MacKay, V.},
year={1974},
title={The time course of the {McCollough} Effect and its physiological implications},
journal={J. Physiol.},
volume={237},
pages={38-39}
}

%MacKay DM, MacKay V (1975) What causes decay of pattern-contingent chromatic aftereffects? Vision Res 15:462-464



@article{McCollough1965,
title={Color adaptation of edge-detectors in the human visual system},
author={C. McCollough},
journal={Science},
volume={149},
pages={1115-1116},
year={1965}
}

@inproceedings{minkalafferty2002,
title={Expectation-Propagation for the Generative Aspect Model},
author={Thomas Minka and John Lafferty},
booktitle={Proceedings of the 18th Conference on Uncertainty in Artificial Intelligence},
pages={352-359},
year={2002}
}
@phdthesis{minkaphd,
title={A family of algorithms for approximate {B}ayesian inference},
author={Thomas Minka},
institute={MIT},
year=2001,
url={http://www.stat.cmu.edu/~minka/papers/ep/}
}

@inproceedings{minkauai,
title={Expectation Propagation for approximate {B}ayesian inference},
author={Thomas Minka},
booktitle={UAI'2001},
pages={362-369}
}

@inproceedings{dmbdynmij:lda,
  author = "David M. Blei and Andrew Y. Ng and Michael I. Jordan",
  title = "{L}atent {D}irichlet {A}llocation",
  year = 2001,
  booktitle = "Neural Information Processing Systems 14",
  url = "citeseer.nj.nec.com/article/blei02latent.html" }


% DMM
@article{MacKayMcCulloch1952,
 author={MacKay, D. M. and McCulloch, W. S.},
 year={1952},
 title={The limiting information capacity of a neuronal link},
 journal={Bull.     Math. Biophys.},
 volume={14},
 pages={127-135}
}
@phdthesis{jpwilsonthesis,
author={J. P. Wilson},
annote={Phone 01782 627 020},
year={1960},
institute={University of London}
}
@article{DMM33,
 author={MacKay, D. M.},
year={1957},
title={Moving visual images produced by regular stationary
patterns},
journal={Nature},
volume={180},
pages={849-850},
annote={First paper on ray figures and concentric circles. Includes the transparent ray on white noise result,
 and says that what is seen to rotate is the complementary image. Stroboscopic.}
}
@article{DMM33,
 author={MacKay, D. M.},
year={1957},
title={Some further visual phenomena associated with regular
patterned stimulation},
journal={Nature}, volume={180},
pages={1145-1146},
annote={Ten seconds of pattern followed by visual noise. One eye views stimulus, other views noise, get eye-eye transfer.
 Includes stabilized image using contact lens and stalk. Concentric rings; move stimulus to and fro (away). Complementary
 image is seen  to contract or expand. Regardless of
 central fixation.}
}
%#__________ (1958a).  Moving visual images produced by regular stationary patterns (II: reply to Campbell &amp; Robson).  <i>Nature</i>, <i>181</i>, 362-363.  
%#__________ (1958b).  Perceptual stability of a stroboscopically lit visual field containing self-luminous objects.  <i>Nature</i>, <i>181</i>, 507-508. 
%#__________ (1960).  Monocular 'rivalry' between stabilized and unstabilized retinal images.  <i>Nature</i>, <i>185</i>, 834.   </p><p>
% #__________ (1961).  The visual effects of non-redundant stimulation. <i>Nature</i>, <i>192</i>, 739-740. </p><p>
% #Andrews, D. P., MacKay, D. M., &amp; Wilson, J. P. (1963).  Apparent relative movement of 'unsharp' and 'sharp' visual patterns (reply to F. J. Verheijen). <i>Nature</i>, <i>199</i>, 161.   </p><p>
% #Anstis, S. M., Gregory, R. L., &amp; De M. Rudolf, N, &amp; MacKay, D. M. (1963).  Influence of stroboscopic illumination on the after-effect of seen movement.  <i>Nature</i>, <i>199</i>, 99-100.




@book{RussellNorvik,
author={Russell, S. and Norvik, P.},
year={1995},
title={Artificial Intelligence: A Modern Approach},
publisher={Prentice Hall},
address={Englewood Cliffs, NJ}
}

@article{KabaSaad99,
 author={Kabashima, Y. and Saad, D.},
title={Statistical Mechanics of Error-correcting Codes},
 year={1999},
 journal={Europhys. Lett.},
 volume={45},
 pages={97-103}
}

@article{KabaMuraSaad00a,
 author={Kabashima, Y. and Murayama, T. and Saad, D.},
title={Typical Performance of {G}allager-Type Error-Correcting Codes},
 year={2000},
 journal={Physical Review Letters},
 volume={84},number={6},
 pages={1355-1358}
}

@article{KabaMuraSaad00b,
 author={Kabashima, Y. and Murayama, T. and Saad, D.},
title={Cryptographical Properties of Ising Spin Systems},
 year={2000},
 journal={Physical Review Letters},
 volume={84},number={9},
 pages={2030-2033}
}

@unpublished{Naka00,
 author={Nakamura, K. and Kabashima, Y.  and Saad, D.},
year={2000},
 title={Statistical Mechanics of Low-Density Parity Check Error-Correcting Codes over {G}alois fields},
note={Submitted to Europhysics Letters}
}

@unpublished{IBMpc,
 author={Evangelos Eleftheriou},
 note={IBM Z\"urich Research Laboratories},
year={2000},
 title={Personal communication}
}


@phdthesis{Minka2001,
title={A family of algorithms for approximate Bayesian inference},
author={Thomas Minka},
type={PhD},
annote={PhD thesis}, 
year=2001,
school={MIT}
}

@article{Immink90,
author={K. A. S. Immink},
title={Runlength-Limited Sequences},
journal={Proc. IEEE}, volume={78}, pages={1745},
month={Nov},
year={1990}
}

@article{Immink97a,
author={K. A. S. Immink},
title={A Practical Method for Approaching the Channel Capacity of
Constrained Channels},
  journal =      {IEEE Trans. on Info. Theory},
volume={43},
pages={1389-1399}, number={5}, month={Sept}, year={1997}
} 

@article{Immink98,
author={K. A. S. Immink and  Paul Siegel and Jack Wolf},
title={Codes for Digital Recorders},
  journal =      {IEEE Trans. on Info. Theory},
volume={44}, pages={2260-2299},
month={Oct}, year={1998}
}
 
@article{Immink97b,
author={K. A. S. Immink},
title={Weakly constrained codes},
journal={Electronics Letters},
volume={33},
number={23},page={1943-1944}, month={Nov.}, year={1997}
}

@article{Immink95,
author={K. A. S. Immink},
title={Constructions of Almost Block-Decodable Runlength-Limited Codes},
journal={IEEE Trans. on Info. Theory},
Volume={ 41}, Number= 1,month={January}, year={ 1995}
}

@article{DengHerro,
author={R. H. Deng and M. A. Herro},
title={{DC}-free coset codes},
journal={IEEE Trans. Inf. Th.}, volume={34},
year={1988},
pages={786-792}
}

@article{Makarian,
author={G. S. Markarian and Naderi, M. and Honary, B. and Popplewell, A. and O'Reilly, J. J.},
title={Maximum likelihood decoding of {RLL-FEC} array codes on partial response channels},
journal={Electronics Letters},
year={1993},
volume={29}, number={16}, pages={1406-1408}
}

@article{Zigangirov1969,
 author={Zigangirov, K. Sh.},
 title={Sequential Decoding for a Binary Channel with Drop-outs and Insertions},
 journal={Problemy Peredachi Informatsii},
volume={5},
number={2},
pages={23-30},
year={1969}
}

@article{Dobrushin1967,
 author={Dobrushin, R. L.},
 year={1967},
 title={Shannon's theorem for Channels with Synchronization Errors},
 journal={Problemy Peredachi Informatsii},
volume={3},
number={4},
pages={18-36},
annote={ref 1 in Zigangirov1969}
}
@unpublished{Pinsker1965,
 author={M. S. Pinsker},
 title={Capacity of Channels with Synchronization Errors},
note={Report at the Second Conference on the Theory of Coding and its Applications,
         Baku},
year={1965},
annote={ref 2 in Zigangirov1969}
}
@article{Dobrushin1968,
 author={Vvedenskaya, N. D., and Dobrushin, R. L.},
 year={1968},
 title={The Computations on a Computer of the Channel Capacity of a Line with Symbol Drop-out},
 journal={Problemy Peredachi Informatsii},
volume={4},
number={3},
pages={92-95},
annote={ref 3 in Zigangirov1969}
}




@Book{Wozencraft1965,
  author =	 {Wozencraft, J. M. and Jacobs, I. M.},
  year=1965,
  title = 	 {Principles of Communication Engineering},
  publisher = 	 {Wiley},
  address =	 {New York},
 annote={ref 4 in Zigangirov1969; [Univ. Lib.] 431.c.96.413
                 South Front, Floor 6}
}

@article{Zigangirov1966,
 author={Zigangirov, K. Sh.},
 title={Some Sequential Decoding Procedures},
 journal={Problemy Peredachi Informatsii},
volume={2},
number={4},
pages={13-25},
year={1966},
annote={ref 5 in Zigangirov1969}
}

@Book{Gallager68,
  author = 	 "Gallager, R. G.",
  title = 	 "Information Theory and Reliable Communication",
  publisher = 	 "Wiley",
  year = 	 1968,
  address =	 "New York"
}
% South Front 6
% [Univ. Lib.] 431.c.96.694

@Article{Gallager68b,
  author = 	 "Gallager, R. G.",
  title = 	 "Sequential Decoding for Binary Channels with Noise and Synchronization Errors",
 note={unpublished Lincoln Lab report 25 G-2},
 year={1961},
  annote =	 "ref 6 in ZIGANGIROV1969.
 The paper you mention was actually 1961 and was a group report
for MIT Lincoln Laboratories.  You could probably get it from
the US Air Force, but I am asking my secretary to simply make
a copy of my copy and send it to you.  It is a has few handwritten
comments on it by someone who read it (name lost in time), I
don't know how it ought to be referred to, probably just as
an unpublished Lincoln Lab report."
}

@Book{Wozencraft1965,
  author =	 {Wozencraft, J. M. and Reiffen, B.},
  year=1963,
  title = 	 {Sequential Decoding},
note={Russian translation -- need to find English reference},
 annote={ref 7 in Zigangirov1969}
}


@article{Zigangirov1968,
 author={Zigangirov, K. Sh.},
 title={Sequential Decoding Procedures with Error Probability Exponent Given by Random Coding},
 journal={Problemy Peredachi Informatsii},
volume={4},
number={2},
pages={83-85},
year={1968},
annote={ref 8 in Zigangirov1969}
}

% moved to http://lids.mit.edu/~sychung
% http://lids.mit.edu/~sychung/gaopt.html
% http://lids.mit.edu/~sychung/gath.html
@unpublished{ChungAppletb,
year={1999},
 author={Chung, Sae-Young and  Urbanke,  R\"udiger L. and  Richardson, Thomas J.},
 title={{LDPC} code design applet},
 note={{\tt http://lids.mit.edu/\verb+~+sychung/gath.html}},
annote={This one finds the threshold only}
}
@unpublished{ChungApplet,
year={1999},
author={Chung, Sae-Young and  Urbanke,  R\"udiger L. and  Richardson, Thomas J.},
 title={{LDPC} code design applet},
 note={{\tt http://lids.mit.edu/\verb+~+sychung/gaopt.html}},
annote={This one optimizes}
}
@misc{UrbankeApplet,
title={{LdpcOpt} -- a fast and accurate degree distribution optimizer for {LDPC} code ensembles},
author={R. Urbanke},
url={http://lthcwww.epfl.ch/research/ldpcopt/},
year={2001},
note={{\tt{http://lthcwww.epfl.ch/research/ldpcopt/}}}
}

% forney
@ARTICLE{Turin97a,
        author      = {Turin, L.},
        title       = {Sensational subjects},
        journal     = {Chem. Ind.},
        year        = {1997},
        volume      = {},
        pages       = {924-+},
        abstract    = {}
}

@ARTICLE{Turin97b,
        author      = {Turin, L.},
        title       = {The nose as spectroscopist},
        journal     = {Chem. Ind.},
        year        = {1997},
        volume      = {},
        pages       = {866-870},
        abstract    = {}
}

@ARTICLE{Turin96,
        author      = {Turin, L.},
        title       = {A spectroscopic mechanism for primary olfactory
          reception},
        journal     = {Chem. Senses},
        year        = {1996},
        volume      = {21},
        pages       = {773-791},
        abstract    = {}
}

%  (John Edensor), 1885-1977
@book{Littlewood1986,
 Author={         Littlewood, J. E.},
annote={         Originally published as: 'A mathematician's miscellany',
                 1953; 
 UL:  348:6.c.95.124                 South Front, Floor 4;
page 186-188 is of interest to me},
 Title={          Littlewood's miscellany},
editor={B\'ela Bollob\'as},
address={                 Cambridge},
publisher={ Cambridge University Press},
year={1986}
}
@incollection{Littlewood1952,
title={ On the problem of $n$ bodies},
 Author={         Littlewood, J. E.},
 booktitle={Communications du s\'eminaire math\'ematique de l'Universit\'e
 de Lund, tome supplementaire, d\'edi\'e \`a Marcel Riesz },
year={1952},
pages={143-151}
}


@book{Bentley2,
author={Jon Bentley},
edition={second},
title={Programming Pearls},
publisher={Addison-Wesley},
address={Reading, Massachusetts},
year={2000},
}
@misc{ dietterich91error-correcting,
    author = "T. Dietterich and G. Bakiri",
    title = "Error-correcting output codes: A general method for improving multiclass
      inductive learning programs",
 note={In Proceedings
      of the Ninth National Conference on Artificial Intelligence (AAAI-91), pages
      572--577. AAAI Press, 1991.},
    text = "T. G. Dietterich and G. Bakiri. Error-correcting output codes: A general
      method for improving multiclass inductive learning programs. In Proceedings
      of the Ninth National Conference on Artificial Intelligence (AAAI-91), pages
      572--577. AAAI Press, 1991.",
    year = "1991"
}
@misc{ dietterich95solving,
    author = "T. Dietterich and G. Bakiri",
    title = "Solving multiclass learning problems via error-correcting output codes",
    text = "Thomas G. Dietterich and Ghulum Bakiri. Solving multiclass learning problems
      via error-correcting output codes. Journal of Artificial Intelligence Research,
      2:263--286, January 1995.",
    year = "1995"
}

@book{zurek,
title={Complexity, Entropy and the Physics of Information},
editor={Wojciech H. Zurek},
series={SFI Studies in the  Sciences of Complexity},
year={1990},
publisher={Addison Wesley Longman},
annote={0-201-51506-7 www.santafe.edu/sfi/publications/Bookinforev/cepinew.html}
}
@article{besag77some,
    author = "J. Besag",
    title = "Some methods of statistical analysis for spatial data",
    journal = "Bull.\  Intern.\  Statist.\ Inst.",
    volume = "47(2)",
    pages = "77-92",
    year = "1977"
}
@techreport{YFW2000,
 author={J. S. Yedidia and W. T. Freeman and Y. Weiss},
 title={Generalized Belief Propagation},
 institution={Mitsubishi Electric Research Laboratories},
 note={TR-2000-26},
 year={2000}
}

% posets:

@techreport{YFW2002,
 author={J. S. Yedidia and W. T. Freeman and Y. Weiss},
 title={Constructing Free Energy Approximations and Generalized Belief Propagation
               Algorithms},
 institution={Mitsubishi Electric Research Laboratories},
 note={TR-2002-35},
 year={2002},
annote={
 The paper describes a new graphical notation ("region graphs") for
expressing propagation algorithms, which generalizes junction trees.  This is contrast
to factor graphs, which are good at expressing a distribution, but not propagation
algorithms.  Because they include both exact and approximate inference, I (TM) think region  
graphs are currently the best method for expressing propagation algorithms.
}
}
@techreport{YFW2001short,
 author={J. S. Yedidia and W. T. Freeman and Y. Weiss},
 title={Characterization of belief propagation and its
 generalizations},
 institution={Mitsubishi Electric Research Laboratories},
 note={TR-2001-15},
 year={2000}
}
@techreport{YFW2001long,
 author={J. S. Yedidia and W. T. Freeman and Y. Weiss},
 title={{B}ethe
Free Energy, {K}ikuchi Approximations and Belief Propagation Algorithms},
 institution={Mitsubishi Electric Research Laboratories},
 note={TR-2001-16},
 year={2000}
}
@techreport{Yedidia2000,
 author={J. S. Yedidia},
 title={An Idiosyncratic Journey Beyond Mean Field Theory},
 institution={Mitsubishi Electric Research Laboratories},
 note={TR-2000-27},
 year={2000}
}

@techreport{SmolaBartlett,
author={A.  Smola and P. Bartlett},
title={Sparse Greedy Gaussian Process Regression},
institution={Australian National University},
year={2000},
note={NIPS 13}
}
% was Welling2001,
@INPROCEEDINGS{Welling143.UAI-2001,
  AUTHOR	= "Welling, Max and Teh, Yee Whye",
  TITLE		= "Belief Optimization for Binary Networks: A Stable Alternative to Loopy Belief Propagation",
  BOOKTITLE	= "Uncertainty in Artificial Intelligence: Proceedings of the Seventeenth Conference (UAI-2001)",
  PUBLISHER	= "Morgan Kaufmann",
  ADDRESS	= "San Francisco, CA",
  YEAR		= "2001",
  PAGES		= "554-561"
}
@proceedings{DBLP:conf/uai/2001,
  editor    = {Jack S. Breese and
               Daphne Koller},
  title     = {UAI '01: Proceedings of the 17th Conference in Uncertainty in
               Artificial Intelligence, University of Washington, Seattle, Washington,
               USA, August 2-5, 2001},
  booktitle = {UAI},
  publisher = {Morgan Kaufmann},
  year      = {2001},
  isbn      = {1-55860-800-1},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{Yuille2001,
author = "A. L. Yuille",
title = "A Double-Loop Algorithm to Minimize the {B}ethe and {K}ikuchi Free
Energies",
year = 2001,
editor={M. Figueiredo and J. Zerubia and A.K. Jain},
booktitle={Energy Minimization Methods in Computer Vision and Pattern Recognition.
 Proceedings Third International Workshop, Sophia Antipolis France, September 3-5, 2001},
publisher={Springer},
annote={EMMCVPR 2001},
series={LNCS},
number = 	 {2134},
pages={3-18}
}


@article{ fisher43relation,
    author = "R. Fisher and A. Corbet and C. Williams",
    title = "The relation between the number of species and the number of individuals
      in a random sample of an animal population",
    annote = "Fisher, R.A., Corbet, A.S., and Williams, C.B. 1943. The relation between
      the number of species and the number of individuals in a random sample of
      an animal population. Journal of Animal Ecology 12, 42-58.",
journal={ Journal of Animal Ecology},
volume={12},
pages={42-58},
    year = "1943"
}
@Book{Schneier96,
  author =	 {B. Schneier},
  title = 	 {Applied Cryptography},
  publisher = 	 {Wiley},
  year = 	 1996,
  address =	 {New York}
}


@book{Layzer84,
author={David Layzer},
title={Constructing the Universe},
publisher={Scientific American Library},
year={1984}
}
@book{Gingerich92,
title={ The Great Copernicus Chase : And Other Adventures in Astronomical History},
author={ Owen Gingerich },
publisher={Cambridge University Press },
year={ 1992}
}

@book{Gingerich93,
author={ Owen Gingerich },
title={The Eye of Heaven : Ptolemy, Copernicus, Kepler (Masters of Modern Physics)},
publisher={ American Institute of Physics  },
year={ 1993}
}

%  author={C. J. Colbourn and J. H. Dinitz (editors)},

@book{Designs,
 editor={C. J. Colbourn and J. H. Dinitz},
title={The {CRC} Handbook of Combinatorial Designs},
 publisher={CRC Press},
 address={New York},
 year=1996
}


@inproceedings{RosenthalVontobel,
author={Joachim Rosenthal and Pascal O. Vontobel},
title={Constructions of {LDPC} codes using {R}amanujan graphs and ideas from {M}argulis}, 
URL={See http://www.nd.edu/~rosen/preprints.html},
conference={38th Annual Allerton Conference on Communication, Control, and Computing, 2000}, 
booktitle={Proceedings of the 38th Annual Allerton Conference on Communication, Control, and Computing},
pages={248-257},
year=2000 
}
% girth properties of gallager
@InProceedings{mao01,
  author =       {Yongyi Mao and Amir Banihashemi},
  title =        {A Heuristic Search for Good {LDPC} Codes at Short Block Lengths},
  booktitle =    {IEEE International Conference on Communications},
  OPTpages =     {},
  year =         {2001},
  OPTeditor =    {},
  month =        {June},
}
@InProceedings{mao00,
  author =       {Yongyi Mao and Amir Banihashemi},
  title =        {Design of Good {LDPC} Codes Using Girth Distribution},
booktitle={IEEE International Symposium on Info. Theory, Italy, June, 2000},
 conference={IEEE International Symposium on Info. Theory, Italy, June, 2000},
  year =         {2000},
  OPTeditor =    {},
  month =        {June},
}


%Dr. Amir H. Banihashemi
% Y. Mao and A. H. Banihashemi, "Design of Good LDPC Codes Using Girth Distribution", presented (by A. Banihashemi. People knowing me will realize that those slides are not my style) at IEEE International Symposium on Info. Theory, Italy, June, 2000

@book{babel,
author="Jorge Luis Borges",
title="The {L}ibrary of {B}abel",
publisher="David R. Godine, Inc.",
address={Boston, Massachusetts},
year="1941", ISBN={ 156792123X},
translator={Andrew Hurley}
}
% ,illustrator={Erik Desmazieres}
% Borges wrote ?La Biblioteca de Babel? in 1941, and it was published the same year in a collection of stories entitled ?El jard?n de senderos que bifurcan? (?The Garden of Forking Paths?). 

