ADVANCES IN NEURAL INFORMATION 
PROCESSING SYSTEMS 10 
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 
Published by Morgan-Kaufmann 
NIPS-1 
Advances in Neural 
David S. Touretzky, 
NIPS -2 
Advances in Neural 
David S. Touretzky, 
NIPS-3 
Information Processing Systems 1: Proceedings of the 1988 Conference, 
ed., 1989. 
Information Processing Systems 2: Proceedings of the 1989 Conference, 
ed., 1990. 
Advances in Neural Information Processing Systems 3: Proceedings of the 1990 Conference, 
Richard Lippmann, John E. Moody and David S. Touretzky, eds., 1991. 
NIPS-4 
Advances in Neural Information Processing Systems 4: Proceedings of the 1991 Conference, 
John E. Moody, Stephen J. Hanson and Richard P. Lippmann, eds., 1