@misc{dasher164,
title={Dasher version 1.6.4},
author={David J. Ward},
note={Dasher version 1.6.4, available from
\verb+www.inference.phy.cam.ac.uk/dasher/+, (2001)},
annoteyear={2001}
}

@phdthesis{teahan97modelling,
  author = "W. Teahan",
  title = "Modelling {E}nglish {T}ext",
type={PhD},
  school="Univ. of Waikato, N.Z.",
  year = "1997" }

% Valiant's "PAC learning"
% http://yoda.cis.temple.edu:8080/UGAIWWW/lectures95/learn/pac/pac.html
% Valiant, L .G.: A Theory of the Learnable, CACM, 27(11):1134-1142,1984

@Article{valiant1984,
  author = 	 "L. G. Valiant",
  title = 	 "A theory of the Learnable",
  journal = 	 "Communications of the ACM",
  year = 	 "1984",
  volume=27,
 number=11,
  pages = 	 "1134-1142"
}



% PPMD5 reference modified for nature idiots
@inproceedings{Teahan95a,
 AUTHOR         ="Teahan, W. J.",
 TITLE          ="Probability estimation for {PPM}",
 booktitle={Proceedings {NZCSRSC}'95},
 note={Available from {\tt{http://citeseer.nj.nec.com/teahan95probability.html}}},
 annote={Available from \verb+http://www.cs.waikato.ac.nz/~wjt/+%
\verb+papers/NZCSRSC.ps.gz+},   
year="1995",
}
%  Theres a copy of the paper in /home/djw30/papers/NZCSRSC.ps
% 


@misc{teahan95probability,
  author = "W. J. Teahan",
  title = "Probability estimation for {PPM}",
  note = "Probability estimation for {PPM}. In {\em Proc. of the N.Z. Comp.
    Sci. Research Students' Conf.,} available from
 \verb+citeseer.nj.nec.com/teahan95probability.html+ (1995).",
annote="Univ. of Waikato, Hamilton, New Zealand.",
  year = "1995",
  url = "citeseer.nj.nec.com/teahan95probability.html" }

@inproceedings{moffat95,
    author = "A. Moffat and R. M. Neal and I. H. Witten",
    title = "Arithmetic Coding Revisited",
    booktitle="Proceedings of the Data Compression Conference 1995",
publisher="IEEE Computer Society Press",
editor="J. A. Storer and M. Cohn",
address="Los Alamitos: CA",
     pages = "202-111",
    year = "1995"
}
@article{ moffat90,
    author = "A. Moffat",
    title = "Implementing the {PPM} Data Compression Scheme",
    journal = "IEEE Trans. on Communications",
    volume = "38",
    year = "1990",
 pages={1917-1921}
}


@inproceedings{zoubincarlBMC,
 author={C. E. Rasmussen and Z. Ghahramani},
 title={{B}ayesian {M}onte {C}arlo},
 year=2003,
 booktitle={Advances in Neural Information Processing Systems XV},
 conference={NIPS 2002},
 editor={Suzanna Becker and Sebastian Thrun and Klaus Obermayer}
}
@INPROCEEDINGS{Chu01a,
  author =       {Chu, Wei and Keerthi, S. Sathiya and Ong, Chong Jin},
  title =        {A unified loss function in {B}ayesian 
 framework for support vector regression},
  booktitle =    {Proceedings of the 18th International Conference on Machine Learning},
  year =         {2001},
  pages =        {51-58},
  url =   {http://guppy.mpe.nus.edu.sg/\verb+~+mpessk/svm/icml.pdf}
}

@INPROCEEDINGS{Chu02b,
  author =       {Chu, Wei and Keerthi, S. S. and Ong, C. J.},
  title =        {A new {B}ayesian design method for support 
vector classification},
  booktitle =    {Special Section on Support Vector Machines of the 
9th International Conference on Neural Information Processing},
  year =         {2002},
  url =          {http://guppy.mpe.nus.edu.sg/\verb+~+chuwei/paper/btsvc_iconip.pdf},
}

@ARTICLE{Chu02c,
  author =       {Chu, Wei and Keerthi, S. Sathiya and Ong, Chong 
Jin},
  title =        {{B}ayesian trigonometric support vector 
classifier},
  journal =      {Neural Computation},
  year =         {2003},
  pages =        {},
  url =          {http://guppy.mpe.nus.edu.sg/\verb+~+mpessk/btsvc/btsvc.ps.gz},
}

@ARTICLE{Chu02d,
  author =       {Chu, Wei and Keerthi, S. Sathiya and Ong, Chong 
Jin},
  title =        {{B}ayesian support vector regression using a unified loss function},
  journal =      {IEEE Trans. on Neural Networks},
  year =         {2003},
note={Submitted},
  pages =        {},
  url = {http://guppy.mpe.nus.edu.sg/\verb+~+mpessk/papers/bisvr.pdf},
}
% the above are references for "doing support vectors in a Bayesian way"
% good stuff Sat 5/10/02

%approximate gaussian technique
@Unpublished{brink02,
  author =       {ten Brink, Stephan and Gerhard Kramer and Alexei Ashikhmin},
  title =        {Design of Low-Density Parity-Check Codes for
Multi-Antenna Modulation and Detection},
  note =         {Submitted to {\em IEEE Trans.\ on Communications}},
  month =        {June},
  year =         {2002},
}

%not looked at yet -- original EXIT chart paper?
@Article{brink99,
  author =       {ten Brink, Stephan},
  title =        {Convergence of Iterative Decoding},
  journal =      {Electronics Letters},
  year =         {1999},
  volume =       {35},
  number =       {10},
  pages =        {806-808},
  month =        {May},
}

% decoding by tanh and look at all dual codewords
%  The expression as a sum over dual codewords is a special case of a very
%general group-theoretic result that is derived in the final section of my
%GSR paper, which I hope you have.  It results from an application of the
%Poisson summation formula.  Other references are Hartmann and Rudolph, IT,
%Sept. 1976;  Battail et al., IT, May 1979;  Hagenauer et al., IT, March
%1996;  Riedel, JSAC, Feb 1998.

% "in [2] We point out that it is merely based on the Poisson summation formula. "

@article{hartmann1976,
author={C. R. P. Hartmann and L. D. Rudolph},
title="An optimum symbol by symbol decoding rule for linear codes",
  journal =      {IEEE Trans. on Info. Theory},
volume={IT-22}, pages={514-517},
month={Sept.},
year={1976},
annote={C. R. P. Hartmann and L. D. Rudolph, "An optimum symbol by symbol decoding rule for linear codes," IEEE Trans. Inform. Theory, Vol. IT-22, pp. 514-517, Sept. 1976.}
}

@book{Terras99,
title={Fourier Analysis on Finite Groups and Applications},
publisher={Cambridge University Press},
address={Cambridge, U.K.},
year={1999},
author={Terras, Audrey},
annote={http://math.ucsd.edu/~aterras/
 http://books.cambridge.org/0521457181.htm
}
}

@inproceedings{Offer2001,
title={{LDPC} codes: a group algebra formulation},
author={E. Offer and E. Soljanin},
booktitle={Proc. Internat. Workshop on Coding and Cryptography WCC 2001, 8-12 Jan. 2001, Paris},
year=2001}

%    *   An algebraic description of iterative decoding schemes (E. Offer and E. Soljanin)
%Codes, Systems and Graphical Models, Volumes in Mathematics and its Applications, Springer Verlag New York, Eds. B. Marcus, J. Rosenthal,  Dec. 2000. 

@InCollection{Offer2000,
 AUTHOR		="E. Offer and E. Soljanin",
 title={ An algebraic description of iterative decoding schemes },
  booktitle = 	 {Codes, Systems and Graphical Models},
volume={123},
  series =	 {IMA Volumes in Mathematics and its Applications},
  publisher =	 {Springer},
  year =	 2000,
  editor =	 {B. Marcus and J. Rosenthal},
  address =	 {New York},
 pages={283-298}
}

% {forneyGSR,
% author={G.D. Forney, Jr.},
% title={Codes on Graphs: Generalized State Realizations},
%note={preprint, 1999}
%} % this ended up being published as
%% G. D. Forney, Jr., "Codes on graphs:  Normal realizations," IEEE Trans.
%% Inform. Theory,  vol. 47, pp. 520-548, Feb. 2001.



@article{goodhillsimmenwillshaw94,
 annote={Goodhill, G J, Simmen, M W & Willshaw, D J (1994). An evaluation of the use of multidimensional scaling for understanding brain connectivity. Phil Trans Roy Soc B, 348, 265-280.},
author={Goodhill, G. J. and Simmen, M. W. and Willshaw, D. J.},
year={1994},
title={An evaluation of the use of multidimensional scaling for understanding brain connectivity},
journal={Phil. Trans. Roy. Soc. B},
volume={348},
pages={265-280}
}
@article{NCRG/96/015,
    title = {GTM: The Generative Topographic Mapping},
    journal   = {Neural Computation},
    volume    = {10},
    number    = {1},
    year      = {1998},
    pages     = {215--235},
    author = {Christopher M. Bishop and Markus Svens\'{e}n and Christopher K. I. Williams},
    abstract = {Latent variable models represent the probability density
        of data in a space of several dimensions in terms of a smaller
        number of latent, or hidden, variables. A familiar example is
        factor analysis which is based on a linear transformations between
        the latent space and the data space. In this paper we introduce a
        form of non-linear latent variable model called the Generative
        Topographic Mapping, for which the parameters of the model can be
        determined using the EM algorithm. GTM provides a principled
        alternative to the widely used Self-Organizing Map (SOM) of
        Kohonen (1982), and overcomes most of the significant limitations
        of the SOM. We demonstrate the performance of the GTM algorithm on
        a toy problem and on simulated data from flow diagnostics for a
        multi-phase oil pipeline.},
    trnumber = {NCRG/96/015}
}

% Digital fountain codes
% see also bibs/luby.bbl

@article{byers2002,
URL={ http://www.digitalfountain.com/technology/researchLibrary/index.cfm },
title={A Digital Fountain Approach to Asynchronous Reliable Multicast
},
Author={John W. Byers and Michael Luby and Michael Mitzenmacher
},
Abstract={The proliferation of applications that must reliably distribute large, rich content to a vast number of autonomous receivers motivates the design of new multicast and broadcast protocols. We describe an ideal, fully scalable protocol for these applications that we call a digital fountain. A digital fountain allows any number of heterogeneous receivers to acquire content with optimal efficiency at times of their choosing. Moreover, no feedback channels are needed to ensure reliable delivery, even in the face of high loss rates.

We develop a protocol that closely approximates a digital fountain using two new classes of erasure codes that for large block sizes are orders of magnitude faster than standard erasure codes. We provide performance measurements that demonstrate the feasibility of our approach and discuss the design, implementation, and performance of an experimental system.
},
annote={IEEE Journal on Selected Areas in Communications, vol. 20, no. 8, pp. 1528-1540, October 2002.}
}


@inproceedings{luby2002,
year={2002},
title={{LT} Codes},
Author={Michael Luby},
Abstract={We introduce LT codes, the first rateless erasure codes that are very efficient as the data length grows.},
URL={ http://www.digitalfountain.com/technology/researchLibrary/index.cfm },
booktitle={ Proceedings of The 43rd Annual IEEE Symposium on Foundations of Computer Science,
 November 16--19 2002},
pages={271-282}
}

@TechReport{wainwright2003old,
author={M. J. Wainwright and T. Jaakkola and A. S. Willsky},
title={Tree-based reparameterization framework for analysis of sum-product and related algorithms},
institution={Laboratory for Information and Decision Systems, MIT},
number={P-2510},
 address={},
year={2002},
url={http://www.cs.berkeley.edu/~martinw/},
annote={M. J. Wainwright, T. Jaakkola and A. S. Willsky.  Tree-based reparameterization framework for analysis of sum-product and related algorithms.  LIDS Technical Report P-2510; Laboratory for Information and Decision Systems, MIT;   IEEE Transactions on Information Theory, 45(9): pages 1120--1146. }
}
@article{wainwright2003,
author={M. J. Wainwright and T. Jaakkola and A. S. Willsky},
title={Tree-based reparameterization framework for analysis of sum-product and related algorithms},
year={2003},
journal={IEEE Transactions on Information Theory},
volume=45,
number=9,
pages={1120-1146}, 
annote={M. J. Wainwright, T. Jaakkola and A. S. Willsky.  Tree-based reparameterization framework for analysis of sum-product and related algorithms.  LIDS Technical Report P-2510; Laboratory for Information and Decision Systems, MIT;   IEEE Transactions on Information Theory, 45(9): pages 1120--1146. }
}
@Article{Scholtz82,
  author = 	 {Scholtz, R. A.},
  title = 	 {The Origins of Spread-Spectrum Communications},
  journal = 	 {IEEE Trans. on Communications},
  year = 	 1982,
  volume =	 30,
  number =	 5,
  pages =	 {822-854},
  month =	 {May}
}

\hyphenation{Spring-er}



@inproceedings{Winn:StructuredVIBES2003,
  author    = "C. M. Bishop and J. M. Winn",
  title     = "Structured variational distributions in {VIBES}",
  year      = 2003,
  booktitle = nips,
  abstract = "Variational methods are becoming increasingly popular
     for the approximate solution of complex probabilistic models in
     machine learning, computer vision, information retrieval and many
     other fields. Unfortunately, for every new application it is necessary
     first to derive the specific forms of the variational update equations
     for the particular probabilistic model being used, and then to implement
     these equations in application-specific software. Each of these steps is
     both time consuming and error prone. We have therefore recently developed
    a general purpose inference engine called VIBES (`Variational Inference for
    Bayesian Networks') which allows a wide variety of probabilistic models to
     be implemented and solved variationally without recourse to coding. New
    models are specified as a directed acyclic graph using an interface analogous
   to a drawing package, and VIBES then automatically generates and solves the
  variational equations. The original version of VIBES assumed a fully factorized
   variational posterior distribution. In this paper we present an extension of
  VIBES in which the variational posterior distribution corresponds to a
  sub-graph of the full probabilistic model. Such structured distributions can
  produce much closer approximations to the true posterior distribution. We
  illustrate this approach using an example based on Bayesian hidden Markov models."
}

@inproceedings{Winn:VIBES2002,
  author    = "C. M. Bishop and J. M. Winn and D. Spiegelhalter",
  title     = "{VIBES}: A variational inference engine for {B}ayesian networks",
  year      = 2002,
 booktitle={Advances in Neural Information Processing Systems XV},
 editor={Suzanna Becker and Sebastian Thrun and Klaus Obermayer},
  abstract = "In recent years several techniques have been proposed for modelling
    the low-dimensional manifolds, or `subspaces', of natural images. Examples
    include principal component analysis (as used for instance in `eigen-faces'),
     independent component analysis, and auto-encoder neural networks. Such
     methods suffer from a number of restrictions such as the limitation to
    linear manifolds or the absence of a probabilistic representation. In this
    paper we exploit recent developments in the fields of variational inference
    and latent variable models to develop a novel and tractable probabilistic
    approach to modelling manifolds which can handle complex non-linearities.
    Our framework comprises a mixture of sub-space components in which both the
    number of components and the effective dimensionality of the sub-spaces are
    determined automatically as part of the Bayesian inference procedure. We
    illustrate our approach using two classical problems: modelling the manifold
    of face images and modelling the manifolds of hand-written digits."
}

@inproceedings{Winn:ImageModelling2000,
  author    = "C. M. Bishop and J. M. Winn",
  title     = "Non-linear {B}ayesian image modelling",
  year      = 2000,
  booktitle = "Proceedings Sixth European Conference on Computer Vision",
  volume    = 1,
  pages     = "3-17",
  publisher = {Springer},
  abstract = "In recent years variational methods have become a popular tool
   for approximate inference and learning in a wide variety of probabilistic models.
  For each new application, however, it is currently necessary first to derive
  the variational update equations, and then to implement them in
  application-specific code. Each of these steps is both time consuming and
  error prone. In this paper we describe a general purpose inference engine
  called VIBES (`Variational Inference for Bayesian Networks') which allows a
  wide variety of probabilistic models to be implemented and solved variationally
  without recourse to coding. New models are specified either through a simple
  script or via a graphical interface analogous to a drawing package. VIBES then
  automatically generates and solves the variational equations. We illustrate
  the power and flexibility of VIBES using examples from Bayesian mixture
  modelling."
}
@misc{grassl2003,
year={2003},
author={Grassl, Markus},
title={Table of Quantum Error-Correcting Codes},
url={http://avalon.ira.uka.de/home/grassl/QECC/},
note={{\tt{http://avalon.ira.uka.de/home/grassl/QECC/}}}
}

% donated by CKIW ........
@phdthesis{adams-01,
  author        = "Adams, N. J.",
  title         = {{Dynamic Trees: A Hierarchical Probabilistic Approach
to Image Modelling}},
type={PhD},
  year          = "2001",
  school        = {Division of Informatics, University of Edinburgh, UK}
}

unpublished{adams-storkey-ghahramani-williams-99,
   author    = {Adams, N. J. and Storkey, A. and Ghahramani, Z. and
Williams, C. K. I.},
   title     = {{MFDTs: Mean Field Dynamic Trees}},
   year      = {1999},
   note      = {Submitted to ICPR 2000}
}

@inproceedings{adams-storkey-ghahramani-williams-00,
   author    = {Adams, N. J. and Storkey, A. and Ghahramani, Z. and
Williams, C. K. I.},
   title     = {{MFDTs: Mean Field Dynamic Trees}},
   booktitle = {Proceedings of 15th International Conference on Pattern Recognition},
   year      = {2000}
}

@inproceedings{adams-williams-99,
   author    = {Adams, N. J. and Williams, C. K. I.},
   title     = {{SDTs: Sparse Dynamic Trees}},
   booktitle = {Proc. ICANN'99},
   year      = {1999},
   note      = {To appear},
   publisher = {IEE}
}

@misc{adams-williams-01a,
   author    = {Adams, N. J. and Williams, C. K. I.},
   title     = {{Dynamic Trees for Image Modelling}},
   year      = {2001},
   note      = {Submitted to \emph{Image and Vision Computing}.}
}


@misc{adams-williams-01b,
   author    = {Adams, N. J. and Williams, C. K. I.},
   title     = {{Dynamic Trees: Learning to Model Outdoor Scenes}},
   year      = {2001},
   note      = {Submitted to \emph{European Conference on Computer Vision ECCV 2002}}
}

@inproceedings{adams-williams-02,
   author    = {Adams, N. J. and Williams, C. K. I.},
   title     = {{Dynamic Trees: Learning to Model Outdoor Scenes}},
   booktitle = {{Proceedings of the Seventh European Conferrence 
on Computer Vision, ECCV 2002}},
   publisher = {Springer},
   editor    = {Heyden, A. and Sparr, G. and Nielsen, M. and Johansen, P.},
   pages     = {IV 82-96},
   note      = {Lecture Notes in Computer Science 2353},
   year      = {2002}
}

@article{aizerman-braverman-rozoner-64,
   author    = {Aizerman, M. A. and Braverman, E. M. and Rozoner, L. I.},
   title     = {{Theoretical foundations of the potential function method
                 in pattern recognition learning}},
   journal   = {Automation and Remote Control},
   year      = {1964},
   volume    = {25},
   pages     = {821-837}
}

@article{ambros-ingerson-granger-lynch-90,
   author    = {Ambros-Ingerson, J. and Granger, R. and Lynch, G.},
   title     = {{Simulation of Paleocortex Performs Hierarchical Clustering}},
   journal   = {Science},
   year      = {1990},
   volume    = {247},
   pages     = {1344-1348}
}

@article{amodei-benbourhim-91,
   author    = {Amodei, L. and Benbourhim, M. N.},
   title     = {{A vector spline approximation}},
   journal   = {J. Approximation Theory},
   year      = {1991},
   volume    = {67},
   pages     = {51-79}
}


@article{anderson-63,
   author    = {Anderson, T. W.},
   title     = {{Asymptotic Theory for Principal Component Analysis}},
   journal   = {Annals of Mathematical Statistics},
   year      = {1963},
   volume    = {34(1)},
   pages     = {122-148}
}


@article{ayache-faugeras-86,
   author    = {Ayache, N. and Faugeras, O. D.},
   title     = {{HYPER: A new approach for the recognition and positioning 
       of two-dimensional objects}},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1986},
   volume    = {8(1)},
   pages     = {44-54}
}


@article{bajcsy-83,
   author    = {Bajcsy, R. and Lieberson, R. and Reivich, M.},
   title     = {A computerized system for the elastic matching of
       deformed radiographic images to idealized atlas images},
   journal   = {Journal of Computer Assisted Tomography},
   year      = {1983},
   volume    = {7(4)},
   pages     = {618-625}
}

@book{baker-77,
   author    = {Baker, C. T. H.},
   title     = {{The numerical treatment of integral equations}},
   year      = {1977},
   publisher = {Clarendon Press},
   address   = {Oxford}
}




@book{ballard-brown-82,
   author    = {Ballard, D. H. and Brown, C.},
   title     = {{Computer Vision}},
   year      = {1982},
   publisher = {Prentice-Hall}
}



@inproceedings{barber-williams-97,		  
   author    = {Barber, D. and Williams, C. K. I},
   title     = {{Gaussian Processes for Bayesian Classification via
               Hybrid Monte Carlo}},
   booktitle = {Advances in Neural Information Processing Systems 9},
   editor    = {Mozer, M. C. and Jordan, M. I. and Petsche, T.},
   publisher = {MIT Press},
   year      = {1997},
}

@article{barlow-89,
   author    = {Barlow, H.},
   title     = {{Unsupervised Learning}},
   journal   = {Neural Computation},
   year      = {1989},
   volume    = {1},
   pages     = {295-311}
}


@article{basseville-benveniste-chou-golden-nikoukhah-willsky-92,
   author    = {Basseville, M. and Benveniste, A. and Chou, K. C. and
Golden, S. A. and Nikoukhah, R. and Willsky, A. S.},
   title     = {{Modelling and estimation of multiresolution stochastic 
processes}},
   journal   = {IEEE Trans. on Info. Theory},
   year      = {1992},
   volume    = {38},
   pages     = {766-784}
}

@incollection{baumberg-hogg-94,
   author    = {Baumberg, A. and Hogg, D.},
   title     = {An efficient method for contour tracking using active shape models},
   booktitle = {{IEEE Workshop on Motion of Non-rigid and Articulated Objects}},
   year      = {1994},
   publisher = {IEEE Press},
   pages     = {194-199}
}

@inproceedings{beis-lowe-93,
   author    = {Beis, J. S. and Lowe, D. G.},
   title     = {{Learning Indexing Functions for 3-D Model-Based Object
       Recognition}},
   booktitle = {AAAI Fall 1993 Symposium on Machine
       Learning in Computer Vision},
   year      = {1993},
   pages     = {50-54},
   note      = {Proceedings available as AAAI Tech Report FSS-93-04}
}


@article{bennett-hoffman-prakash-93,
   author    = {Bennett, B. M. and Hoffman, D. D. and Prakash, C.},
   title     = {{Recognition polynomials}},
   journal   = {J. Opt. Soc. Am. A},
   year      = {1993},
   volume    = {10(4)},
   pages     = {759-764}
}

@book{berg-christensen-ressel-84,
   author    = {Berg, C. and Christensen, J. P. R. and Ressel, P.},
   title     = {{Harmonic Analysis on Semigroups}},
   year      = {1984},
   publisher = {Springer},
   address   = {New York}
}


@book{bernardo-smith-94,
   author    = {Bernardo, J. M. and Smith, A. F. M.},
   title     = {{Bayesian Theory}},
   year      = {1994},
   publisher = {Wiley},
   address   = {Chichester, UK}
}


@article{besag-74,
  author        = "J. Besag",
  title         = "On the statistical analysis of dirty pirtures",
  journal       = "Journal of Royal Statistics, Soc. B",
  year          = "1974",
  volume        = "48(3)",
  pages         = {259-302}
}



@techreport{beymer-shashua-poggio-93,
   author    = {Beymer, D. and Shashua, A. and Poggio, T.},
   title     = {{Example Based Image Analysis and Synthesis}},
   institution = {AI Laboratory, MIT},
   year      = {1993},
   number    = {{1431}},
   type      = {AI Memo}
}

@article{biehl-schwarze-95,
   author    = {Biehl, M. and Schwarze, H.},
   title     = {{Learning by Online Gradient Descent}},
   journal   = {J. Phys. A},
   year      = {1995},
   volume    = {28},
   pages     = {643}
}

@inproceedings{binford-71,
   author    = {Binford, T. O.},
   title     = {{Visual perception by computer}},
   booktitle = {{Proceedings of the IEEE Conference on Systems and Control}},
   year      = {1971},
   note      = {Miami}
}


@techreport{bishop-94,
   author    = {Bishop, C. M.},
   title     = {{Mixture Density Networks}},
   institution = {Neural Computing Research Group, Aston University, UK},
   year      = {1994},
   number    = {{NCRG/4288}},
   type      = {Technical Report}
}


@book{bishop-95,
   author    = {C. M. Bishop},
   title     = {{Neural Networks for Pattern Recognition}},
   year      = {1995},
   publisher = {Clarendon Press},
   address   = {Oxford}
}


@article{bishop-novelty-94,
   author    = {Bishop, C. M.},
   title     = {Novelty Detection and Neural Network Validation},
   journal   = {IEE Proceedings: Vision, Image and Signal Processing},
   year      = 1994,
   volume    = 141,
   number    = 4,
   pages     = {217--222}
}

@unpublished{bishop-svensen-williams-97,
   author    = {Bishop, C. M. and Svensen, M. and Williams, C. K. I.},
   title     = {{GTM: The Generative Topographic Mapping}},
   year      = {1997},
   note      = {Accepted for publication in \emph{Neural Computation}.}
}

@inproceedings{bishop-svensen-williams-97b,
   author    = {Bishop, C. M. and Svensen, M. and Williams, C. K. I.},
   title     = {{Magnification Factors for the GTM Algorithm}},
   booktitle = {Proc. 5th IEE Conference on Artificial Neural Networks},
   year      = {1997}
}


@article{bishop-svensen-williams-98,
   author    = {Bishop, C. M. and Svensen, M. and Williams, C. K. I.},
   title     = {{GTM: The Generative Topographic Mapping}},
   journal   = {Neural Computation},
   year      = {1998},
   volume    = {10(1)},
   pages     = {215-234}
}

@article{bishop-svensen-williams-98b,
   author    = {Bishop, C. M. and Svensen, M. and Williams, C. K. I.},
   title     = {{Developments of the Generative Topographic Mapping}},
   journal   = {Neurocomputing},
   year      = {1998},
   volume    = {21},
   pages     = {203-224}
}

@inproceedings{bishop-hinton-strachan-97,
   author    = {Bishop, C. M. and Hinton, G. E. and Strachan, I. G. D.},
   title     = {{GTM Through Time}},
   booktitle = {Proc. 5th IEE Conference on Artificial Neural Networks},
   year      = {1997}
}

@inproceedings{black-jepson-96,
   author    = {Black, M. J. and Jepson, A.},
   title     = {{EigenTracking: Robust matching and tracking of 
articulated objects using a view-based representation}},
   booktitle = {Proceedings of the Fourth European Conference on Computer 
Vision, ECCV'96}, 
   editor    = {B. Buxton and R. Cipolla},
   publisher = {Springer},
   ignote    = {Lecture Notes in Computer Science 1064},
   pages     = {329-342},
   year      = {1996}
}


@book{blake-isard-98,
   author    = {Blake, A. and Isard, M.},
   title     = {{Active Contours}},
   year      = {1998},
   publisher = {Springer}
}

@article{blake-curwen-zisserman-93,
   author    = {Blake, A. and Curwen, R. and Zisserman, A.},
   title     = {{A Framework for Spatiotemporal Control in the
       Tracking of Visual Contours}},
   journal   = {International Journal of Computer Vision},
   year      = {1993},
   volume    = {11(2)},
   pages     = {127-145}
}


@misc{blake-merz-98,
       author = "Blake, C. L. and Merz, C. J.",
       year = "1998",
       title = "{UCI} Repository of machine learning databases",
       note = "http://www.ics.uci.edu/\verb+~+mlearn/MLRepository.html",
       institution = "University of California, Irvine, Dept. of Information and Computer Sciences" 
} 

@article{blight-ott-75,
   author    = {Blight, B. J. N. and Ott, L.},
   title     = {{A Bayesian approach to model inadequacy for
       polynomial regression}},
   journal   = {Biometrika},
   year      = {1975},
   volume    = {62(1)},
   pages     = {79-88}
}


@article{bolles-cain-82,
   author    = {Bolles, R. C. and Cain, R. C.},
   title     = {{Recognizing and locating partially visible objects: The 
       local-feature-focus method}},
   journal   = {International Journal of Robotics Research},
   year      = {1982},
   volume    = {1(3)},
   pages     = {57-82}
}


@article{bouman-shapiro-94,
   author    = {Bouman, C. A. and Shapiro, M.},
   title     = {{A Multiscale Random Field Model for Bayesian Image
       Segmentation}},
   journal   = {IEEE Trans. on Image Processing},
   year      = {1994},
   volume    = {3(2)},
   pages     = {162-177}
}

@phdthesis{brown-87,
  author        = "Brown, P. F.",
  title         = "The Acoustic-Modeling Problem in 
                   Automatic Speech Recognition",
  year          = "1987",
type={PhD},
  school        = {Computer Science Department, CMU}
}


@book{castillo-gutierrez-hadi-97,
   author    = {Castillo, E. and Guti\'{e}rrez, J. M. and Hadi, A. S.},
   title     = {{Expert Systems and Probabilistic Network Models}},
   year      = {1997},
   publisher = {Springer},
   address   = {New York}
}

@article{castro-lawton-sylvestre-86,
   author    = {Castro, P. E. and Lawton, W. H. and Sylvestre, E. A.},
   title     = {{Principal Modes of Variation for Processes With Continuous
   Sample Curves}},
   journal   = {Technometrics},
   year      = {1986},
   volume    = {28(4)},
   pages     = {329-337}
}

@book{charniak-93,
   author    = {Charniak, E.},
   title     = {{Statistical Language Learning}},
   year      = {1993},
   publisher = {MIT Press},
   address   = {Cambridge, Massachusetts}
}

@book{chatfield-89,
   author    = {Chatfield, C.},
   title     = {{The Analysis of Time Series: An Introduction}},
   year      = {1989},
   publisher = {Chapman and Hall},
   edition   = {4th},
   address   = {London}
}

@article{chatfield-95,
   author    = {Chatfield, C.},
   title     = {{Model Uncertainty, Data Mining and Statistical-inference}},
   journal   = {J. Roy. Stat. Soc. A},
   year      = {1995},
   volume    = {158},
   pages     = {419-466}
}


@inproceedings{cheng-bouman-98,
   author    = {Cheng, H. and Bouman, C. A.},
   title     = {{Trainable Context Model for Multiscale Segmentation}},
   booktitle = {Proc. ICIP '98},
   year      = {1998},
   volume    = {1},
   pages     = {610-614}
}

@article{chow-liu-68,
   author    = {Chow, C. K. and Liu, C. N.},
   title     = {{Approximating discrete probability distributions with 
   dependence trees}},
   journal   = {IEEE Trans. on Info. Theory},
   year      = {1968},
   volume    = {14},
   pages     = {462-467}
}

@inproceedings{cipolla-blake-90,
   author    = {Cipolla, R. and Blake, A.},
   title     = {{The Dynamic Analysis of Apparent Contours}},
   booktitle = {{Proc. International Conference on Computer Vision}},
   year      = {1990},
   note      = {Osaka}
}


@book{ckiw-gonzalez-wintz,
   key       = {image-processing},
   author    = {Gonzalez, R. C. and Wintz, P.},
   title     = {Digital Image Processing},
   year      = {1987},
   publisher = {Addison-Wesley},
   address   = {Reading, Massachusetts},
   edition   = {second}
}


@book{ckiw-lowe-85,
   author    = {Lowe, D. G.},
   title     = {{Perceptual Organization and Visual Recognition}},
   year      = {1985},
   publisher = {Kluwer},
   address   = {Boston}
}


@book{ckiw-mclachlan-basford-88,
   key       = {mclachlan},
   author    = {McLachlan, G.~J. and Basford, K.~E.},
   title     = {Mixture models:  inference and applications to clustering},
   year      = {1988},
   publisher = {Marcel Dekker, Inc.}
}

@book{mclachlan-krishnan-97,
   author    = {McLachlan, G.~J. and Krishnan, T.},
   title     = {{THe EM Algorithm}},
   year      = {1997},
   publisher = {Wiley},
   address   = {Chichester, UK}
}


@book{ckiw-rissanen-89,
   key       = {Rissanen},
   author    = {Rissanen, J.},
   title     = {Stochastic Complexity in Statistical Inquiry},
   year      = {1989},
   publisher = {World Scientific Publ. Co.}
}


@incollection{cootes-taylor-92,
   author    = {Cootes, T. F. and Taylor, C. J.},
   title     = {Active Shape Models---Smart Snakes},
   booktitle = {Proceedings of the British Machine Vision Conference},
   year      = {1992},
   editor    = {Hogg, D. and Boyle, R.},
   publisher = {Springer},
   pages     = {266-275}
}

@misc{CornfordNabney_satilite:98,
  author =       {Cornford, D. and Ramage, G. and Nabney, I. T.},
  title =        {A Neural Network Sensor Model with Input Noise},
  year =         {1999},
  note =         {Submitted to Neurocomputing Letters}
}


@article{cortes-vapnik-95,
   author    = {Cortes, C. and Vapnik, V.},
   title     = {{Support Vector networks}},
   journal   = {Machine Learning},
   year      = {1995},
   volume    = {20},
   pages     = {273-297}
}

@article{cowles-carlin-96,
   author    = {Cowles, M. K. and Carlin, B. P.},
   title     = {{Markov-Chain Monte-Carlo Convergence Diagnostics---A
   Comparative Review}},
   journal   = {J. American Stat. Assoc.},
   year      = {1996},
   volume    = {91},
   pages     = {883-904}
}

@book{cox-cox-94,
   author    = {Cox, T. F. and Cox, M. A. A.},
   title     = {{Multidimensional Scaling}},
   year      = {1994},
   publisher = {Chapman and Hall},
   address   = {London}
}


@book{cressie-93,
   author    = {Cressie, N. A. C.},
   title     = {{Statistics for Spatial Data}},
   year      = {1993},
   publisher = {Wiley},
   address   = {New York}
}

@book{cristianini-shawe-taylor-00,
   author    = {Cristianini, N. and Shawe-Taylor, J.},
   title     = {{An Introduction to Support Vector Machines}},
   year      = {2000},
   publisher = {Cambridge University Press}
}

@incollection{critchley-78,
   author    = {Critchley, F.},
   title     = {Multidimensionsal scaling: a short critique and a 
new method},
   booktitle = {COMPSTAT 1978},
   year      = {1978},
   editor    = {Corsten, L. C. A and Hermans, J.},
   publisher = {Physica-Verlag},
   address   = {Vienna}
}


@article{crouse-nowak-baraniuk-98,
   author    = {Crouse, M. and Nowak, R. and Baraniuk, R.},
   title     = {{Wavelet-based statistical signal proccessing using hidden
Markov models}},
   journal   = {IEEE Trans. on Signal Processing},
   year      = {1998},
   volume    = {46},
   pages     = {886-902}
}


@incollection{csato-opper-00,
   author    = {Csato, L. and Opper, M.},
   title     = {{Sparse Representation for Gaussian Process Models}},
   booktitle = {{Advances in Neural Information Processing Systems 13}},
   year      = {2001},
   editor    = {Leen, T. K. and Diettrich, T. G. and Tresp, V.},
   publisher = {MIT Press}
}

@book{david-70,
   author    = {David, H. A.},
   title     = {{Order Statistics}},
   year      = {1970},
   publisher = {Wiley},
   address   = {New York}
}

@article{dayan-hinton-neal-zemel-95,
   author    = {Dayan, P. and Hinton, G. E.  and Neal, R. M. and Zemel, R. S.},
   title     = {{The Helmholtz Machine}},
   journal   = {Neural Computation},
   year      = {1995},
   volume    = {7(5)},
   pages     = {889-904}
}

@incollection{debonet-viola-98,
   author    = {de Bonet, J. S. and Viola, P. A.},
   title     = {{A Non-Parametric Multi-Scale Statistical Model for Natural
               Images}},
   booktitle = {Advances in Neural Information Processing Systems 10},
   year      = {1998},
   editor    = {Jordan, M. I. and Kearns, M. J. and Solla, S. A.},
   publisher = {MIT Press},
   address   = {Cambridge, MA},
   pages     = {773-779}
}

@inproceedings{delatorre-black-01,
   author    = {De la Torre, F. and Black, M.},
   title     = {{Robust principal component analysis for computer vision}},
   booktitle = {Proceedings of Eighth IEEE International Conference on 
Computer Vision ICCV-2001},
   volume    = {I},
   pages     = {362-369},
   year      = {2001}
}

@article{dellaportas-stephens-95,
   author    = {Dellaportas, P. and Stephens, D. A.},
   title     = {{Bayesian Analysis of Errors-in-Variables Regression Models}},
   journal   = {Biometrics},
   year      = {1995},
   volume    = {51},
   pages     = {1085-1095}
}

@incollection{diebolt-ip-96,
   author    = {Diebolt, J. and Ip, E. H. S.},
   title     = {{Stochastic {EM}: method and application}},
   booktitle = {Markov Chain Monte Carlo in Practice},
   year      = {1996},
   editor    = {Gilks, W. R. and Richardson, S. and Spiegelhalter, D. J.},
   publisher = {Chapman and Hall},
   pages     = {259-274}
}

@inproceedings{doermann-rosenfeld-92,
   author    = {Doermann, D. S. and Rosenfeld, A.},
   title     = {{Recovery of temporal information from static images of handwriting}},
   booktitle = {{Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}},
   year      = {1992}
}

@book{doob-53,
   author    = {Doob, J. L.},
   title     = {{Stochastic Processes}},
   year      = {1953},
   publisher = {Wiley},
   address   = {New York}
}

@article{draper-95,
   author    = {Draper, D.},
   title     = {{Assessment and propagation of model uncertainty (with discussion)}},
   journal   = {J. Roy. Stat. Soc. B},
   year      = {1995},
   volume    = {57},
   pages     = {45-97}
}

@article{duane-kennedy-pendleton-roweth-87,
   author    = {Duane, S. and Kennedy, A. D. and Pendleton, B. J. and
       Roweth, D.},
   title     = {{Hybrid Monte Carlo}},
   journal   = {Physics Letters B},
   year      = {1987},
   volume    = {195},
   pages     = {216-222}
}

@inproceedings{ducksbury-93,
   author    = {Ducksbury, P. G.},
   title     = {{Parallel Model-Based Segmentation using a Pearl Bayes Network}},
   booktitle = {{Proc. British Machine Vision Conference 1993}},
   publisher = {BMVA Press},
   year      = {1993}
}


@inproceedings{dudek-tsotsos-91,
   author    = {Dudek, G. and Tsotsos, J. K.},
   title     = {{Shape representation and recognition from curvature}},
   booktitle = {{Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}},
   year      = {1991},
   pages     = {35-41}
}

@book{durbin-eddy-krogh-mitchison-98,
   author    = {Durbin, R. and Eddy, S. and Krogh, A. and Mitchison, G.},
   title     = {{Biological Sequence Analysis}},
   year      = {1998},
   publisher = {Cambridge University Press},
   address   = {Cambridge, UK}
}

@article{eaton-tyler-91,
   author    = {Eaton, M. L. and Tyler, D. E.},
   title     = {{On Wielandt's Inequality and Its Application to the Asymptotic
Distribution of the Eigenvalues of a Random Symmetric Matrix}},
   journal   = {Annals of Statistics},
   year      = {1991},
   volume    = {19(1)},
   pages     = {260-271}
}

@techreport{edelman-poggio-90,
   author    = {Edelman, S. and Poggio, T.},
   title     = {{Bringing the Grandmother back into the picture: a memory-based view of object recognition}},
   institution = {AI Laboratory, MIT},
   year      = {1990},
   number    = {{1181}},
   type      = {Technical Report}
}


@book{edelsbrunner-87,
   author    = {Edelsbrunner, H.},
   title     = {{Algorithms in combinatorial geometry}},
   year      = {1987},
   publisher = {Springer}
}

@article{edwards-70,
   author    = {Edwards, A. W. F.},
   title     = {{Estimation of the Branch Points of a Branching Diffusion 
                Process}},
   journal   = {Journal of the Royal Statistical Society B},
   year      = {1970},
   volume    = {32(2)},
   pages     = {155-174}
}

@techreport{felderhof-storkey-williams-01,
   author    = {Felderhof, S. N. and Storkey, A. J. and Williams, C. K. I.},
   title     = {{Position Encoding Dynamic Trees for Image Sequence Analysis}},
   institution = {Division of Informatics, University of Edinburgh},
   year      = {2001}
}

@article{feldman-yakimovsky-74,
   author    = {Feldman, J. A. and Yakimovsky, Y.},
   title     = {{Decision Theory and Artificial Intelligence: I. A
   Semantics-Based Region Analyzer}},
   journal   = {Artificial Intelligence},
   year      = {1974},
   volume    = {5},
   pages     = {349-371}
}

@inproceedings{feng-williams-98,
  author        = "Feng, Xiaojuan and Williams, C. K. I. ",
  title         = {{Training Bayesian networks for image segmentation}},
  booktitle = "Mathematical Modeling and
                  Estimation Techniques in Computer Vision",
  editor    = "Pr{\^{e}}teux, F. and Davidson, J. L.  and
                  Dougherty, E. R. ",
  publisher = "SPIE",
  volume    = "3457",
  year      = "1998",
  pages     = "82-92"
}

@unpublished{feng-williams-99,
  author        = "Feng, Xiaojuan and Williams, C. K. I. ",
  title         = {{Combining belief networks and neural networks for image segmentation}},
  year      = "1999",
  note      = {Submitted for publication}
}

@misc{feng-williams-felderhof-01,
  author        = "Feng, Xiaojuan and Williams, C. K. I. and Felderhof, S. N.",
  title         = {{Combining Belief Networks and Neural Networks for 
Scene Segmentation}},
  year      = "2001",
  note      = {Accepted for publication in \emph{IEEE Trans. Pattern 
Analysis and Machine Intelligence}.}
}

@article{feng-williams-felderhof-02,
  author        = "Feng, Xiaojuan and Williams, C. K. I. and Felderhof, S. N.",
  title         = {{Combining Belief Networks and Neural Networks for 
Scene Segmentation}},
   journal   = {IEEE Trans Pattern Analysis and Machine Intelligence},
   year      = {2002},
   volume    = {24},
   number    = {4},
   pages     = {467-483}
}

@book         {ferguson-67,
  author    = "Ferguson, T. S.",
  title     = "{Mathematical Statistics: A Decision Theoretic Approach}",
  publisher = "Academic Press",
  year      = "1967"
}                

@incollection{ferrari-trecate-williams-opper-99,
   author    = {Ferrari Trecate, G. and Williams, C. K. I. and Opper, M.},
   title     = {{Finite-dimensional approximation of Gaussian processes}},
   booktitle = {{Advances in Neural Information Processing Systems 11}},
   year      = {1999},
   editor    = {Kearns, M. S. and Solla, S. A. and Cohn, D. A.},
   publisher = {MIT Press},
   pages     = {218-224}
}

@article{fieguth-karl-willsky-98,
   author    = {Fieguth, P. and Karl, W. and Willsky, A. S.},
   title     = {Efficient multiresolution counterparts to variational methods for surface reconstruction},
   journal   = {Computer Vision and Image Understanding},
   year      = {1998},
   volume    = {70},
   number    = {2},
   pages     = {157-176}
}

@techreport{fine-scheinberg-00,
   author    = {Fine, S. and Scheinberg, K.},
   title     = {{Efficient SVM Training Using Low-Rank Kernel Representation}},
   institution = {IBM T. J. Watson Research Center},
   year      = {2000},
   number    = {{RC 21911}},
   type      = {Research Report}
}

@article{fisher-87,
   author    = {Fisher, D. H.},
   title     = {{Knowledge Acquisition Via Incremental Conceptual Clustering}},
   journal   = {{Machine Learning}},
   year      = {1987},
   volume    = {2},
   pages     = {139-172}
}

@inproceedings{fowlkes-belongie-malik-01,
   author    = {Fowlkes, C. and Belongie, S. and Malik, J.}, 
   title     = {{Efficient Spatiotemporal Grouping Using the Nystr\"{o}m
Method}},
   booktitle = {{Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2001}},
   year      = {2001}
}

                                                                                                

@inproceedings{frasconi-gori-sperduti-96,
   author    = {Frasconi, P. and Gori, M. and Speduti, A.},
   title     = {{On the Efficient Classification of Data Structures by Neural
Networks}},
   booktitle = {{Proceedings of the International Joint
       Conference on Artificial Intelligence (IJCAI-97)}},
   year      = {1997}
}

@article{freeman-94,
   author    = {Freeman, W. T.},
   title     = {{The generic viewpoint assumption in a framework for visual perception}},
   journal   = {Nature},
   year      = {1994},
   volume    = {368},
   pages     = {542-545}
}


@inproceedings{frey-jojic-99,
   author    = {Frey, B. J. and Jojic, N.},
   title     = {{Estimating mixture models of images and inferring 
spatial transformations using the EM algorithm}},
   booktitle = {Proceedings of the IEEE Conference on Computer Vision 
and Pattern Recognition 1999},
   year      = {1999},
   publisher = {IEEE Computer Society Press},
   note      = {Ft. Collins, CO}
}


@misc{frey-jojic-02a,
   author    = {Frey, B. J. and Jojic, N.},
   title     = {{Transformation Invariant Clustering and Linear 
Component Analysis Using the EM Algorithm}},
   year      = {2002},
   note      = {Revised manuscript under review for IEEE PAMI},
   ignote    = {Revised manuscript under review for IEEE 
Trans. on Pattern Analysis and Machine Intelligence}
}

@article{frey-jojic-03,
   author    = {Frey, B. J. and Jojic, N.},
   title     = {{Transformation Invariant Clustering Using the EM Algorithm}},
   journal   = {IEEE Trans Pattern Analysis and Machine Intelligence},
   year      = {2003},
   volume    = {25(1)},
   pages     = {1-17}
}



@incollection{frey-mackay-98,
   author    = {Frey, B. J. and MacKay, D. J. C.},
   title     = {{A Revolution: Belief Propagation in Graphs with Cycles}},
   booktitle = {Advances in Neural Information Processing Systems 10},
   year      = {1998},
   editor    = {Jordan, M. I. and Kearns, M. J. and Solla, S. A.},
   publisher = {MIT Press}
}


@inproceedings{frieze-kannan-vempala-98,
   author    = {Frieze, A. and Kannan, R. and Vempala, S.},
   title     = {{Fast Monte-Carlo Algorithms for finding low-rank 
approximations}},
   booktitle = {39th Conference on the Foundations of Computer Science},
   year      = {1998},
   pages     = {370-378}
}



@inproceedings{fritzke-95,
   author    = {Fritzke, B.},
   title     = {A Growing Neural Gas Network Learns Topologies},
   booktitle = {Advances in Neural Information Processing Systems 7},
   year      = {1995},
   editor    = {Tesauro, G. and Touretzky, D. and Leen, T.},
   publisher = {MIT Press},
   pages     = {625-632}
}

@inproceedings{fua-hanson-89,
   author    = {Fua, P. and Hanson, A. J.},
   title     = {{Objective Functions for Feature Discrimination: Theory}},
   booktitle = {{Proc. DARPA Image Understanding Workshop}},
   year      = {1989}
}

@book{gelman-carlin-stern-rubin-95,
   author    = {Gelman, A. and Carlin, J. B. and Stern, H. S. and Rubin, D. B.

},
   title     = {{Bayesian Data Analysis}},
   year      = {1995},
   publisher = {Chapman and Hall},
   address   = {London}
}
@article{geiger-heckerman-96,
   author    = {Geiger, D. and Heckerman, D.},
   title     = {{Knowledge representation and inference in similarity
networks and Bayesian multinets}},
   journal   = {Artificial Intelligence},
   year      = {1996},
   volume    = {82},
   pages     = {45-74}
}


@article{geiger-yuille-91,
   author    = {Geiger, D. and Yuille, A.},
   title     = {{A Common Framework for Image Segmentation}},
   journal   = {International {J}ournal of {C}omputer {V}ision},
   year      = {1991},
   volume    = {6(3)},
   pages     = {227-243}
}


@article{geman-bienenstock-doursat-92,
   author    = {Geman, S. and Bienenstock, E. and Doursat, R.},
   title     = {{Neural Networks and the Bias/Variance Dilemma}},
   journal   = {Neural {C}omputation},
   year      = {1992},
   volume    = {4(1)},
   pages     = {1-58}
}


@article{geman-geman-84,
   author    = {Geman, S. and Geman, D.},
   title     = {{Stochastic Relaxation, Gibbs Distributions, and the
                Bayesian Restoration of Images}},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intellligence},
   year      = {1984},
   volume    = {6(6)},
   pages     = {721-741}
}

@incollection{ghahramani-95,
   author    = {Ghahramani, Z.},
   title     = {{Factorial Learning and the EM Algorithm}},
   year      = {1995},
   pages     = {617-624},
   booktitle = {Advances in Neural Information Processing Systems 7},
   editor    = {Tesauro, G. and Touretzky, D. S. and Leen, T. K.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA}

}

@article{ghahramani-hinton-98,
   author    = {Ghahramani, Z. and Hinton, G. E.},
   title     = {{Variational Learning for Switching State-Space Models}},
   journal   = {Neural Computation},
   year      = {1998},
   volume    = {12(4)},
   pages     = {963-996}
}


@incollection{ghahramani-jordan-94,
   author    = {Ghahramani, Z. and Jordan, M. I.},
   title     = {Supervised Learning from Incomplete Data via an {EM} Approach},
   booktitle = {Neural Information Processing Systems, Vol. 6},
   year      = {1994},
   pages     = {120-127},		  
   editor    = {Cowan, J. D. and Tesauro, G. and Alspector, J.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA}
}

@incollection{ghahramani-jordan-96,
   author    = {Ghahramani, Z. and Jordan, M. I.},
   title     = {Factorial Hidden Markov Models},
   booktitle = {Advances in Neural Information Processing Systems 8},
   year      = {1996},
   editor    = {Touretzky, D. S. and Mozer, M. C. and Hasselmo, M. E.},
   publisher = {MIT Press},
   address   = {Cambridge, MA}
}

@article{ghahramani-jordan-97,
   author    = {Ghahramani, Z. and Jordan, M. I.},
   title     = {Factorial Hidden Markov Models},
   journal   = {Machine Learning},
   year      = {1997},
   volume    = {29},
   pages     = {245-273}
}

@incollection{gidas-93,
   author    = {Gidas, B.},
   title     = {{Parameter estimation for Gibbs distributions from fully
       observed data}},
   booktitle = {Markov Random Fields: Theory and Application},
   year      = {1993},
   editor    = {Chellappa, R. and Jain, A.},
   publisher = {Academic Press}
}


@article{girard-89,
   author    = {Girard, D.},
   title     = {{A fast "Monte Carlo cross-validation" procedure for large least squares problems with noisy data}},
   journal   = {Numer. Math.},
   year      = {1989},
   volume    = {56},
   pages     = {1-23}
}

@article{girosi-jones-poggio-95,
   author    = {Girosi, F. and Jones, M. and Poggio, T.},
   title     = {{Regularization Theory and Neural Networks Architectures}},
   journal   = {Neural Computation},
   year      = {1995},
   volume    = {7(2)},
   pages     = {219-269}
}

@incollection{gold-mjolsness-rangarajan-94,
   author    = {Gold, S. and Mjolsness, E. and Rangarajan, A.},
   title     = {{Clustering with a Domain-Specific Distance Measure}},
   booktitle = {Neural Information Processing Systems, Vol. 6},
   year      = {1994},
   editor    = {Cowan, J. D. and Tesauro, G. and Alspector, J.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA}
}

@incollection{goldberg-williams-bishop-97, 
   author    = {Goldberg, P. W. and Williams, C. K. I. and Bishop, C. M.},
   title     = {{Regression with Input-dependent Noise: A Gaussian Process Treatment}},
   booktitle = {Advances in Neural Information Processing Systems 10},
   year      = {1998},
   editor    = {Jordan, M. I. and Kearns, M. J. and Solla, S. A.},
   publisher = {MIT Press},
   address   = {Cambridge, MA}
}

@article{gopalakrishnan-91,
  author        = "Gopalakrishnan, P. S. and Kanevsky, D.  
                   and Nadas, A.  and D. Nahamoo",
  title         = {{A}n inequality for rational functions with applications to 
                   some statistical estimation problems},
  journal       = "IEEE Trans. on Info. Theory",
  year          = "1991",
  volume        = "{\bf 37}(1)",
  pages         = "107-113"
}

@book{gradshteyn-ryzhik-80,
   author    = {Gradshteyn, I. S. and Ryzhik, I. M.},
   title     = {Tables of Integrals, Series and Products},
   year      = {1980},
   note      = {Corrected and enlarged edition prepared by A. Jeffrey},
   publisher = {Academic Press}
}

@article{green-90,
   author    = {Green, P. J.},
   title     = {{On the use of the EM Algorithm for Penalized Likelihood Estimation}},
   journal   = {J. Roy. Stat. Soc. B},
   year      = {1990},
   volume    = {52(3)},
   pages     = {443-452}
}

@article{green-95,
   author    = {Green, P. J.},
   title     = {{Reversible Jump Markov chain Monte Carlo computation and 
Bayesian model determination}},
   journal   = {Biometrika},
   year      = {1995},
   volume    = {82(4)},
   pages     = {711-732}
}

@book         {green-silverman-94,
  author    = "Green, P. J. and Silverman, B. W.",
  title     = "{Nonparametric regression and generalized linear models}",
  publisher = "Chapman and Hall",
  year      = "1994",
  address   = {London}
}

@book{grigoriu-95,
   author    = {Grigoriu, M.},
   title     = {{Applied Non-Gaussian processes}},
   year      = {1995},
   publisher = {PTR Prentice Hall}
}


@book{grimson-90,
   author    = {Grimson, W. E. L.},
   title     = {{Object recognition by computer}},
   year      = {1990},
   publisher = {MIT Press},
   address   = {Cambridge, MA}
}


@incollection{gull-88,
   author    = {Gull, S. F.},
   title     = {{Bayesian inductive inference and maximum entropy}},
   booktitle = {{Maximum Entropy and Bayesian Methods in science and engineering, vol1: Foundations}},
   year      = {1988},
   editor    = {Erickson, G. J. and Smith, C. R.},
   publisher = {Kluwer}
}


@article{handcock-stein-93,
   author    = {Handcock, M. S. and Stein, M. L.},
   title     = {{A Bayesian Analysis of Kriging}},
   journal   = {Technometrics},
   year      = {1993},
   volume    = {35(4)},
   pages     = {403-410}
}

@article{hansen-93,
   author    = {Hansen, L. K.},
   title     = {{Stocastic Linear Learning:Exact Test and Training Error
Averages}},
   journal   = {Neural Networks},
   year      = {1993},
   volume    = {6},
   pages     = {393-396}
}


@inproceedings{hanson-stutz-cheeseman-91,
   author    = {Hanson, R. and Stutz, J. and Cheeseman, P.},
   title     = {{Bayesian Classification with Correlation and Inheritance}},
   booktitle = {{IJCAI-91: Proceedings of the Twelfth International Joint 
                 Conference on Artificial Intelligence}},
   year      = {1991},
   note      = {Sydney, Australia}
}

@book{hardle-90,
   author    = {H\"{a}rdle, W.},
   title     = {{Applied Nonparametric Regression}},
   year      = {1990},
   publisher = {Cambridge University Press},
   address   = {Cambridge, England}
}


@article{harrison-rubinfeld-78,
   author    = {Harrison, D. and Rubinfeld, D. L.},
   title     = {{Hedonic housing prices and the demand for clean air}},
   journal   = {Journal of Environmental Economics and Management},
   year      = {1978},
   volume    = {5},
   pages     = {81-102}
}

@article{hastie-stuetzle-89,
   author    = {Hastie, T. and Stuetzle, W.},
   title     = {{Principal Curves}},
   journal   = {J. American Statistical Association},
   year      = {1989},
   volume    = {84},
   pages     = {502-516}
}

@article{hastie-96,
   author    = {Hastie, T.},
   title     = {{Pseudosplines}},
   journal   = {Journal of the Royal Statistical Society B},
   year      = {1996},
   volume    = {58},
   pages     = {379-396}
}

@misc{haussler-opper-95,
   author    = {Haussler, D. and Opper, M.},
   title     = {{Mutual Information, Metric Entropy, and Risk in Estimation of
Probability Distributions}},
   year      = {1995},
   note      = {Submitted to \emph{Annals of Statistics}}
}

@book{haykin-99,
   author    = {Haykin, S.},
   title     = {{Neural Networks: A Comprehensive Foundation}},
   year      = {1999},
   publisher = {Prentice Hall International},
   note      = {Second edition},
   address   = {London, England}
}

@techreport{heckerman-95,
   author    = {Heckerman, D.},
   title     = {{ A tutorial on learning with Bayesian networks}},
   institution = {Microsoft Research},
   year      = {1995},
   number    = {{MSR-TR-95-06}},
   note      = {Revised November 1996. Available from \\ 
\verb+http://www.research.microsoft.com/research/dtg/heckerma/heckerma.html+}
}

@book         {hertz-krogh-palmer-91,
  author    = "Hertz, J. and Krogh, A. and Palmer, R. G.",
  title     = "{Introduction to the Theory of Neural Computation}",
  publisher = "Addison-Wesley",
  note      = "Lecture Notes Volume I: Santa Fe Institute Studies in the
               Sciences of Complexity",
  year      = "1991"
}                

@book         {helstrom-95,
  author    = "Helstrom, C. W.",
  title     = "{Elements of Signal Detection and Estimation}",
  publisher = "PTR Prentice Hall",
  year      = "1995"
}                

@article{hinton-89,
   author    = {Hinton, G. E.},
   title     = {Connectionist learning procedures},
   journal   = {Artificial Intelligence},
   year      = {1989},
   volume    = {40},
   pages     = {185-234}
}

@inproceedings{hinton-99,
   author    = {Hinton, G. E.},
   title     = {{Products of Experts}},
   booktitle = {Proceedings of the Ninth International Conference on
Artificial Neural Networks},
   year      = {1999},
   volume    = {1},
   pages     = {1-6}
}

@incollection{hinton-dayan-to-neal-95,
   author    = {Hinton, G. ~E. and Dayan, P. S. and To, A. and Neal. R. M.},
   title     = {{The Helmholtz Machine Through Time}},
   booktitle = {Proc. ICANN 95},
   year      = {1995},
   editor    = {Fogelman-Soulie, F. and Gallinari, P.},
   publisher = {EC2 et Cie}
}


@incollection{hinton-ghahramani-teh-00,
   author    = {Hinton, G. E. and Ghahramani, Z. and Teh, Y. W.},
   title     = {{Learning to Parse Images}},
   booktitle = {{Advances in Neural Information Processing Systems 12}},
   year      = {2000},
   editor    = {Solla, S. A. and Leen, T. K. and M\"{u}ller, K.-R.},
   publisher = {MIT Press},
   pages     = {463-469},
   address   = {Cambridge, MA}
}
   

@misc{hinton-revow-dayan-94,
   author    = {Hinton, G. E. and Revow, M. and Dayan, P.},
   title     = {{Recognizing Handwritten Digits Using Mixtures of Linear Models}},
   year      = {1994},
   note      = {Submitted to NIPS-7}
}


@article{hinton-dayan-revow-97,
   author    = {Hinton, G. E. and Dayan, P. and Revow, M.},
   title     = {{Modelling the Manifolds of Images of Handwritten Digits}},
   journal   = {IEEE Trans. on Neural Networks},
   year      = {1997},
   volume    = {8(1)},
   pages     = {65-74}
}


@incollection{hinton-williams-revow-92b,
   author    = {Hinton, G. ~E. and Williams, C. ~K. ~I. and Revow, M. ~D.},
   title     = {Combinining two methods of recognizing hand-printed digits},
   booktitle = {Artificial Neural Networks 2},
   year      = {1992},
   editor    = {I. Aleksander and J. Taylor},
   publisher = {Elsevier Science Publishers}
}

@incollection{hinton-zemel-94,
   author    = {Hinton, G. ~E. and Zemel, R. S.},
   title     = {{Autoencoders, minimum description length, and Helmholtz
free energy}},
   booktitle = {Advances in Neural Information Processing Systems 6},
   year      = {1994},
   editor    = {Cowan, J. and Tesauro, G. and Alspector, J.},
   publisher = {Morgan Kaufmann}
}

@incollection{hofmann-buhmann-95,
   author    = {Hofmann, T. and Buhmann, J. M.},
   title     = {{Hierarchical Pairwise Data Clustering by Mean-Field
Annealing}},
   booktitle = {Proc. ICANN 95},
   year      = {1995},
   editor    = {Fogelman-Soulie, F. and Gallinari, P.},
   publisher = {EC2 et Cie}
}



@book{horn-86,
   author    = {Horn, B. K. P.},
   title     = {{Robot Vision}},
   year      = {1986},
   publisher = {MIT Press},
   address   = {Cambridge, MA}
}

@article{hornik-93,
   author    = {Hornik, K.},
   title     = {Some New Results on Neural Network Approximation},
   journal   = {Neural Networks},
   year      = {1993},
   volume    = {6},
   number    = {8},
   pages     = {1069-1072}
}

@misc{hough-62,
   author    = {Hough, P. V. C.},
   title     = {{Methods and Means for Recognizing Complex Patterns}},
   year      = {1962},
   month     = {December},
   note      = {U.S. Patent 3069654}
}


@book{huber-81,
   author    = {Huber, P. J.},
   title     = {{Robust Statistics}},
   year      = {1981},
   publisher = {Wiley},
   address   = {New York}
}

@article{hull-94,
   key       = {OCR},
   author    = {Hull, J. J},
   title     = {A database for handwritten text recognition research},
   journal   = PAMI,
   year      = {1994},
   volume    = {16},
   number    = {5},
   pages     = {550-554}
}


@article{hunt-nolte-ruedger-88,
   author    = {Hunt, D. J. and Nolte, L. W. and Ruedger, W. H.},
   title     = {{Performance of the Hough Transform and its Relationship
       to Statistical Signal Detection Theory}},
   journal   = {{Computer Vision, Graphics and Image Processing}},
   year      = {1988},
   volume    = {43},
   pages     = {221-238}
}

@article{hutchinson-89,
   author    = {Hutchinson, M.},
   title     = {{A stochastic estimator for the trace of the influence matrix for Laplacian smoothing splines}},
   journal   = {{Communications in statistics:Simulation and computation}},
   year      = {1989},
   volume    = {18},
   pages     = {1059-1076}
}


@article{hyvarinen-99,
   author    = {A. Hyv\"{a}rinen},
   title     = {{Survey on Independent Component Analysis}},
   journal   = {{Neural Computing Surveys}},
   year      = {1999},
   volume    = {2},
   pages     = {94-128}
}


@article{illingworth-kittler-88,
   author    = {Illingworth, J. and Kittler, J.},
   title     = {{A Survey of the Hough Transform}},
   journal   = {{Computer Vision, Graphics and Image Processing}},
   year      = {1988},
   volume    = {44},
   pages     = {87-116}
}

@inproceedings{isard-blake-96,
   author    = {Isard, M. and Blake, A.},
   title     = {{Contour tracking by stochastic propagation of 
               conditinal density}},
   booktitle = {Proc. European Conf. on Computer Vision},
   year      = {1996},
   pages     = {343-356}
}

@phdthesis{jaakola-97,
   author    = {Jaakkola, T. S.},
   title     = {{Variational Methods for Inference and Estimation in 
Graphical Models}},
type={PhD},
   year      = {1997},
   school    = {Dept. of Brain and Cognitive Sciences, MIT}
}



@incollection{jaakkola-haussler-99,
   author    = {Jaakkola, T. S. and Haussler, D.},
   title     = {{Exploiting Generative Models in Discriminative Classifiers}},
   booktitle = {Advances in Neural Information Processing Systems 11},
   year      = {1999},
   editor    = {Kearns, M. S. and Solla, S. A. and Cohn, D. A.},
   publisher = {MIT Press}
}

@article{jacobs-jordan-nowlan-hinton-91,
   author    = {Jacobs, R. A. and Jordan, M. I. and Nowlan, S. J. and
Hinton, G. E.},
   title     = {{Adaptive Mixtures of Local Experts}},
   journal   = {Neural Computation},
   year      = {1991},
   volume    = {3},
   pages     = {79-87}
}


@article{james-60,
   author    = {James, A. T.},
   title     = {{The distribution of the latent roots of the covariance matrix}},
   journal   = {Annals of Math. Stat.},
   year      = {1960},
   volume    = {31},
   pages     = {151-158}
}

@inproceedings{jasiobedzki-williams-lu-94,
   author    = {Jasiobedzki, P. and Williams, C. K. I. and Lu, F.},
   title     = {{Detecting and Reconstructing Vascular Trees in Retinal Images}},
   booktitle = {{Medical Imaging 1994: Image Processing}},
   year      = {1994},
   address   = {Newport Beach, CA, USA}
}


@book           {jensen-96,
  author        = "Jensen, F. V.",
  title         = "An Introduction to Bayesian Networks",
  year          = "1996",
  address       ="London",
  publisher     = "UCL Press"
}
 @article{hojen02meanfield,
   author = "P. A.d.F.R. Hojen-Sorensen and O. Winther and L. K. Hansen",
   title = "Mean Field Approaches to Independent Component Analysis",
   journal = "Neural Computation",
   volume = "14",
   pages = "889-918",
   year = "2002"
}


@incollection{jepson-richards-93,
   author    = {Jepson, A. D. and Richards, W.},
   title     = {{What makes a good feature ?}},
   booktitle = {Spatial Vision in Humans and Robots},
   year      = {1993},
   editor    = {L. Harris and M. Jenkin},
   publisher = {Cambridge University Press}
}
@article{opper00gaussian,
   author = "Manfred Opper and Ole Winther",
   title = "Gaussian Processes for Classification: Mean-Field Algorithms",
   journal = "Neural Computation",
   volume = "12",
   number = "11",
   pages = "2655-2684",
   year = "2000"
}

@inproceedings{jojic-frey-01,
   author    = {Jojic, N. and Frey, B. J.},
   title     = {{Learning Flexible Sprites in Video Layers}},
   booktitle = {Proceedings of the IEEE Conference on Computer Vision 
and Pattern Recognition 2001},
   year      = {2001},
   publisher = {IEEE Computer Society Press},
   note      = {Kauai, Hawaii}
}


@book{journel-huijbregts-78,
   author    = {Journel, A. G. and Huijbregts, {Ch}. J.},
   title     = {{Mining Geostatistics}},
   year      = {1978},
   publisher = {Academic Press}
}


@article{kass-witkin-terzopoulos-87b,
   author    = {Kass, M. and Witkin, A. and Terzopoulos, D.},
   title     = {Snakes: Active Contour Models},
   journal   = {International Journal of Computer Vision},
   year      = {1987},
   volume    = {1(4)},
   pages     = {321-332}
}

@inproceedings{keren-92,
   author    = {Keren, D. and Subrahmonia, J. and Cooper, D. B.},
   title     = {{Robust Object Recognition Based on Implicit Algebraic Curves
       and Surfaces}},
   booktitle = {{Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}},
   year      = {1992}
}

@article{kenny-lennig-mermelstein-90,
   author    = {Kenny, P. and Lennig, M. and Mermelstein, P.},
   title     = {{A Linear Predictive HMM for Vector Valued Observations
with Applications to Speech Recognition}},
   journal   = {IEEE Trans. on Acoustics, Speech and Signal Processing},
   year      = {1990},
   volume    = {38},
   pages     = {220-225}
}


@article{kimeldorf-wahba-70,
   author    = {Kimeldorf, G.  and Wahba, G.},
   title     = {{A correspondence between Bayesian estimation of stochastic
                processes and smoothing by splines}},
   journal   = {Annals of {Math.} Statistics},
   year      = {1970},
   volume    = {41},
   pages     = {495-502}
}

@incollection{kittler-94,
   author    = {Kittler, J.},
   title     = {Statistical pattern recognition in image analysis},
   booktitle = {{Statistics and Images 2}},
   year      = {1994},
   publisher = {Carfax Publishing Co.},
   editor    = {Mardia, K. V.},
   pages     = {61-75}
}



@article{king-muggleton-etal-96,
   author    = {King,  R. D. and Muggleton, S. H. and others},
   title     = {{Structure-activity relationships derived by machine learning:
The use of atoms and their bond connectivities to predict mutagenicity by
inductive logic programming}},
   journal   = {{Proc. Natl. Acad. Sci}},
   year      = {1996},
   volume    = {93},
   pages     = {438-442}
}

@techreport{knoerr-88,
   author    = {Knoerr, A.},
   title     = {{Global models and natural boundaries: Theory and applications}},
   institution = {Division of Applied Mathematics, Brown University, Providence, RI},
   year      = {1988},
   number    = {{148}},
   type      = {Reports in Pattern Analysis}
}


@article{kohn-ansley-87,
   author    = {Kohn, R. and Ansley, C. F.},
   title     = {A new algorithm for spline smoothing based on
       smoothing a stochastic process},
   journal   = {SIAM J. Sci. Stat. Comput.},
   year      = {1987},
   volume    = {8(1)},
   pages     = {33-48}
}


@article{Kohonen82,
       author = "Kohonen, T.",
        title = "Self-Organized Formation of Topologically Correct Feature Maps",
      journal =  {Biological Cybernetics},
       volume =  43,
         year =  1982
}

@inproceedings{Kohonen84,
       author = {Kohonen, T. and K. M\"akisara and T. Saram\"aki},
        title = "Phonotopic Maps --- Insightful Representation of Phonological Features for Speech Recognition",
        pages = "182--185",
    booktitle = "Proceedings of the Seventh International Conference on Pattern Recognition",
      address = "Montreal 1984",
    publisher = "IEEE, New York",
         year =  1984
}

@book{Kohonen89,
       author = "Kohonen, T.",
        title = "Self-Organization and Associative Memory",
       edition = "3rd",
    publisher = "Springer",
      address = "Berlin",
         year =  1989
}

@article{koltchinskii-gine-00,
   author    = {Koltchinskii, V. and Gine, E.},
   title     = {{Random matrix approximation of spectra of integral operators}},
   journal   = {Bernoulli},
   year      = {2000},
   volume    = {6(1)},
   pages     = {113-167}
}

@article{kramer-91,
   author    = {Kramer, M. A.},
   title     = {Nonlinear principal component analysis using autoassociative
neural networks},
   journal   = {AICHE Journal},
   year      = {1991},
   volume    = {37},
   pages     = {233-243}
}

@article{krishnamachari-chellappa-97,
  author        = "Krishnamachari, S. and Chellappa, R.",
  title         = {{Multiresolution Gauss-Markov random field models
                  for texture segmentation}},
  journal       = "IEEE Trans. on Image Processing",
  year          = "1997",
  volume        = "6(2)",
  pages         = {251-267}
}

@inproceedings{krogh-94,
  author        = "A. Krogh",
  title         = "Hidden Markov models for labeled sequences",
  booktitle     = "Proceedings of the 12th IAPR International 
                   Conference on Pattern Recognition",
  editor        = "",
  publisher     = "IEEE Computer Society Press",
  volume        = "",
  year          = "1994",
  pages         = "140-144"
}

@book{kruskal-wish-78,
   author    = {Kruskal, J. B. and Wish, M.},
   title     = {{Multidimensional Scaling}},
   year      = {1978},
   publisher = {Sage Publications},
   address   = {Beverly Hills}
}

@book{kullback-59,
 author = {Kullback, S.},
 title = {Information Theory and Statistics},
 address = {New York},
 publisher = {Dover},
 year = {1959}
}


@article{lades-93,
   author    = {Lades, M. and Vorbr\"{u}ggen, J. C. and Buhmann, J. and
       Lange, J. and von der Malsburg, C. and W\"{u}rtz, R. P. and Konen, W.},
   title     = {{Distortion Invariant Object Recognition in the Dynamic Link Architecture}},
   journal   = {{IEEE Trans. on Computers}},
   year      = {1993},
   volume    = {42(3)},
   pages     = {300-311}
}

@incollection{laferte-heitz-perez-fabre-95,
   author    = {Lafert\'{e}, J-M. and Heitz, F. and P\'{e}rez, P. and 
Fabre, E.},
   title     = {{Hierarchical statistical models for the fusion of multiresolution data}},
   booktitle = {Proceedings of the Fifth International Conference on Computer Vision},
   year      = {1995},
   publisher = {IEEE}
}

@article{laferte-perez-heitz-00,
   author    = {Lafert\'{e}, J-M. and P\'{e}rez, P. and Heitz, F.},
   title     = {{Discrete Markov Image Modelling and Inference on the 
Quadtree}},
   journal   = {IEEE Trans. on Image Processing},
   year      = {2000},
   volume    = {9(3)},
   pages     = {390-404}
}

@incollection{lamdan-wolfson-88,
   author    = {Lamdan, Y. and Wolfson, H. J.},
   title     = {{Geometric Hashing: A General and Efficient Model-Based Recognition Scheme}},
   booktitle = {Proceedings of the Second International Conference on Computer Vision},
   year      = {1988},
   publisher = {IEEE}
}


@incollection{lanitis-93,
   author    = {Lanitis, A. and Taylor, C. J. and Cootes, T. F.},
   title     = {A generic system for classifying variable objects using
       flexible template matching},
   booktitle = {Proceedings of the British Machine Vision Conference},
   year      = {1993},
   editor    = {Illingworth, J.},
   publisher = {BMVA Press},
   pages     = {329-338},
   volume    = {volume 1}
}

@book         {lauritzen-96,
  author    = "Lauritzen, S. L.",
  title     = "{Graphical Models}",
  publisher = "Oxford University Press",
  year      = "1996"
}

@article{lawley-56,
   author    = {Lawley, D. N.},
   title     = {{Tests of Significance for the Latent Roots of Covariance 
and Correlation  Matrices}},
   journal   = {Biometrika},
   year      = {1956},
   volume    = {43(1/2)},
   pages     = {128-136}
}

@article{lee-seung-99,
   author    = {Lee, D. D. and Seung, H. S.},
   title     = {{Learning the parts of objects by non-negative
matrix factorization}},
   journal   = {Nature},
   year      = {1999},
   volume    = {401},
   pages     = {788-791}
}

@article{levine-nazif-85,
  author        = "Levine, M. D. and Nazif, A. M.",
  title         = "Dynamic Measurement of Computer Generated Image Segmentations",
  journal       = "IEEE Trans. Pattern Analysis and Machine Intelligence",
  year          = "1985",
  volume        = "7(2)",
  pages         = {155-164}
}


@incollection{leung-burl-perona-95,
   author    = {Leung, T. K. and Burl, M. C. and Perona, P.},
   title     = {{Finding Faces in Cluttered Scenes using Random Labelled
       Graph Matching}},
   booktitle = {Proceedings of the Fifth International Conference on Computer Vision},
   year      = {1995},
   publisher = {IEEE}
}


@article{li-90,
   author    = {Li, W.},
   title     = {{Mutual Information Functions versus Correlation Functions}},
   journal   = {Journal of Statistical Physics},
   year      = {1990},
   volume    = {60(5/6)},
   pages     = {823-837}
}

@book{lillesand-kiefer-94,
  author    = "{Lillesand, T. M. and Kiefer, R. W.}",
  title     = "{Remote Sensing and Image Interpretation}",
  publisher = "Wiley",
  year      = "1994",
  address   = {New York},
  edition   = {third}
}                                      

@article{lindley-smith-72,
   author    = {Lindley, D. V. and Smith, A. F. M.},
   title     = {{Bayes Estimates for the Linear Model}},
   journal   = {{Journal of the Royal Statistical Society B}},
   year      = {1972},
   volume    = {34(1)},
   pages     = {1-18}
}


@article{lowe-95,
   author    = {Lowe, D. G.},
   title     = {{Similarity Metric Learning for a Variable-Kernel Classifier}},
   journal   = {{Neural Computation}},
   year      = {1995},
   volume    = {7(1)}
}

@article{lucke-95,
   author    = {Lucke, H.},
   title     = {{Bayesian Belief Networks as a tool for stochastic parsing}},
   journal   = {{Speech Communication}},
   year      = {1995},
   volume    = {16},
   pages     = {89-118}
}

@book{luenberger-84,
       author = "Luenberger, D. G.",
        title = {{Linear and nonlinear programming}},
         note = {2nd ed.},
    publisher = "Addison-Wesley",
    address   = {Reading, MA},
         year =  1984
}

@article{luettgen-karl-willsky-94,
   author    = {Luettgen, M. R. and Karl, W. and Willsky, A. S.},
   title     = {{Efficient multiscale regularization with applications to the computation of optical flow}},
   journal   = {{IEEE Trans. Image Processing}},
   year      = {1994},
   volume    = {3},
   pages     = {41-64}
}

@article{luettgen-willsky-95,
   author    = {Luettgen, M. R. and Willsky, A. S.},
   title     = {{Likelihood Calculation for a Class of Multiscale Stochastic Models, with Application to Texture Discrimination}},
   journal   = {{IEEE Trans. Image Processing}},
   year      = {1995},
   volume    = {4(2)},
   pages     = {194-207}
}

%Luo, Z. and Wahba, G. " Hybrid Adaptive Splines" TR 947, June 1995, slightly revised version has appeared in
%       J. Amer. Statist. Assoc., 92, 1997, pp. 107-116. 


@article{luo-wahba-97,
   author    = {Luo, Z. and Wahba, G.},
   title     = {Hybrid Adaptive Splines},
   journal   = {J.\ Amer.\ Statist.\ Assoc.}, 
   year      = {1997},
   volume    = {92},
   pages     = {107-116}
}

@article{luttrell-90,
   author    = {Luttrell, S. P.},
   title     = {Derivation of a class of training algorithms},
   journal   = {{IEEE Trans. on Neural Networks}},
   year      = {1990},
   volume    = {1(2)},
   pages     = {229-232}
}

@inproceedings{luttrell-97,
   author    = {Luttrell, S. P.},
   title     = {Partitioned Mixture Distributions: The Dynamical Case},
   booktitle = {Proceedings of the 5th IEE Conference on Artificial
                Neural Networks},
   year      = {1997},
   note      = {Held at Churchill College, Cambridge, UK}
}

@techreport{lu-mjolsness-93,
   author    = {Lu, C-P. and Mjolsness, E.},
   title     = {{Mean Field Matching by Vernier Network and by Generalized Hough Transform}},
   institution = {Department of Computer Science, Yale University},
   year      = {1993},
   number    = {{YALEU/DCS/RR-974}},
   type      = {Research Report}
}


@article{madigan-york-95,
   author    = {Madigan, D. and York, J.},
   title     = {{Bayesian Graphical Models for Discrete Data}},
   journal   = {{International Statistical Review}},
   year      = {1995},
   volume    = {63},
   pages     = {215-232}
}

@article{mccauley-engel-95,
   author    = {McCauley, J. D. and Engel, B. A.},
   title     = {{Comparison of Scene Segmentations: SMAP, ECHO and Maximum Likelihood}},
   journal   = {{IEEE Trans. on Geoscience and Remote Sensing}},
   year      = {1995},
   volume    = {33(6)},
   pages     = {1313-1316}
}

@book{mccullagh-nelder-83,
  author    = "{McCullagh, P. and Nelder, J.}",
  title     = "{Generalized Linear Models}",
  publisher = "Chapman and Hall",
  year      = "1983"
}                                      

@article{mardia-97,
  author        = "Mardia, K. V. and Baczkowski, A. J. and Feng, X. and Hainsworth, T. J.",
  title         = "Statistical methods for automatic interpretation of digitally scanned finger prints",
  journal       = "Pattern Recognition Letters",
  year          = "1997",
  volume        = "18",
  pages         = {1197-1203}
}

@book{mardia-kent-bibby-79,
  author    = {Mardia, K. V. and Kent, J. T. and Bibby, J. M.},
  title     = "{Multivariate Analysis}",
  publisher = "Academic Press",
  address   = {London},
  year      = "1979"
}                                      

@article{mardia-marshall-84,
   author    = {Mardia, K. V. and Marshall, R. J.},
   title     = {{Maximum likelihood estimation for models of residual 
       covariance in spatial regression}},
   journal   = {{Biometrika}},
   year      = {1984},
   volume    = {71(1)},
   pages     = {135-146}
}


@article{marr-nishihara-78,
   author    = {Marr, D. and Nishihara, H.~K.},
   title     = {{Representation and recognition of the spatial organization 
       of three-dimensional images}},
   journal   = {{Proceedings of the Royal Society of London, Series B}},
   year      = {1978},
   volume    = {200},
   pages     = {269-294}
}


@article{martin-pitman-91,
   author    = {Martin, G. L.  and Pitman, J. A.},
   title     = {{Recognizing Hand-Printed Letters  and Digits using Backpropagation Learning}},
   journal   = {Neural {C}omputation},
   year      = {1991},
   volume    = {3(2)},
   pages     = {258-267}
}

@article{matheron-73,
   author    = {Matheron, G.},
   title     = {{The intrinsic random functions and their applications}},
   journal   = {{Advances in Applied Probability}},
   year      = {1973},
   volume    = {5},
   pages     = {439-468}
}

@book{matern-80,
  author    = "{Mat\'{e}rn, B.}",
  title     = "{Spatial Variation}",
  publisher = "Springer",
  note      = "Lecture Notes in Statistics 36",
  edition   = {second},
  year      = "1980"
}                                      

@mastersthesis{maxwell-92,
author  =       "Maxwell,  B. A.",
title   =       "{Hidden Markov models using shared and global vector linear predictors}",
year    =       "1992",
school  =       "Cambridge University",
note    =       "Available online from
\verb+http://www.palantir.swarthmore.edu/~maxwell/speech/thesis/thesis.html+."
}

@article{mccabe-84,
  author        = "McCabe, G. P.",
  title         = "Principal Variables",
  journal       = "Technometrics",
  year          = "1984",
  volume        = "26(2)",
  pages         = {137-144}
}

@article{mckeown-harvey-mcdermott-85,
  author        = "McKeown, D. M.  Harvey, W. A.  and McDermott, J. ",
  title         = "Rule-based interpretation of aerial imagery",
  journal       = "IEEE Trans. Pattern Analysis and Machine Intelligence",
  year          = "1985",
  volume        = "7(5)",
  pages         = {570-585}
}

@article{meir-91,
   author    = {Meir, R.},
   title     = {On deriving deterministic learning rules from stochastic systems},
   journal   = {International {J}ournal of {N}eural {S}ystems},
   year      = {1991},
   volume    = {2(4)},
   pages     = {283-289}
}

@incollection{meiring-monestiez-sampson-guttorp-97,
   author    = {Meiring, W. and Monestiez, P. and Sampson, P. D. and Guttorp. P.},
   title     = {Developments in the modelling of nonstationary spatial covariance structure for space-time monitoring data},
   booktitle = {{Geostatistics Wollongong '96}},
   year      = {1997},
   publisher = {Kluwer},
   editor    = {Baafi, E. Y. and Schofield, N.},
   volume    = {1},
   pages     = {162-173}
}


@incollection{michelli-wahba-81,
   author    = {Michelli, C. A. and Wahba, G.},
   title     = {Design problems for optimal surface interpolation},
   booktitle = {{Approximation Theory and Applications}},
   year      = {1981},
   publisher = {Academic Press},
   editor    = {Ziegler, Z.},
   pages     = {329-348}
}

@book{mitchell-97,
  author    = {Mitchell, T. M.},
  title     = "{Machine Learning}",
  publisher = "McGraw-Hill",
  year      = "1997",
  address   = {New York},
}                                      

@incollection{mjolsness-92,
   author    = {Mjolsness, E.},
   title     = {{Visual Grammars and their Neural Nets}},
   booktitle = {Neural Information Processing Systems, Vol. 4},
   year      = {1992},
   editor    = {Moody, J. E. and Hanson, S. J. and Lippmann, R. E.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA}
}


@article{moller-93,
   author    = {M. M{\o}ller},
   title     = {A scaled conjugate gradient algorithm for fast supervised 
       learning},
   journal   = {Neural Networks},
   year      = 1993,
   volume    = 6,
   number    = 4,
   pages     = {525--533}
}

@article{montanvert-meer-rosenfeld-91,
   author    = {Montanvert, A. and Meer, P. and Rosenfeld, A.},
   title     = {{Hierarchical Image Analysis Using Irregular Tesselations}},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1991},
   volume    = {13(4)},
   pages     = {307-316}
}

@incollection{moody-rognvaldsson-97,
   author    = {Moody, J. E. and R\"ognvaldsson, T. S.},
   title     = {Smoothing Regularizers for Projective Basis Functions},
   booktitle = {Neural Information Processing Systems, Vol. 9},
   year      = {1997},
   editor    = {Mozer, M. C. and Jordan, M. I.  and Petsche, T.},
   publisher = {MIT Press}
}

@book         {moore-85,
  author    = "Moore, R. E.",
  title     = "{Computational Functional Analysis}",
  publisher = "Ellis Horwood",
  year      = "1985"
}                
@article{morgan-bourlard-95,
   author    = {Morgan, N. and Bourlard, H. A.},
   title     = {{Neural Networks for Statistical Recognition of
       Continuous Speech}},
   journal   = {Proceedings of the IEEE},
   year      = 1995,
   volume    = 83,
   number    = 5,
   pages     = {742-770}
}


@techreport{movellan-mcclelland-91,
   author    = {Movellan, J. R. and McClelland, J. L.},
   title     = {{Learning Continuous Probability Distributions with the Contrastive Hebbian Algorithm}},
   institution = {Department of Psychology, Carnegie Mellon University, PA},
   year      = {1991},
   number    = {{PDP.CNS.91.2}},
   type      = {Technical Report}
}

@incollection{mozer-91,
   author    = {Mozer, M. C.},
   title     = {{Discovering Discrete Distributed Representations with
Iterated Competitive Learning}},
   booktitle = {Advances in Neural Information Processing Systems 3},
   year      = {1991},
   editor    = {Lippmann, R. P. and Moody, J. E. and Touretzky, D. S.},
   publisher = {Morgan Kaufmann}
}


@article{mozer-zemel-behrmann-williams-92,
   author    = {Mozer, M. C. and Zemel, R. S. and Behrmann, M. and 
       Williams, C. K. I.},
   title     = {{Learning to segment images using dynamic feature binding}},
   journal   = {Neural Computation},
   year      = 1992,
   volume    = 4,
   number    = 5,
   pages     = {650-665}
}


@inproceedings{nabney-paven-eldridge-lee-97,
    title = {Practical Assessment of Neural Network Applications},
    booktitle = {SafeComp 97, Proceedings of the 16th International Conference
         on Computer Safety, Reliability and Security},
    publisher = {Springer},
    year = {1997},
    author = {Ian T Nabney and Mickael J S Paven and Richard C Eldridge and Clive Lee},
    editor = {Daniel, P.},
    pages  = {357-368}

}                                 

@incollection{nason-silverman-95,
   author    = {Nason, G. P. and Silverman, B. W.},
   title     = {The Stationary Wavelet Transform and some Statistical Applications},
   booktitle = {{Wavelets and Statistics}},
   year      = {1995},
   publisher = {Springer},
   editor    = {Antoniadis, A. and Oppenheim, G.},
   note      = {Lecture Notes in Statistics 103},
   pages     = {281--299}
}


@techreport{neal-93a,
   author    = {Neal, R. M.},
   title     = {Probabilistic Inference Using {Markov} Chain {Monte Carlo} Methods},
   institution = {Department of Computer Science, University of Toronto},
   year      = {1993},
   number    = {{CRG-TR-93-1}},
   type      = {Technical Report}
}


@incollection{neal-93b,
   author    = {Neal, R. M.},
   title     = {{Bayesian} Learning via Stochastic Dynamics},
   booktitle = {Neural Information Processing Systems, Vol. 5},
   year      = {1993},
   editor    = {Hanson, S. J. and Cowan, J. D. and Giles, C. L.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA},
   pages     = {475-482}
}


@phdthesis{neal-95,
   author    = {Neal, R. M.},
   title     = {{Bayesian Learning for Neural Networks}},
type={PhD},
   year      = {1995},
   school    = {Dept. of Computer Science, University of Toronto}
}

@book{neal-96,
  author    = "{Neal, R. M.}",
  title     = "{Bayesian Learning for Neural Networks}",
  publisher = "Springer",
  note      = "Lecture Notes in Statistics 118",
  year      = "1996",
  address   = {New York}
}                                      

@techreport{neal-97,
   author    = {Neal, R. M.},
   title     = {{Monte Carlo Implementation of Gaussian Process Models
                 for Bayesian Regression and Classification}},
   year      = {1997},
   note      = {Available from \verb+http://www.cs.toronto.edu/~radford/+},
   institution = {Department of Statistics, University of Toronto},
   number    = {{9702}}
}


@incollection{neal-98,
   author    = {Neal, R. M.},
   title     = {{Regression and classification using Gaussian process priors (with discussion)}},
   booktitle = {{Bayesian statistics 6}},
   editor    = {Bernardo, J. M and others},
   year      = {1998},
   publisher = {Oxford University Press},
   pages     = {475-501}
}



@article{nickels-hutchinson-97,
   author    = {Nickels, K. M. and Hutchinson, S.},
   title     = {{Textured image segmentation: returning multiple solutions}},
   journal   = {{Image and Vision Computing}},
   year      = {1997},
   volume    = {15},
   pages     = {781-795}
}

@article{ohagan-78,
   author    = {O'Hagan, A.},
   title     = {{Curve Fitting and Optimal Design for Prediction
       (with discussion)}},
   journal   = {{Journal of the Royal Statistical Society B}},
   year      = {1978},
   volume    = {40(1)},
   pages     = {1-42}
}

@BOOK{ohta-85,
  author        = "Ohta, Yuichi",
  title         = "Knowledge-based Interpretation of Outdoor 
                   Natural Colour Scenes",
  year          = "1985",
  address       = "London",
  publisher     = "Pitman Publishing Limited"
}

@article{olshausen-field-96,
   author    = {Olshausen, B. A. and Field, D. J.},
   title     = {{Emergence of simple-cell receptive field properties by
learning a sparse code for natural images}},
   journal   = {Nature},
   year      = {1996},
   volume    = {381},
   pages     = {607-609}
}


@article{osullivan-yandell-raynor-86,
   author    = {O'Sullivan, F. and Yandell, B. S. and Raynor, W. J.},
   title     = {{Automatic Smoothing of Regression Functions in 
                 Generalized Linear Models}},
   journal   = {{Journal of the American Statistical Association}},
   year      = {1986},
   volume    = {81},
   pages     = {96-103}
}


@article{plate-95,
   author    = {Plate, T. A.},
   title     = {{Holographic Reduced Representations}}, 
   journal   = {{IEEE Trans. on Neural Networks}},
   year      = {1995},
   volume    = {6(3)},
   pages     = {623-641}
}

@book{papoulis-91,
   author    = {Papoulis, A.},
   title     = {Probability, Random Variables, and Stochastic Processes},
   year      = {1991},
   publisher = {McGraw-Hill},
   address   = {New York},
   note      = {Third Edition}
}
		  
@book{pavlidis-77,
   author    = {Pavlidis, T.},
   title     = {{Structural Pattern Recognition}},
   year      = {1977},
   publisher = {Springer},
   address   = {New York}
}

@book{pearl-88,
   author    = {Pearl, J.},
   title     = {{Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference}},
   year      = {1988},
   publisher = {Morgan Kaufmann},
   address   = {San Mateo, CA}
}


@article{penny-roberts-99,
   author    = {Penny, W. D. and Roberts, S. J.},
   title     = {Dynamic models for nonstationary signal segmentation},
   journal   = {Computers and Biomedical Research},
   year      = {1999},
   volume    = {32(6)},
   pages     = {483-502}
}

@article{pentland-89,
   author    = {Pentland, A.},
   title     = {Part segmentation for object recognition},
   journal   = {Neural Computation},
   year      = {1989},
   volume    = {1},
   pages     = {82-91}
}


@article{pentland-sclaroff-91,
   author    = {Pentland, A. and Sclaroff, S.},
   title     = {{Closed-Form Solutions for Physically Based Shape Modelling 
       and Recognition}},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1991},
   volume    = {13(7)},
   pages     = {715-729}
}

@article{perez-chardin-laferte-00,
   author    = {P\'{e}rez, P. and Chardin, A. and Lafert\'{e}, J-M.},
   title     = {{Noniterative manipulation of discrete energy-based models
       for image analysis}},
   journal   = {Pattern Recognition},
   year      = {2000},
   volume    = {33(4)},
   pages     = {573-586}
}


@techreport{poggio-voorhees-yuille-85,
   author    = {Poggio, T. and Voorhees, H. and Yuille, A.},
   title     = {{A Regularized Solution to Edge Detection}},
   institution = {MIT AI Laboratory},
   year      = {1985},
   number    = {AI Memo 833}
}

@article{poggio-edelman-90,
   author    = {Poggio, T. and Edelman, S.},
   title     = {A network that learns to recognize three-dimensional objects},
   journal   = {Nature},
   year      = {1990},
   volume    = {343},
   pages     = {263-266}
}

@article        (poggio-girosi-90,
key      =      "Poggio",
author   =      "Poggio, T. and Girosi, F.",
title    =      "Networks for approximation and learning",
journal  =      "Proceedings of IEEE",
year     =      "1990",
volume   =      "78",
pages    =      "1481-1497"
)                                            

@inproceedings{pope-lowe-93,
   author    = {Pope, A. R. and Lowe, D. G.},
   title     = {Learning 3D Object Recognition Models from 2D Images},
   booktitle = {AAAI Fall 1993 Symposium on Machine
       Learning in Computer Vision},
   year      = {1993},
   pages     = {35-39},
   note      = {Proceedings available as AAAI Tech Report FSS-93-04}
}

@book         {pratt-78,
  author    = "Pratt, W. K.",
  title     = "{Digital Image Processing}",
  publisher = "John Wiley and Sons",
  year      = "1978"
}                

@book{press-etal-92,
   author    = {Press, W. H. and Teukolsky, S. A. and Vetterling,
       W. T. and Flannery, B. P.},
   title     = {{Numerical Recipes in C}},
   year      = {1992},
   publisher = {Cambridge University Press},
   edition   = {{Second}}
}

@incollection{qazaz-williams-bishop-97,
   author    = {Qazaz, C. S. and Williams, C. K. I. and Bishop, C. M.},
   title     = {{n Upper Bound on the Bayesian Error Bars for Generalized Linear Regression}},
   year      = {1997},
   booktitle = {Mathematics of Neural Networks: Models, Algorithms and Applications},
   publisher = {Kluwer},
   editor    = {Ellacott, S. W. and Mason, J. C. and Anderson, I. J.},
}

@article        (quinlan-86,
author   =      "Quinlan, J. R.",
title    =      {{Induction of Decision Trees}},
journal  =      "Machine Learning",
year     =      "1986",
volume   =      "1(1)",
pages    =      "81-106"
)                                            

@inproceedings{quinlan-93,
   author    = {Quinlan, J. R.},
   title     = {{Combining Instance-Based and Model-Based Learning}},
   booktitle = {Proc. ML'93},
   year      = {1993},
   editor    = {Utgoff, P. E.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA}
}

@article        (rabiner-89,
author   =      "Rabiner, L. R.",
title    =      {{A Tutorial on Hidden Markov Models and Selected Applications
                 in Speech Recognition}},
journal  =      "Proceedings of IEEE",
year     =      "1989",
volume   =      "77(2)",
pages    =      "257-285"
)                                            

@incollection{rasmussen-96,
   author    = {Rasmussen, C. E.},
   title     = {{A Practical {M}onte {C}arlo Implementation of {B}ayesian Learning}},
   booktitle = {Advances in Neural Information Processing Systems 8},
   year      = {1996},
   editor    = {Touretzky, D. S. and Mozer, M. C. and Hasselmo, M. E.},
   publisher = {MIT Press}
}

@phdthesis{rasmussen-phd-96,
   author    = {Rasmussen, C. E.},
   title     = {{Evaluation of {G}aussian Processes and Other Methods for Non-linear Regression}},
type={PhD},
   year      = {1996},
   note      = {Available from \verb+http://www.cs.utoronto.ca/~carl/+.},
   school    = {Dept. of Computer Science, University of Toronto}
}

@unpublished{rasmussen-02,
   author    = {Rasmussen, C. E.},
   title     = {Reduced Rank {G}aussian Process Learning},
   year      = {2002},
   note      = {Unpublished manuscript}
}

@inproceedings{rasmussenIGMM,
title={The Infinite {G}aussian Mixture Model},
author={Carl Edward Rasmussen},
abstract={
In a Bayesian mixture model it is not necessary a priori to limit the number of components to be finite. In this paper an infinite Gaussian mixture model is presented which neatly sidesteps the difficult problem of finding the ``right'' number of mixture components. Inference in the model is done using an efficient parameter-free Markov Chain that relies entirely on Gibbs sampling.
},
annote={Advances in Neural Information Processing Systems 12, S.A. Solla, T.K. Leen and K.-R. M\"uller (eds.), pp. 554-560, MIT Press (2000).},
pages={554-560},
booktitle={Advances in Neural Information Processing Systems 12},
editor={S.A. Solla and T.K. Leen and K.-R. M\"uller}, 
publisher={MIT Press},
year={2000}
}


@incollection{rasmussen-ghahramani-02,
   author    = {Rasmussen, C. E. and Ghahramani, Z.},
   title     = {Infinite Mixtures of {G}aussian Process Experts},
   booktitle = {Advances in Neural Information Processing Systems 14},
   year      = {2002},
   editor    = {Diettrich, T. G. and Becker, S. and Ghahramani, Z.},
   publisher = {MIT Press},
}


@inproceedings{revow-williams-hinton-93,
   author    = {Revow, M. D. and Williams, C. K. I. and Hinton, G. E.},
   title     = {{Using mixtures of deformable models to capture variations in hand printed digits}},
   booktitle = {Proceedings of the Third International Workshop on Frontiers in Handwriting Recognition},
   year      = {1993},
   editor    = {Srihari, S.},
   address   = {Buffalo, New York, USA},
   pages     = {142-152}
}


@article{revow-williams-hinton-96,
   author    = {Revow, M. and Williams, C. K. I. and Hinton, G. E.},
   title     = {{Using Generative Models for Handwritten Digit Recognition}},
   year      = {1996},
   journal   = {IEEE Trans. on Pattern Analysis and Machine Intelligence},
   volume    = {18(6)},
   pages     = {592-606}
}

@article{richard-lippmann-91,
  author        = "Richard, M. D. and R. P. Lippmann",
  title         = "Neural network classifiers estimate Bayesian
                  a-posteriori probabilities",
  journal       = "Neural Computation",
  year          = "1991",
  volume        = "3 (4)",
  pages         = {461-483}
}

@article{richardson-green-97,
  author        = "Richardson, S. and Green, p.",
  title         = "On Bayesian analysis of mixtures with an unknown
                   number of components",
  journal       = "Journal of the Royal Statistical Society, B",
  year          = "1997",
  volume        = 59,
  pages         = {731-792}
}                 

@inproceedings{riis-krogh-97,
  author        = "Riis, S. K. and Krogh, A.",
  title         = "Hidden neural networks: a framework for 
                   {HMM/NN} hybrids",
  booktitle = "Proceedings ICASSP-97, April 21-24, Munich, Germany",
  editor    = "",
  publisher = "",
  volume    = "",
  year      = "1997",
  pages     = ""
}

@book{ripley-81,
   author    = {Ripley, B.},
   title     = {{Spatial Statistics}},
   year      = {1981},
   publisher = {Wiley}
}


@incollection{ripley-93,
   author    = {Ripley, B. D.},
   title     = {{Statistical aspects of neural networks}},
   booktitle = {Networks and Chaos---Statistical and Probabilistic Aspects},
   year      = {1993},
   editor    = {Barndorff-Nielsen, O. E. and Jensen, J. L. and Kendall,  W. S.},
   publisher = {Chapman and Hall},
   pages     = {40-123}
}

@incollection{ripley-94,
   author    = {Ripley, B. D.},
   title     = {{Flexible Non-linear Approaches to Classification}},
   booktitle = {From Statistics to Neural Networks},
   year      = {1994},
   editor    = {Cherkassy, V. and Friedman, J. H. and Wechsler, H.},
   publisher = {Springer},
   pages     = {105-126}
}
		  
@book{ripley-96,
   author    = {Ripley, B.},
   title     = {{Pattern Recognition and Neural Networks}},
   year      = {1996},
   publisher = {Cambridge University Press},
   address   = {Cambridge, UK}
}

@incollection{rissanen-85,
   author    = {Rissanen, J.},
   title     = {{Minimum description length principle}},
   booktitle = {Encyclopedia of Statistical Sciences vol. 5},
   year      = {1985},
   editor    = {Kotz, S. and Johnson, N. L.},
   publisher = {Wiley and Sons}
}


@article{ritter-wasilkowski-wozniakowski-95,
   author    = {Ritter, K. and Wasilkowski, G. W. and
                Wo\'{z}niakowski, H.},
   title     = {{Multivariate integration and approximation of 
random fields satisfying Sacks-Ylvisaker conditions}},
   journal   = {{Annals of  Applied Probability}},
   year      = {1995},
   volume    = {5},
   pages     = {518-540}
}

@article{ritter-96,
   author    = {Ritter, K.},
   title     = {{Almost Optimal Differentiation Using Noisy Data}},
   journal   = {{J. Approximation Theory}},
   year      = {1996},
   volume    = {86},
   pages     = {293-309}
}

@book{ritter-00,
   author    = {Ritter, K.},
   title     = {{Average-Case Analysis of Numerical Problems}},
   year      = {2000},
   publisher = {Springer}
}

@misc{rohwer-morciniec-96,
   author    = {Rohwer, R. J. and Morciniec, M.},
   title     = {{Estimation of sub-optimality}},
   year      = {1996},
   note      = {Submitted to NIPS*96}
}		  

@article{ronen-rohlicek-ostendorf-95,
   author    = {Ronen, O. and Rohlicek, J. R. and Ostendorf, M.},
   title     = {{Parameter Estimation of Dependence Tree Models Using the
EM ALgorithm}},
   journal   = {{IEEE Signal Processing Letters}},
   year      = {1995},
   volume    = {2(8)},
   pages     = {157-159}
}

@incollection{rowe-blake-95,
   author    = {Rowe, S. and Blake, A.},
   title     = {{Statistical Background Modelling For Tracking With A
Virtual Camera}},
   booktitle = {Proceedings of the 6th British Machine Vision Conference},
   year      = {1995},
   editor    = {Pycock, D.},
   publisher = {BMVA Press},
   pages     = {423-432},
   volume    = {volume 2}
}


@article{rubin-thayer-82,
   author    = {Rubin, D. B. and Thayer, D. T.},
   title     = {{EM Algorithms for ML Factor Analysis}},
   journal   = {{Psychometrika}},
   year      = {1982},
   volume    = {47(1)},
   pages     = {69-76}
}

@article{sacks-welch-mitchell-wynn-89,
   author    = {Sacks, J. and Welch, W. J. and Mitchell, T. J. and Wynn,
                H. P.},
   title     = {{Design and Analysis of Computer Experiments}},
   journal   = {{Statistical Science}},
   year      = {1989},
   volume    = {4(4)},
   pages     = {409-435}
}
		  
@inproceedings{sakoe-chiba-71,
   author    = {Sakoe, H. and Chiba, S.},
   title     = {{A Dynamic Programming Approach to Continuous Speech Recognition}},
   booktitle = {Proc. Intl. Congress on Acoustics},
   year      = {1971},
   address   = {Budapest, Hungary}
}


@incollection{sallans-hinton-ghahramani-98,
   author    = {Sallans, B. and Hinton, G. E. and Ghahramani, Z.},
   title     = {{A Hierarchical Community of Experts}},
   booktitle = {Neural Networks and Machine Learning},
   year      = {1998},
   editor    = {Bishop, C. M.},
   publisher = {Springer}
}

@article{sammon-69,
   author    = {Sammon, J. W.},
   title     = {{A nonlinear mapping for data structure analysis}},
   journal   = {{IEEE Trans. on Computers}},
   year      = {1969},
   volume    = {18},
   pages     = {401-409}
}

@article{sampson-guttorp-92,
   author    = {Sampson, P. D. and Guttorp, P.},
   title     = {{Nonparametric estimation of nonstationary covariance 
                structure}},
   journal   = {{Journal of the American Statistical Association}},
   year      = {1992},
   volume    = {87},
   pages     = {108-119}
}

@article{sanger-89,
   author    = {Sanger, T. D.},
   title     = {{Optimal unsupervised learning in a single-layer linear 
feedforward neural network}},
   journal   = {{Neural Networks}},
   year      = {1989},
   volume    = {2},
   pages     = {459-473}
}

@incollection{saul-jordan-96,
   author    = {Saul, L. K. and Jordan, M .I.},
   title     = {{Exploiting tractable substructures in intractable networks}},
   booktitle = {Advances in Neural Information Processing Systems 8},
   year      = {1996},
   editor    = {Touretzky, D. S. and Mozer, M. C. and Hasselmo, M. E.},
   publisher = {MIT Press},
   address   = {Cambridge, MA}
}

@incollection{saul-jordan-98,
	author = "Saul, L. and Jordan, M. I.",
	title  = "A Mean Field Learning Algorithm for Unsupervised Neural Networks",
	booktitle = "Learning in Graphical Models",
	editor = "Jordan, M. I.",
	publisher = "Kluwer",
	year   = "1998",
	pages  = "541-554"
}

@article{saund-95,
   author    = {Saund, E.},
   title     = {{A multiple cause mixture model for unsupervised learning}},
   journal   = {{Neural Computation}},
   year      = {1995},
   volume    = {7},
   part      = {1},
   pages     = {51-71}
}
   
@techreport{schoelkopf-shawe-taylor-smola-williamson-99,
   author    = {Sch\"{o}lkopf, B. and Shawe-Taylor, J. and Smola, A. J. and
Williamson, R. C.},
   title     = {{Generalization bounds via eigenvalues of the Gram matrix}},
   institution = {},
   year      = {1999},
   number    = {NC2-TR-1999-035},
   note      = {Available from \verb+http://www.neurocolt.com+.}
}



@article{SchMikBurKniMulRatSmo99,
   author    = {Sch\"{o}lkopf, B. and Mika, S. and Burges, C. J. C. and others},
   title     = {{Input space vs feature space in kernel-based methods}},
   journal   = {{IEEE Trans. on Neural Networks}},
   year      = {1999},
   volume    = {10(5)},
   pages     = {1000-1017}
}

@article{SchSmoMue98,
   author    = "B.~{Sch\"olkopf} and A.~Smola and K.-R.~{M\"uller}",
   title     = "Nonlinear component analysis as a kernel Eigenvalue problem",
   journal =     {Neural Computation},
   volume    = 10,
   issue     = 5,
   pages     = "1299-1319",
   year      = 1998}

@book{schoelkopf-smola-02,
   author    = {Sch\"{o}lkopf, B. and A. Smola}, 
   title     = {{Learning with Kernels}},
   year      = {2002},
   publisher = {MIT Press}
}

@book{scott-92,
   author    = {Scott, D. W.},
   title     = {{Multivariate Density Estimation}},
   year      = {1992},
   publisher = {Wiley}
}

@book         {serra-82,
  author    = "Serra, J.",
  title     = "{Image Analysis and Mathematical Morphology}",
  publisher = "Academic Press",
  year      = "1982"
} 

@incollection{seeger-00,
   author    = {Seeger, M.},
   title     = {{Bayesian model selection for support vector machines,
Gaussian Processes and other kernel classifiers}},
   booktitle = {{Advances in Neural Information Processing Systems 12}},
   year      = {2000},
   editor    = {Solla, S. A. and Leen, T. K. and M\"{u}ller, K.-R.},
   publisher = {MIT Press},
   address   = {Cambridge, MA}
}

@incollection{seeger-williams-lawrence-03,
   author    = {Seeger, M. and Williams, C. K. I. and Lawrence, N.},
   title     = {Fast Forward Selection to Speed Up Sparse {G}aussian Process Regression},
   booktitle = {{Proceedings of the Ninth International Workshop
on Artificial Intelligence and Statistics}},
   editor    = {Bishop, C.M. and Frey, B. J.},
   year      = {2003},
ISBN={ 0-9727358-0-1},
publisher={Society for Artificial Intelligence and Statistics}
}

@article{shams-vdm-99,
   author    = {Shams, L. and von der Malsburg, C.},
   title     = {Are object shape primitives learnable?},
   journal   = {Neurocomputing},
   year      = {1999},
   volume    = {26-27},
   pages     = {855-863}
}
               

@incollection{shawe-taylor-cristianini-kandola-02,
   author    = {Shawe-Taylor, J. and Cristianini, N. and Kandola, J.},
   title     = {{On the Concentration of Spectral Properties}},
   booktitle = {Advances in Neural Information Processing Systems 14},
   year      = {2002},
   editor    = {Diettrich, T. G. and Becker, S. and Ghahramani, Z.},
   publisher = {MIT Press},
}



@techreport{shawe-taylor-williams-cristianini-kandola-03,
   author    = {Shawe-Taylor, J. and Williams, C. K. I. and Cristianini, N. and Kandola, J.},
   title     = {{On the Eigenspectrum of the Gram Matrix and the
		  Generalisation Error of Kernel PCA}},
   institution = {Dept of Computer Science, Royal Holloway, University of 
                 London},
   year      = {2003}
}

@article{silverman-78,
   author    = {Silverman, B. W.},
   title     = {{Density Ratios, Empirical Likelihood and Cot Death}},
   journal   = {{Applied Statistics}},
   year      = {1978},
   volume    = {27(1)},
   pages     = {26-33}
}

@article{silverman-84,
   author    = {Silverman, B. W.},
   title     = {{Spline Smoothing: The Equivalent Variable Kernel Method}},
   journal   = {{Annals of Statistics}},
   year      = {1984},
   volume    = {12(3)},
   pages     = {898-916}
}

@article{silverman-85,
   author    = {Silverman, B. W.},
   title     = {{Some aspects of the spline smoothing approach to 
       non-parametric regression curve fitting (with discussion)}},
   journal   = {{J. Roy. Stat. Soc. B}},
   year      = {1985},
   volume    = {47(1)},
   pages     = {1-52}
}

@incollection{skilling-93,
   author    = {Skilling, J.},
   title     = {Bayesian numerical analysis},
   booktitle = {Physics and Probability},
   year      = {1993},
   editor    = {Grandy, Jr., W. T. and  Milonni, P.},
   publisher = {Cambridge University Press}
}


@inproceedings{smola-schoelkopf-00,
   author    = {Smola, A. J. and Sch\"{o}lkopf, B.},
   title     = {{Sparse Greedy Matrix Approximation for Machine Learning}},
   booktitle = {{Proceedings of the Seventeenth 
International Conference on Machine Learning}},
   publisher = {Morgan Kaufmann},
   year      = {2000}
}

@incollection{smola-bartlett-01,
   author    = {Smola, A. J. and Bartlett, P.},
   title     = {{Sparse Greedy Gaussian Process Regression}},
   booktitle = {{Advances in Neural Information Processing Systems 13}},
   year      = {2001},
   pages     = {619-625},
   editor    = {Leen, T. K. and Diettrich, T. G. and Tresp, V.},
   publisher = {MIT Press}
}

@article{smyth-94,
   author    = {Smyth, P.},
   title     = {{Hidden Markov models for fault detection in dynamic systems}},
   journal   = {{Pattern Recogntion}},
   year      = {1994},
   volume    = {27(1)},
   pages     = {149-164}
}

@incollection{sollich-99,
   author    = {Sollich, P.},
   title     = {{Learning curves for Gaussian processes}},
   booktitle = {Neural Information Processing Systems, Vol. 11},
   year      = {1999},
   editor    = {Kearns, M. S. and Solla, S. A. and Cohn, D. A.},
   publisher = {MIT Press}
}
@article{ mykland95regeneration,
    author = "Per Mykland and Luke Tierney and Bin Yu",
    title = "Regeneration in {Markov} Chain Samplers",
    journal = "Journal of the American Statistical Association",
    volume = "90",
    number = "429",
    pages = "233--241",
    year = "1995",
    url = "citeseer.nj.nec.com/mykland94regeneration.html" }


@article{dawidMarg,
annote={Marginalization paradoxes in Bayesian and structural inference (Dawid, A.P,  M. Stone and  J. V. Zidek).  With discussion.  J. Roy. Statist. Soc. B 35 (1973), 189-233.},
title={Marginalization paradoxes in {Bayesian} and structural inference},
author={Dawid, A.P. and M. Stone and J.V. Zidek},
note={With discussion},
journal={J.\ Roy.\ Statist.\ Soc.\ B},
volume={35},
year={1973},
pages={189-233}
}

@techreport{dawidJaynes,
title={Critique of {E.T~Jaynes}'s `Paradoxes of probability theory'},
author={Dawid, A.P. and M. Stone and J.V. Zidek},
year={1996},
annote={Dawid, A.P., M. Stone and J.V. Zidek (1996) Critique of E.T. Jaynes's `Paradoxes of Probability Theory '. Research report 172, Department of Statistical Science, University College London. Available at http:// www.ucl.ac.uk/ Stats/ research/ abstracts.html },
url={http://www.ucl.ac.uk/Stats/research/abstracts.html},
number={172},
institution={Department of Statistical Science, University College London.}
}

article{MCMCRegeneration,
title={Adaptive {Markov} chain {Monte Carlo} through Regeneration},
author={Gilks, W. R. and Roberts, G. O. and Sahu, S. K.},
annote={Walter R. Gilks, Gareth O. Roberts, and Sujit K. Sahu,
Adaptive Markov Chain Monte Carlo Through Regeneration
},
abstract={
Markov chain Monte Carlo (MCMC) is used for evaluating expectations of functions of interest under a target distribution p. This is done by calculating averages over the sample path of a Markov chain having p as its stationary distribution. For computational efficiency, the Markov chain should be rapidly mixing. This sometimes can be achieved only by careful design of the transition kernel of the chain, on the basis of a detailed preliminary exploratory analysis of p. An alternative approach might be to allow the transition kernel to adapt whenever new features of p are encountered during the MCMC run. However, if such adaptation occurs infinitely often, then the stationary distribution of the chain may be disturbed. We describe a framework, based on the concept of Markov chain regeneration, which allows adaptation to occur infinitely often but does not disturb the stationary distribution of the chain or the consistency of sample path averages.
},
journal={J.A.S.A.},
Volume=93, Number=443,
month={September},
year={1998},
pages={1045-1054}
}

@article{spiegelhalter-dawid-lauritzen-cowell-93,
   author    = {Spiegelhalter, D. J. and Dawid, A. P. and Lauritzen,
       S. L. and Cowell, R. G.},
   title     = {{Bayesian Analysis in Expert Systems}},
   journal   = {{Statistical Science}},
   year      = {1993},
   volume    = {8(3)},
   pages     = {219-283}
}


@book{steeb-91,
   author    = {Steeb, W-H.},
   title     = {{Kronecker product of matrices and applications}},
   year      = {1991},
   publisher = {Mannheim : B.I. Wissenschaftsverlag}
}

@article{stein-91,
   author    = {Stein, M.},
   title     = {A kernel approximation to the kriging predictor of a
		  spatial process},
   journal   = {Ann.\ Inst.\ Statist.\ Math},
   year      = {1991},
   volume    = {43},
number={1},
   pages     = {61-75}
}



@book{stewart-sun-90,
   author    = {Stewart, G. W. and Sun, J.},
   title     = {Matrix Perturbation Theory},
   year      = {1990},
   publisher = {Academic Press},
   address   = {San Diego, CA}
}

@inproceedings{storkey-00,
    title = {{Dynamic Trees: A Structured Variational Method Giving 
Efficient Propagation Rules}},
    booktitle = {{Proceedings of the Sixteenth Conference on 
Uncertainty in Artificial Intelligence}},
    year = {2000},
    author = {Storkey, A. J.},
   publisher = {Morgan Kaufmann},
    EDITOR    = {C. Boutilier and M. Goldszmidt},
    PAGES     = {566-573}
}

@inproceedings{storkey-williams-01a,
    title = {Dynamic Positional Trees for Structural Image Analysis},
    booktitle = {{Proceedings of the Eighth
International Workshop on Artificial Intelligence and Statistics}},
    year = {2001},
    author = {Storkey, A. and Williams, C. K. I.},
   publisher = {Morgan Kaufmann},
    EDITOR    = {T. Jaakkola and T. Richardson},
    PAGES     = {298-304}
}                                 


@misc{storkey-williams-01b,
    author = {Storkey, A. and Williams, C. K. I.},
   title     = {{Image Modelling with Position-Encoding Dynamic Trees}},
   year      = {2001},
   note      = {Submitted to \emph{IEEE Trans Pattern Analysis and
Machine Intelligence}, Nov 2001}
}

@inproceedings{szeliski-87,
   author    = {Szeliski, R.},
   title     = {{Regularization uses Fractal Priors}},
   booktitle = {{Proceedings of the 6th National Conference on
		  Artificial Intelligence (AAAI-87)}},
   year      = {1987}
}

@book{szeliski-89,
   author    = {Szeliski, R.},
   title     = {{Bayesian modeling of uncertainty in low-level vision}},
   year      = {1989},
   publisher = {Kluwer}
}

@inproceedings{tao-sawhney-kumar-00,
   author    = {Tao, H. and Sawhney, H. S. and Kumar, R.},
   title     = {{Dynamic Layer Representation with Applications to Tracking}},
   booktitle = {{Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}},
   year      = {2000}
}


@article{tappert-suen-wakahara-90,
   author    = {Tappert, C. C. and Suen, C. Y. and Wakahara, T.},
   title     = {{The State of the Art in On-Line Handwriting Recognition}},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1990},
   volume    = {12(8)},
   pages     = {787-808}
}


@inproceedings{taubin-92,
   author    = {Taubin, G. and Cukierman, F. and Sullivan, S. and Ponce, J. 
       and Kriegman, D. J.},
   title     = {{Parameterizing and fitting bounded algebraic curves and 
       surfaces}},
   booktitle = {{Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}},
   year      = {1992}
}


@article{terzopoulos-86a,
   author    = {Terzopoulos, D.},
   title     = {{Image Analysis Using Multigrid Relaxation Methods}},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1986},
   volume    = {8(2)},
   pages     = {129-139}
}


@article{terzopoulos-86b,
   author    = {Terzopoulos, D.},
   title     = {Regularization of inverse problems involving discontinuities},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1986},
   volume    = {8},
   pages     = {413-424}
}

@article{tibshirani-92,
   author    = {Tibshrani, R.},
   title     = {{Principal curves revisited}},
   journal   = {{Statistics and Computing}},
   year      = {1992},
   volume    = {2},
   pages     = {183-190}
}

@article{tierney-94,
   author    = {Tierney, L.},
   title     = {Markov chains for exploring posterior distributions
       (with discussion)},
   journal   = {Annals of Statistics},
   year      = {1994},
   volume    = {22},
   pages     = {1701-1762}
}

@article{tipping-bishop-99,
   author    = {Tipping. M. E. and Bishop. C. M.},
   title     = {Probabilistic principal components analysis},
   journal   = {J. Roy. Statistical Society B},
   year      = {1999},
   volume    = {61(3)},
   pages     = {611-622}
}


@techreport{thomas-agnan-93,
   author    = {Thomas-Agnan, C.},
   title     = {Computing a family of reproducing kernels for
		  statistical applications},
   institution = {Dept. of Statistics, University of Wisconsin},
   year      = {1993},
   number    = {{908}}
}

@article{thomas-agnan-96,
   author    = {Thomas-Agnan, C.},
   title     = {Computing a family of reproducing kernels for
		  statistical applications},
   journal   = {Numerical Algorithms},
   volume    = {13},
   pages     = {21-32},
   year      = {1996}
}

@BOOK{tikhonov-arsenin-77,
  author        = "Tikhononv, A. N. and Arsenin, V. Y.",
  title         = {Solutions of Ill-posed Problems},
  year          = 1977,
  address       = "Washington, D.C.",
  publisher     = "W. H. Winston"
}

@BOOK{titterington-books85,
  author        = "D. M. Titterington, A. F. M. Smith and U. E. Makov",
  title         = "Statistical Analysis of Finite Mixture Distributions",
  year          = 1985,
  address       = "New York",
  publisher     = "Wiley"
}


@book{torn-zilinskas-89,
   author    = {T\"{o}rn, A. and \v{Z}ilinskas, A.},
   title     = {Global Optimization},
   year      = {1989},
   publisher = {Springer},
   note      = {LNCS 350}
}

@article{tresp-00,
   author    = {Tresp, V.},
   title     = {A {Bayesian} Committee Machine},
   journal   = {Neural Computation},
   year      = {2000},
   volume    = {12},
number={11},
   pages     = {2719-2741}
}


@misc{tresp-schwaighofer-01,
   author    = {Tresp, V. and Schwaighofer, A.},
   title     = {Scalable Kernel Systems},
   year      = {2001},
   note      = {Presentation at NIPS 2001 workshop on New Directions in Kernel-Based Learning Methods}
}


@article{tomasi-kanade-92,
   author    = {Tomasi, C. and Kanade, T.},
   title     = {Shape and Motion from Image Streams under Orthography: a Factorization Method},
   journal   = {International {J}ournal of {C}omputer {V}ision},
   year      = {1992},
   volume    = {9(2)},
   pages     = {137-154}
}


@article{turk-pentland-91,
   author    = {Turk, M. and Pentland, A.},
   title     = {Eigenfaces for Recognition},
   journal   = {Journal of Cognitive Neurosccience},
   year      = {1991},
   volume    = {3(1)},
   pages     = {71-86}
}

@article{turney-mudge-volz-85,
   author    = {Turney, J. L. and Mudge, T. N. and Volz, R. A.},
   title     = {Recognizing partially occluded parts},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1985},
   volume    = {7(4)},
   pages     = {410-421}
}

@Article{ullman67,
  author =       {Jeffrey D. Ullman},
  title =        {On the capabilities of codes to correct synchronization errors},
  journal =      ieeeit,
  year =         {1967},
  OPTkey =       {},
  volume =       {13},
  number =       {1},
  pages =        {95-105},
  month =        jan,
  OPTnote =      {},
  OPTannote =    {}
}
@Article{zigangirov69,
  author =       {Kamil Sh. Zigangirov},
  title =        {Sequential decoding for a binary channel with drop-outs and insertions},
  journal =      {Problemy Peredachi Informatsii},
  year =         {1969},
  OPTkey =       {},
  volume =       {5},
  number =       {2},
  pages =        {23-30},
  OPTmonth =     {},
  OPTnote =      {},
  OPTannote =    {}
}

@InProceedings{ratzer03a,
  author =       {Edward A. Ratzer},
  title = {Marker codes for channels with insertions and deletions},   
  booktitle = {3rd International Symposium on Turbo Codes and Applications},
  year =         {2003},
  month =        sep
}



@book{ullman-79,
   author    = {Ullman, S.},
   title     = {The Interpretation of Visual Motion},
   year      = {1979},
   publisher = {MIT Press}
}


@article{ullman-89,
   author    = {Ullman, S.},
   title     = {{Aligning pictorial descriptions: An approach to object
       recognition}},
   journal   = {Cognition},
   year      = {1989},
   volume    = {32},
   number    = {3},
   pages     = {193-254}
}


@article{ullman-basri-91,
   author    = {Ullman, S. and Basri, R.},
   title     = {{Recognition by Linear Combinations of Models}},
   journal   = {IEEE Trans. Pattern Analysis and Machine Intelligence},
   year      = {1991},
   volume    = {13},
   number    = {10},
   pages     = {992-1006}
}

@incollection{utans-94,
   author    = {Utans, J.},
   title     = {{Learning in Compositional Hierarchies: Inducing the 
Structure of Objects from Data}},
   booktitle = {Neural Information Processing Systems, Vol. 6},
   year      = {1994},
   pages     = {285-292},		  
   editor    = {Cowan, J. D. and Tesauro, G. and Alspector, J.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA}
}

@article{utsugi-97,
   author    = {Utsugi, A.},
   title     = {{Hyperparameter Selection for Self-Organizing Maps}},
   journal   = {Neural Computation},
   year      = {1997},
   volume    = {9},
   number    = {3},
   pages     = {623-636}
}

@book{vapnik-95,
   author    = {Vapnik, V. N.},
   title     = {{The nature of statistical learning theory}},
   year      = {1995},
   publisher = {Springer},
   address   = {New York}
}

@incollection{vasconcelos-lippmann-99,
   author    = {Vasconcelos, N. and Lippmann, A.},
   title     = {{Learning Mixture Hierarchies}},
   booktitle = {Advances in Neural Information Processing Systems 11},
   year      = {1999},
   editor    = {Kearns, M. S. and Solla, S. A. and Cohn, D. A.},
   publisher = {MIT Press},
   pages     = {606-612}
}

@inproceedings{vivarelli-williams-97,		  
   author    = {Vivarelli, F. and Williams, C. K. I},
   title     = {{Using Bayesian neural networks to classify segmented images}},
   booktitle = {Proc. 5th IEE Conference on Artificial Neural Networks},
   year      = {1997}
}

@inproceedings{vivarelli-williams-99,		  
   author    = {Vivarelli, F. and Williams, C. K. I},
   title     = {{Discovering hidden features with Gaussian processes regression}},
   booktitle = {Advances in Neural Information Processing Systems 11},
   year      = {1999},
   editor    = {Kearns, M. S. and Solla, S. A. and Cohn, D. A.},
   publisher = {MIT Press}
}

@book{von-mises-64,
   author    = {von Mises, R.},
   title     = {{Mathematical Theory of Probability and Statistics}},
   year      = {1964},
   publisher = {Academic Press}
}

@techreport{vdM-81,
   author    = {von der Malsburg, C.},
   title     = {{The correlation theory of brain function}},
   institution = {Max-Planck-Institut f\"{u}r Biophysikalische Chemie},
   year      = {1981},
   number    = {{81-2}},
   note      = {Reprinted in \emph{Models of Neural Networks}, eds. K.
Schulten and H.-J. van Hemmen, 2nd. ed, Springer, 1994.},
   type      = {Internal Report}
}

@incollection{vdM-arbib-95,
   author    = {von der Malsburg, C.},
   title     = {Dynamic Link Architecture},
   booktitle = {Handbook of Brain Theory and Neural Networks},
   editor    = {Arbib, M. A.},
   year      = {1995},
   publisher = {MIT Press},
   pages     = {329-331}
}



@article{wahba-78,
   author    = {Wahba, G.},
   title     = {{Improper Priors, Spline Smoothing and the Problem of
       Guarding Against Model Errors in Regression}},
   journal   = {{Journal of the Royal Statistical Society B}},
   year      = {1978},
   volume    = {40(3)},
   pages     = {364-372}
}

@article{wahba-85,
   author    = {Wahba, G.},
   title     = {{A Comparison of GCV and GML for Choosing the Smoothing
   Parameter in the Generalized Spline Smoothing Problem}},
   journal   = {{Annals of Statistics}},
   year      = {1985},
   volume    = {13},
   pages     = {1378-1402}
}

@book{wahba-90,
   author    = {Wahba, G.},
   title     = {{Spline models for observational data}},
   year      = {1990},
   publisher = {Society for Industrial and Applied Mathematics},
   address   = {Philadelphia, PA},
   note      = {CBMS-NSF Regional Conference Series in Applied Mathematics}
}

@incollection  (wahba-gu-wang-chappell-95,
author     =   "Wahba, G. and Gu, C. and Wang, Y. and Chappell, R.",
title      =   "{Soft Classification, a.k.a. Risk Estimation, via Penalized 
             Log Likelihood and Smoothing Spline Analysis of Variance}",
year       =   "1995",
publisher  = "Addison-Wesley",
editor     =   "Wolpert, D. H.",
booktitle  = "{The Mathematics of Generalization}",
note       =  "{Proceedings volume XX in the Santa Fe Institute Studies
              in the Sciences of Complexity}"
)

@misc{wahba-96,
   author    = {Wahba, G.},
   title     = {{RBF's, SBF's, TreeBF's, Smoothing Spline ANOVA: Representers and pseudo-representers for a dictionary of basis functions for penalized likelihood estimates}},
   year      = {1996},
   note      = {Slides presented at the NIPS workshop on Model Complexity, December 1996. Available from \verb+http://www.stat.wisc.edu/~wahba/wahba.html+.}
}

@incollection{wahba-99,
   author    = {Wahba, G.},
   title     = {{Support Vector Machines, Reproducing Kernel Hilbert Spaces,
   and Randomized GACV}},
   booktitle = {Advances in Kernel Methods},
   year      = {1999},
   editor    = {Sch\"{o}lkopf, B. and Burges, C. J. C. and Smola, A. J.},
   publisher = {MIT Press}
}

@techreport{wang-91,
   author    = {Wang, Z.},
   title     = {{Using Complex Gabor Filters to Detect and Localize Edges and Bars}},
   institution = {Department of Computer Science, York University, Ontario},
   year      = {1991},
   number    = {{CS-91-04}},
   type      = {Technical Report}
}

@article{wang-adelson-94,
  author        = "Wang,  J. Y. A. and Adelson, E. H.",
  title         = {{Representing Moving Images with Layers}},
  journal       = "IEEE Trans. on Image Processing",
  year          = "1994",
  volume        = "3(5)",
  pages         = {625-638}
}

@article{waternaux-76,
  author        = "Waternaux, C. M.",
  title         = {{Asymptotic Distribution of the Sample Roots for a 
Nonnormal Population}},
  journal       = "Biometrika",
  year          = "1976",
  volume        = "63(3)",
  pages         = {639-645}
}



@inproceedings{weinberger-seroussi-sapiro-96,
   author    = {Weinberger, M. and Seroussi, G. and Sapiro, G.},
   title     = {{ "LOCO-I: A Low Complexity, Context-Based, Lossless Image
       Compression Algorithm}}, 
   booktitle = {Proc. IEEE Data Compression Conference},
   year      = {1996},
   note	     = {Snowbird, Utah}
}

@misc{weinberger-seroussi-sapiro-99,
   author    = {Weinberger, M. and Seroussi, G. and Sapiro, G.},
   title     = {{The LOCO-I Lossless Image Compression Algorithm: Principles
       and Standardization into JPEG-LS}},
   year      = {1999},
   note      = {Hewlett-Packard Laboratories Technical Report No. HPL-98-193R1,
       November 1998, revised October 1999. Available from 
{\tt http://www.hpl.hp.com/loco/}. To appear in
\emph{IEEE Trans. Image Processing}}
}


@incollection{weiss-freeman-00,
   author    = {Weiss, Y. and Freeman, W. T.},
   title     = {{Correctness of belief propagation in Gaussian graphical 
models of arbitrary topology}},
   booktitle = {{Advances in Neural Information Processing Systems 12}},
   year      = {2000},
   editor    = {Solla, S. A. and Leen, T. K. and M\"{u}ller, K.-R.},
   publisher = {MIT Press},
   address   = {Cambridge, MA}
}

@article{welch-navar-sengupta-89,
  author        = "Welch, R. M. and Navar, M. S. and Sengupta, S. K.",
  title         = "The effect of spatial resolution upon texture-based 
                   cloud field classifications",
  journal       = "Journal of Geophysical Research",
  year          = "1989",
  volume        = "{\bf 94}",
  pages         = {14767-14781}
}

@article{wertheimer-23,
   author    = {Wertheimer, M.},
   title     = {{Laws of organization in perceptual forms}},
   journal   = {Psychologische Forschung},
   year      = {1923},
   volume    = {4},
   pages     = {301-350},
   note      = {Translated in W. D. Ellis, {\em A Source Book of Gestalt
       Psychology}. New York, Humanities Press, 1967}
}

@book{west-harrison-97,
   author    = {West, M. and Harrison, P. J.},
   title     = {{Bayesian Forecasting and Dynamic Models}},
   year      = {1997},
   publisher = {Springer},
   note      = {Second edition}
}

@article{weszka-dyer-rosenfeld-76,
  author        = "Weszka, J. S. and Dyer, C. R. and Rosenfeld, A.",
  title         = "A comparative study of texture measures for terrain
                  classification",
  journal       = "IEEE Trans. on Systems, Man, and Cybernetics",
  year          = "1976",
  volume        = "{\bf SMC-6}(4)",
  pages         = {269-285}
}

@book{whittle-63,
   author    = {Whittle, P.},
   title     = {{Prediction and regulation by linear least-square methods}},
   year      = {1963},
   publisher = {English Universities Press}
}

@mastersthesis      (williams-90,
author  =       "Williams, C. K. I.",
title   =       "{Using Deterministic Boltzmann machines for discriminating temporally distorted strings}",
year    =       "1990",
school  =       "Dept. of Computer Science, University of Toronto"
)

@incollection  (williams-hinton-91,
author  =   "Williams, C. K. I. and Hinton, G. E.",
title   =   "{Mean field networks that learn to discriminate temporally distorted strings}",
year    =   "1991",
publisher  = "Morgan Kaufmann",
address="San Mateo, CA",
editor  =   "Touretzky, D. S. and Elman, J. L. and Sejnowski, T. J.",
booktitle = "{Connectionist Models: Proceedings of the 1990 Summer School}"
)

		  
@phdthesis{williams-94,
   author    = {Williams, C. K. I.},
   title     = {{Combining deformable models and neural networks for 
       handprinted digit recognition}},
type={PhD},
   year      = {1994},
   school    = {Dept. of Computer Science, University of Toronto}
}


@incollection{williams-95,
   author    = {Williams, C. K. I.},
   title     = {{Regression with Gaussian Processes}},
   year      = {1997},
   booktitle = {Mathematics of Neural Networks: Models, Algorithms and Applications},
   publisher = {Kluwer},
   editor    = {Ellacott, S. W. and Mason, J. C. and Anderson, I. J.},
   note      = {Paper presented at the Mathematics of Neural Networks
       and Applications Conference, Oxford, UK, June 1995.}
}


@unpublished{williams-cvbm-93,
   author    = {Williams, C. K. I. and others},
   title     = {{Continuous valued Boltzmann machines}},
   year      = {1993},
   note      = {Unpublished manuscript},
   institution = {Department of Computer Science, University of Toronto}
}


@unpublished{williams-gen-stat-93,
   author    = {Williams, C. K. I. and others},
   title     = {{Generative statistical models for object recognition}},
   year      = {1993},
   note      = {Unpublished manuscript},
   institution = {Department of Computer Science, University of Toronto}
}

@inproceedings{williams-97a,		  
   author    = {Williams, C. K. I.},
   title     = {{Computing with infinite networks}},
   booktitle = {Advances in Neural Information Processing Systems 9},
   editor    = {Mozer, M. C. and Jordan, M. I. and Petsche, T.},
   publisher = {MIT Press},
   year      = {1997},
}


@incollection{williams-98,
author = "Williams, C. K. I.",
title  = "Prediction with {Gaussian} Processes: From Linear Regression
          to Linear Prediction and beyond",     
booktitle = "Learning in Graphical Models",
editor = "Jordan, M. I.",
publisher = "Kluwer",
year   = "1998",
pages  = "599-621"
}

% was williams-97b
@article{williams-98b,
   author    = {Williams, C. K. I.},
   title     = {{Computation with infinite neural networks}},
   year      = {1998},
   journal   = {Neural Computation},
   volume    = {10(5)},
   pages     = {1203-1216},
}

@incollection{williams-00,
   author    = {Williams, C. K. I.},
   title     = {{A {MCMC} approach to Hierarchical Mixture Modelling }},
   booktitle = {Advances in Neural Information Processing Systems 12},
   year      = {2000},
   editor    = {Solla, S. A. and Leen, T. K. and M\"{u}ller, K-R.},
   publisher = {MIT Press}
}


@incollection{williams-02,
   author    = {Williams, C. K. I.},
   title     = {Gaussian Processes},
   booktitle = {{Handbook of Brain Theory and Neural Networks}},
   year      = {2002},
   publisher = {MIT Press},
   editor     = {Arbib, M. A.}
}


@incollection{williams-adams-99,
   author    = {Williams, C. K. I. and Adams, N. J.},
   title     = {{DTs: Dynamic Trees}},
   booktitle = {Advances in Neural Information Processing Systems 11},
   year      = {1999},
   editor    = {Kearns, M. J. and Solla, S. A. and Cohn, D. A.},
   publisher = {MIT Press}
}

@incollection{williams-agakov-felderhof-01,
   author    = {Williams, C. K. I. and Agakov, F. V and Felderhof, S. N.},
   title     = {{Products of Gaussians}},
   booktitle = {Advances in Neural Information Processing Systems 14},
   year      = {2002},
   editor    = {Dietterich, T. G. and Becker, S. and Ghahramani, Z.},
   publisher = {MIT Press}
}

@misc{williams-barber-97,
   author    = {Williams, C. K. I. and Barber, D.},
   title     = {{Bayesian Classification with Gaussian Processes}},
   year      = {1997},
   note      = {Submitted to \emph{IEEE PAMI}}
}

@article{williams-barber-98,
   author    = {Williams, C. K. I. and Barber, D.},
   title     = {{Bayesian classification with Gaussian processes}},
   year      = {1998},
   journal   = {{IEEE Trans. on Pattern Analysis and Machine Intelligence}},
   volume    = {20(12)},
   pages     = {1342-1351}
}

@incollection{williams-felderhof-01,
   author    = {Williams, C. K. I. and Felderhof, S. N.},
   title     = {Products and Sums of Tree-Structured Gaussian Processes},
   booktitle = {Proceedings of the Fourth International ICSC Symposium on
Soft Computing},
   year      = {2001},
   publisher = {ICSC-NAISO Academic Press},
}

@inproceedings{williams-feng-98,
   author    = {Williams, C. K. I. and Feng, X.},
   title     = {{Combining Neural Networks and Belief Networks for Image
                Segmentation}},
   booktitle = {Neural Networks for Signal Processing VIII},
   year      = {1998},
   editor    = {Constantinides, T. and Kung, S-Y. and Niranjan, M. and
                Wilson, E.},
   publisher = {IEEE}
}

@inproceedings{williams-feng-99,
   author    = {Williams, C. K. I. and Feng, X.},
   title     = {{Tree-structured belief networks as models of images}},
   booktitle = {Proc. ICANN'99},
   year      = {1999},
   note      = {To appear},
   publisher = {IEE}
}

@inproceedings{williams-qazaz-bishop-zhu-95,
   author    = {Williams, C. K. I. and Qazaz, C. and Bishop, C. M. and
		  Zhu, H.},
   title     = {{On the relationship between Bayesian error bars and
		  the input data density}},
   booktitle = {Fourth International Conference on Artificial Neural Networks},
   year      = {1995},
   pages     = {160-165},
   note      = {Held at Churchill College, Cambridge, UK, 26-28 June 1995},
   publisher = {IEE Conference Publication No. 409} 
}

		  
@incollection{williams-rasmussen-96,
   author    = {Williams, C. K. I. and Rasmussen,  C. E.},
   title     = {Gaussian processes for regression},
   booktitle = {Advances in Neural Information Processing Systems 8},
   year      = {1996},
   pages     = {514-520},
   editor    = {Touretzky, D. S. and Mozer, M. C. and Hasselmo, M. E.},
   publisher = {MIT Press},
}


@incollection{williams-revow-hinton-93,
   key       = {Williams},
   author    = {Williams, C. K. I. and Revow, M. D. and Hinton, G. E.},
   title     = {{Hand-printed digit recogntion using deformable models}},
   booktitle = {Spatial Vision in Humans and Robots},
   year      = {1993},
   editor    = {L. Harris and M. Jenkin},
   publisher = {Cambridge University Press}
}

@article{williams-revow-hinton-97,
   author    = {Williams, C. K. I. and Revow, M. and Hinton, G. E.},
   title     = {Instantiating deformable models with a neural net},
   journal   = {Computer Vision and Image Understanding},
   year      = {1997},
   volume    = {68},
   number    = {1},
   pages     = {120-126}
}

@inproceedings{williams-revow-hinton-95,
   author    = {Williams, C. K. I. and Revow, M. D. and Hinton, G. E.},
   title     = {Using a neural net to instantiate a deformable
       model},
   booktitle = {Advances in Neural Information Processing Systems,
       Vol. 7},
   year      = {1995},
   editor    = {Tesauro, G. and Touretzky, D. and Leen, T.},
   publisher = {MIT Press}
}


@inproceedings{williams-seeger-00,
   author    = {Williams, C. K. I. and Seeger, M.},
   title     = {{The Effect of the Input Density Distribution on Kernel-based Classifiers}},
   booktitle = {Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)},
   year      = {2000},
   editor    = {Langley, P.},
   publisher = {Morgan Kaufmann}
}

@incollection{williams-seeger-01,
   author    = {Williams, C. K. I. and Seeger, M.},
   title     = {{Using the Nystr\"{o}m Method to Speed Up Kernel Machines}},
   booktitle = {{Advances in Neural Information Processing Systems 13}},
   year      = {2001},
   pages     = {682-688},
   editor    = {Leen, T. K. and Diettrich, T. G. and Tresp, V.},
   publisher = {MIT Press}
}

@incollection{williams-titsias-03,
   author    = {Williams, C. K. I. and Titsias, M. K.},
   title     = {{Learning About Multiple Objects in Images: 
Factorial Learning without Factorial Search}},
   booktitle = {{Advances in Neural Information Processing Systems 15}},
   year      = {2003},
   editor    = {Becker, S. and Thrun, S. and Obermayer,  K.},
   publisher = {MIT Press}
}


@inproceedings{williams-zemel-mozer-93,
   author    = {Christopher K. I. Williams and Richard S. Zemel and
       Michael C. Mozer},
   title     = {Unsupervised learning of object models},
   booktitle = {AAAI Fall 1993 Symposium on Machine
       Learning in Computer Vision},
   year      = {1993},
   pages     = {20-24},
   note      = {Proceedings available as AAAI Tech Report FSS-93-04}
}

@article{Willshaw76,
       author = "Willshaw, D.J. and C. von der Malsburg",
        title = "How Patterned Neural Connections Can Be Set Up by Self-Organization",
        pages = "431--445",
      journal =  {{Proceedings of the Royal Society of London B}},
       volume =  194,
         year =  1976
  }

@incollection{wold-85,
   author    = {Wold, S.},
   title     = {{Partial Least Squares}},
   booktitle = {Encyclopedia of Statistical Sciences vol 6.},
   year      = {1985},
   editor    = {Kotz, S. and Johnson, N. L.},
   publisher = {Wiley, New York}
}

@book{wong-71,
   author    = {E. Wong},
   title     = {{Stochastic Processes in Information and Dynamical Systems}},
   year      = {1971},
   publisher = {McGraw-Hill},
   address   = {New York}
}

@article{wornell-90,
   author    = {Wornell, G. W.},
   title     = {{A Karhunen-Lo\`{e}ve-like Expansion for $1/f$ Processes
via Wavelets}},
   journal   = {IEEE Trans. Information Theory},
   year      = {1990},
   volume    = {36},
   number    = {4},
   pages     = {859-861}
}

@inproceedings{woodland-92,
   author    = {Woodland, P. C.},
   title     = {{Hidden Markov Models using Vector Linear Prediction and
Discriminative Output Distributions}},
   booktitle = {Proceedings of 1992 IEEE International Conference on 
Acoustics, Speech, and Signal Processing},
  publisher =  {IEEE},
   volume    = {I},
   pages     = {509-512},
   year      = {1992}
}

@inproceedings{wright-mackeown-greenway-95,
  author        = "Wright, W. A. and Mackeown, W. P. J. and Greenway, P.",
  title         = "The use of neural networks for region labelling and scene  understanding",
  booktitle = "Neural Networks",
  editor    = "Taylor, J.~G",
  publisher = "Alfred Waller",
  volume    = "",
  year      = 1995,
  pages     = "165-192"
}
        
@inproceedings{wright-89,
  author        = "Wright, W. A.",
  title         = "Image labelling with a neural network",
  booktitle = "Proceedings $5^{th}$ Alvey Vision Conference",
  publisher = "Sheffield University Press",
  year      = 1989,
  pages     = "227-232"
}


@article{xu-krzyzak-suen-92,
   author    = {Xu, L. and Krzyzak, A. and Suen, C. Y.},
   title     = {{Methods of Combining Multiple Classifiers and Their Applications to Handwriting Recognition}},
   journal   = {IEEE Trans. Systems Man and Cybernetics},
   year      = {1992},
   volume    = {22},
   number    = {3},
   pages     = {418-435}
}

@incollection{xu-pearl-89,
   author    = {Xu, L. and Pearl, J.},
   title     = {{Structuring Causal Tree Models with Continuous Variables}},
   booktitle = {Uncertainty in Artificial Intelligence 3},
   year      = {1989},
   editor    = {Kanal, L. N. and Levitt, T. S. and Lemmer, J. F.},
   publisher = {Elsevier}
}


@article{xu-oja-93,
   author    = {Xu, L. and Oja, E.},
   title     = {{Randomized Hough Transform (RHT): Basic Mechanisms, Algorithms, and Computational Complexities}},
   journal   = {CVGIP: Image Understanding},
   year      = {1993},
   volume    = {57},
   number    = {2},
   pages     = {131-154}
}


@book{yaglom-87,
   author    = {Yaglom, A. M.},
   title     = {{Correlation Theory of Stationary and Related Random
		  Functions Volume I:Basic Results}},
   year      = {1987},
   publisher = {Springer}
}

@article{yakowitz-szidarovszky-85,
   author    = {Yakowitz, S. J. and Szidarovszky, F.},
   title     = {{A Comparison of Kriging with Nonparametric Regression
Methods}},
   journal   = {{J. Multivariate Analysis}},
   year      = {1985},
   volume    = {16},
   pages     = {21-53}
}
		  
@article{young-77,
   author    = {Young, A. S.},
   title     = {{A Bayesian approach to prediction using polynomials}},
   journal   = {Biometrika},
   year      = {1977},
   volume    = {64(2)},
   pages     = {309-317}
}


@article{yuille-90,
   author    = {Yuille, A.},
   title     = {{Generalized Deformable Models, Statistical Physics and Matching Problems}},
   journal   = {Neural Computation},
   year      = {1990},
   volume    = {2},
   number    = {1},
   pages     = {1-24}
}

@article{yuille-grzywacz-89,
   author    = {Yuille, A. and Grzywacz, N. M.},
   title     = {{A Mathematical Analysis of Motion Coherence Theory}},
   journal   = {International Journal of Computer Vision},
   year      = {1989},
   volume    = {3},
   pages     = {155-175}
}


@techreport{yuille-honda-peterson-90,
   author    = {Yuille, A. and Honda, K. and Peterson, C.},
   title     = {{Deformable Templates for Particle Tracking}},
   institution = {Harvard Robotics Laboratory},
   year      = {1990},
   number    = {{90-8}},
   type      = {Technical Report}
}


@phdthesis{zemel-93,
   author    = {Zemel, R. S.},
   title     = {{A Minimum Description Length Framework for Unsupervised Learning}},
type={PhD},
   year      = {1993},
   school    = {Dept. of Computer Science, University of Toronto}
}


@incollection{zemel-williams-mozer-93,
   author    = {Zemel, R.~S. and Williams, C. K. I. and Mozer, M.~C.},
   title     = {{Directional-Unit Boltzmann machines}},
   booktitle = {Neural Information Processing Systems, Vol. 5},
   year      = {1993},
   editor    = {Hanson, S. J. and Cowan, J. D. and Giles, C. L.},
   publisher = {Morgan Kaufmann},
address={San Mateo, CA}
}

@article{zhu-rohwer-96,
   author    = {Zhu, H. and Rohwer, R.},
   title     = {{Bayesian Regression Filters and the Issue of Priors}},
   journal   = {Neural Computing and Applications},
   year      = {1996},
   volume    = {4},
   pages     = {130-142}
}

@techreport{zhu-williams-rohwer-morciniec-97,
   author    = {Zhu, H. and Williams, C. K. I. and Rohwer, R. J. and Morciniec, M.},
   title     = {{Gaussian Regression and Optimal Finite Dimensional Linear Models}},
   year      = {1997},
   institution = {Aston University, UK},
   number    = {{NCRG/97/011}},
   note      = {Available from {\tt http://www.ncrg.aston.ac.uk/Papers/ .}}
}

@incollection{zhu-williams-rohwer-morciniec-98,
   author    = {Zhu, H. and Williams, C. K. I. and Rohwer, R. J. and Morciniec, M.},
   title     = {{Gaussian regression and optimal finite dimensional linear models}},
   year      = {1998},
   editor    = {C. M. Bishop}, 
   booktitle = {Neural Networks and Machine Learning},
   address   = {Berlin},
   publisher = {Springer}
}




@article{zhuang-engel-xiong-johannsen-95,
   author    = {Zhuang, X. and Engel, B. A. and Xiong, X. 
   and Johannsen, C. J.},
   title     = {{Analysis of Classification Results of Remotely Sensed Data
   and Evaluation of Classification Algorithms}},
   journal   = {Photogrammetric Engineering and Remote Sensing},
   year      = {1995},
   volume    = {61(4)},
   pages     = {427-433}
}
@book{JoZigangirov,
author={R. Johannesson and Zigangirov, K. Sh.},
title={Fundamentals of Convolutional Coding},
publisher={IEEE Press},
address={Piscataway, N.J.},
year={1999},
annote={R. Johannesson and K. Sh. Zigangirov, Fundamentals of Convolutional Coding, IEEE Press, Piscataway, N.J., Febr., 1999}
}
refer.bib

@BOOK{sutton98reinforcement,
 TITLE = {Reinforcement Learning: An Introduction},
 AUTHOR = {Richard S. Sutton and Andrew G. Barto},
 PUBLISHER = {MIT Press},
 ADDRESS = {Cambridge, MA},
 YEAR = 1998,
 anNOTE = {A Bradford Book},
 URL = {http://www-anw.cs.umass.edu/~rich/book/the-book.html}
}

% Kraft inequality
% L. G. Kraft. A Device for Quantizing Grouping and Coding Amplitude Modulated Pulses, MS Thesis, Electrical Eng. Dept., MIT, Cambridge, MA, 1949. 
% B. McMillan, Two Inequalities Implied by Unique Decipherability, IRE Trans. Infom. Theory, IT-2 (1965), 115-116.
@article{mcmillan1956,
author={B. McMillan},
title={Two Inequalities Implied by Unique Decipherability},
journal={IRE Trans. Inform. Theory},
volume={2},
year={1956},
pages={115-116},
annote={B. McMillan, Two Inequalities Implied by Unique Decipherability, IRE Trans. Infom. Theory, IT-2 (1956), 115-116.}
}

@article{Graham66,
author={R. L. Graham},
title={On partitions of a finite set},
journal={Journal of Combinatorial Theory},
volume={1},
year={1966},
pages={215-223},
annote={ R. L. Graham, ``On partitions of a finite set,'' {\sl Journal of Combinatorial
 Theory\/ \bf 1} (1966), 215--223 }
}
@misc{GrahamKnowlton68,
author={Ronald L. Graham and Kenneth C. Knowlton},
title={Method of identifying conductors in a cable by establishing conductor connection groupings at both ends of the
 cable},
year={1968},
howpublished={U.S. Patent 3,369,177},
annote={(13~Feb 1968)},
annote={Ronald L. Graham and Kenneth C. Knowlton, ``Method of identifying conductors in
 a cable by establishing conductor connection groupings at both ends of the
 cable,'' U.S. Patent 3,369,177 (13~Feb 1968).}
}

%2 Diopters ....... the approximate amount of longitudinal chromatic aberration of the human eye over the visible spectrum The reference I like is Howarth and Bradley, Vision Research 26, 361-366, 1986 but probably a better one is Wald and Griffin 1947, JOSA, 37, 321-336

% Howarth, P.A. and Bradley, A. (1986) The longitudinal aberration of the human eye and its correction. Vision Res., 26, 361-366.
@article{ChromAb1986,
author={Howarth, P.A. and Bradley, A.},
year={1986},
title={The longitudinal aberration of the human eye and its correction},
journal={Vision Res.},
volume={26},
pages={361-366}
}

% Wald, G. and Griffin, D.R. 1947. The change in refractive power of the eye in bright and dim light. J. Opt. Soc. Am. 37.  321-336
@article{ChromAb1947,
author={Wald, G. and Griffin, D.R.},
year={1947},
title={The change in refractive power of the eye in bright and dim light},
journal={J. Opt. Soc. Am.},
volume={37},
pages={321-336}
}

% # Howarth, P.A. and Bradley, A. (1986) The longitudinal chromatic aberration of the eye. Proceedings of the Northeastern State Symposium on theoretical and clinical optometry. pp124-137.


%Howarth, P.A., Zhang, X., Bradley, A.B., Still, D.L. and Thibos, L.N. (1988) Does the chromatic aberration of the eye vary with age? J. Opt. Soc. Amer. A 5, 2087-2092.
%
%Thibos, L.N., Bradley, A., Still, D.L., Zhang, X. and Howarth, P.A. (1990) Theory and measurement of ocular chromatic aberration. Vision Res. 30, 33-49.
%
%Bradley, A., Zhang, X. and Thibos, L.N. (1991). Achromatizing the human eye. Optom. Vis. Sci. 68, 608-616.
%
%http://www.opt.indiana.edu/people/faculty/bradley.htm
%
%# Thibos, L.N., Bradley, A. and Still, D. (1991). Interferometric measurement of visual acuity and the effect of ocular chromatic aberration. Appl. Opt. 30, 2079-2087.
%
%# Thibos, L.N., Bradley, A. and Zhang, X. (1991). The effect of ocular chromatic aberration on monocular visual performance. Optom. Vis. Sci. 68, 599-607.
%
%# Zhang, X., Bradley, A. and Thibos, L.N. (1991). Achromatizing the human eye: the problem of chromatic parallax. J. Opt. Soc. Am. A. 8,686-691.
%
%# Zhang, X., Thibos, L.N. and Bradley, A. (1991). A simple model to describe the relationship between the chromatic difference of focus and chromatic difference of magnification in human eyes. Optom. Vis. Sci. 68, 456-458.
%
%Ye, M., Bradley, A., Zhang, X., Thibos, L.N. (1992) The effect of pupil size on chromostereopsis and chromatic diplopia: Interaction between the Stiles-Crawford Effect and chromatic aberration. Vision Research , 32, 2121-28.
%
%# Thibos, L.N., Ye M, Zhang, X, and Bradley, A. (1992) The Chromatic Eye: A new reduced-eye model of Ocular Chromatic Aberration in humans, Applied Optics, 31, 3594-600.
%
%
%
%Winn, B., Bradley, A., Strang, N.C., McGraw, P.V. and Thibos, L.N. (1995). Reversals of the colour-depth illusion explained by ocular chromatic aberration. Vision Research, 35, 2675-2684.
%

@InProceedings{diggavi02,
  author =       {Suhas N. Diggavi and Matthias Grossglauer},
  title =        {Bounds on the Capacity of Deletion Channels},
  booktitle =    {IEEE International Symposium on Information Theory},
  OPTcrossref =  {},
  OPTkey =       {},
  OPTpages =     {},
  year =         {2002},
  OPTeditor =    {},
  OPTannote =    {http://icapeople.epfl.ch/grossglauser/Papers/allerton01.ps}
}

@article{QianHopfield96,
author={Qian, H. and Hopfield, J. J.},
year={1996},
title={Entropy-enthalpy compensation: {P}erturbation
and relaxation in thermodynamic systems},
journal={J. Phys. Chem},
volume={105},
pages={9292-9299},
annote={Qian, H. and Hopfield, J. 1996. Entropy-enthalpy compensation: Perturbation
and relaxation in thermodynamic systems. J. Phys. Chem. 105: 9292-9299}
}


@PHDTHESIS{Speelpenning1980a,
  author = "Bert Speelpenning",
  month = "January",
  year = 1980,
  title = "Compiling Fast Partial Derivatives of Functions Given by Algorithms",
  address = "Urbana-Champaign, IL",
  school = "Department of Computer Science, University of Illinois at
           Urbana-Champaign",
  key = "Speelpenning1980a",
  abstract = "This is the author's doctoral thesis. It starts by comparing
             previous work in the area of symbolic differentiation of
             algorithms. Specifically it considers the work of Warner in 1975,
             Joss in 1976 and Kedem in 1977. The conclusions reached in this
             discussion are that the work by Joss is the best in terms of
             improvement. The author proceeds to describe how Joss' work can
             be improved in terms of speed, accuracy and space. A package,
             Jake, is described which is a compiler that takes a Fortran 66
             input definition of a function. This input is limited in that
             only one subroutine can be specified, and that certain Fortran 66
             statements are disallowed. Jake is instructed on how to perform
             its task by directives within the subroutine. Timing results are
             provided on the performance of the code produced by Jake over
             those where finite differencing is used.",
  keywords = "point algorithm; precompiler; numerical results."
}

@BOOK{Griewank2000a,
  author = "Andreas Griewank",
  year = 2000,
  title = "Evaluating Derivatives: Principles and Techniques of Algorithmic
          Differentiation",
  series = "Frontiers in Appl. Math.",
  number = 19,
  publisher = "SIAM",
  address = "Philadelphia, PA",
  key = "Griewank2000a",
  isbn = "0--89871--451--6"
}


@misc{hu-eleftheriou-arnold2003,
 year={2003},
 author = "Hu, Xiao--Yu and Eleftheriou, Evangelos and Arnold, Dieter-Michael",
 annote = "Xiao--Yu Hu,  Evangelos  Eleftheriou,  Dieter-Michael  Arnold",
 title = "Regular and    Irregular Progressive Edge-Growth {T}anner Graphs",
 note={Submitted to IEEE TRANS. on INFORMATION THEORY},
 url = "citeseer.nj.nec.com/570728.html"
}

@article{BakerJoshE1999,
author = {Baker, Josh E. and LaConte, Leslie E. W. and Brust-Mascher, Ingrid and Thomas, David D.},
title = {{Mechanochemical Coupling in Spin-Labeled, Active, Isometric Muscle}},
journal = {Biophys. J.},
volume = {77},
number = {5},
pages = {2657-2664},
year = {1999},
 abstract = {Observed effects of inorganic phosphate (Pi) on active isometric muscle may provide the answer to one of the fundamental questions in muscle biophysics: how are the free energies of the chemical species in the myosin-catalyzed ATP hydrolysis (ATPase) reaction coupled to muscle force? Pate and Cooke (1989. Pflugers Arch. 414:73-81) showed that active, isometric muscle force varies logarithmically with [Pi]. Here, by simultaneously measuring electron paramagnetic resonance and the force of spin-labeled muscle fibers, we show that, in active, isometric muscle, the fraction of myosin heads in any given biochemical state is independent of both [Pi] and force. These direct observations of mechanochemical coupling in muscle are immediately described by a muscle equation of state containing muscle force as a state variable. These results challenge the conventional assumption mechanochemical coupling is localized to individual myosin heads in muscle.
},
URL = {http://www.biophysj.org/cgi/content/abstract/77/5/2657},
eprint = {http://www.biophysj.org/cgi/reprint/77/5/2657.pdf}
}
@article{ ldpc_7,
  author = "A. Shokrollahi",
  journal = "Proceedings of AAECC-13, Lecture Notes in Computer Science 1719",
  title = "New sequences of linear time erasure codes approaching the channel capacity",
}

@book{Ambegaokar1996,
title={Reasoning about Luck: Probability and its Uses in Physics},
author={Vinay Ambegaokar},
year={1996},
isbn={0521447372}
}

@book{Tversky1982,
title={Judgment under Uncertainty: Heuristics and Biases},
editor={Daniel Kahneman and Paul Slovic and Amos Tversky},
year={1982},
annote={544 pages},
ISBN={0521284147}
}

@inproceedings{Huber1998,
author={Mark Huber},
title={Exact Sampling and Approximate Counting Techniques},
booktitle={Proceedings of the 30th ACM Symposium on the Theory of Computing},
pages={31-40},
year={1998},
annote={Mark Huber. Exact Sampling and Approximate Counting Techniques. In Proceedings of the 30th ACM Symposium on the Theory of Computing, pages 31--40, 1998.}
}

@article{Mead1979,
author={D. G. Mead},
title={The average number of weighings to locate
	     a counterfeit coin},
journal={IEEE Transactions on Information Theory},
month={Sept},
year={1979}, vol= 25, number= 5,
pages={616-617}
}

@article{Berlekamp1976,
 author={Elwyn R. Berlekamp},
 title={Cooperative Bridge Bidding},
 journal={IEEE Transactions on Information Theory},
 month={Nov},
 year={1976}, vol=22, number=6, pages={753-756}
}

@article{Cohn1976,
author={David L. Cohn},
title={An Enumeration Scheme for Bidding Sequences in Bridge},
journal={IEEE Transactions on Information Theory},
month={Nov},
year={1976}, vol=22, number=6, pages={756-757}
}

@article{haffenden,
author={Haffenden, L. J. W.  and Yaylayan, V. A.,  and Fortin, J.},
annote={ (<a href=http://www.elsevier.com/locate/foodchem>Food Chemistry</a> 73, <a href=FoodScience2001.pdf>67-72</a>)
 reported that <b>deuteration of Benzaldehyde changes its perceived smell</b>.
},
title={Investigation of vibrational theory of olfaction with variously labelled benzaldehydes},
journal={Food Chemistry},
volume={73},
number={1},
year={2001},
pages={67-72},
annote={L.J.W. Haffenden, V.A. Yaylayan, J. Fortin, Investigation of vibrational theory of olfaction with variously labelled benzaldehydes, Food Chemistry 73 (1) (2001) pp. 67-72. }
}



@article{Keller2004,
 title={A psychophysical test of the vibration theory of olfaction},
 author={Andreas Keller and Leslie B. Vosshall},
 annote={    Laboratory of Neurogenetics and Behavior, The Rockefeller University, 1230 York Avenue, Box 63, New York New York, 10021, USA.
    Correspondence should be addressed to A Keller. e-mail: kellera@mail.rockefeller.edu
 },
 abstract={At present, no satisfactory theory exists to explain how a given
 molecule results in the perception of a particular smell. One theory
 is that olfactory sensory neurons detect intramolecular vibrations of
 the odorous molecule. We used psychophysical methods in humans to
 test this vibration theory of olfaction and found no evidence to
 support it.},
 journal={Nature Neuroscience},
 note={published online 21 March 2004, doi:10.1038/nn1215 }
}


@inproceedings{grassl:qc2002a,
  author = {M. Grassl and A. Klappenecker and M. R\"otteler},
  title = "Graphs, Quadratic Forms and Quantum Codes",
  booktitle = "Proc. IEEE Int. Symp. Inf. Th. 2002",
  publisher = "IEEE Inf. Th. Soc.",
  year = 2002
}

@article{schlingemann:qc2001a,
  author = "Schlingemann, D.  and Werner, R. F. ",
  title = "Quantum Error-Correcting Codes Associated with Graphs",
  year = 2002,
  journal = pra,
  volume = 65,
  pages = "012308/1--8",
  web = "http://arxiv.org/abs/quant-ph/0012111",
  xxxep = "quant-ph/0012111",
  address = "{\tt d.schlingemann@tu-bs.de}"
}

@article{schlingemann:qc2001b,
  author = "Schlingemann, D.  and Werner, R. F. ",
  title = "Stabilizer Codes Can Be Realized as Graph Codes",
  journal = qic,
  volume = 2,
  pages = "307-323",
  year = 2002,
  web = "http://arxiv.org/abs/quant-ph/0111080",
  xxxep = "quant-ph/0111080",
  address = "{\tt d.schlingemann@tu-bs.de}"
}


@article{Jarzynski97,
author   = "Jarzynski, C",
title    = "Nonequilibrium equality for free energy differences",
journal  = "Phys.\ Rev.\ Lett.",
year     = "1997",
volume   = "78",
number   = "14",
pages    = "2690-2693",
BIDS-type = "journal",
abstract = "An expression is derived for the equilibrium free energy
            difference between two configurations of a system, in terms of
            an ensemble of finite-time measurements of the work performed
            in parametrically switching from one configuration to the
            other. Two well-known identities emerge as limiting cases of
            this result.",
copy = {StatMech},
annote={PS says:
You were right about the Jarzynski result being essentially just AIS.
The generalized version of his expression for the free energy, which
relates the distributions of the work during the forward and backward
processes, also has an analog in AIS when "run backwards".
}

}


@article{ClaCueSeaSolSpe00,
author   = "Clarke, N  and Cuesta, J A  and Sear, R  and Sollich, P  and
            Speranza, A",
title    = "Phase equilibria in the polydisperse {Zwanzig} model of hard
            rods",
journal  = "J.\ Chem.\ Phys.",
year     = "2000",
volume   = "113",
number   = "14",
pages    = "5817-5829",
annote={
 On the Zwanzig model, the original ref is in here
}
}

@article{Flory56b,
  author =       "Flory, P J",
  title  =        "Phase equilibria in solutions of rod-like particles",
  journal =      "Proc. R. Soc. London A",
  year =         "1956",
  volume =       "234",
  pages =        "73-89",
  copy = {Poly:Rods}
}

@article{FloAbe78,
  author =       "Flory, P J and Abe, A",
  title  =        "Statistical Thermodynamics of Mixtures of Rodlike
                  Particles. 1. {T}heory for Polydisperse Systems",
  journal =      macromol,
  year =         "1978",
  volume =       "11",
  pages =        "1119-1122",
  copy = {Poly:Rods}
}



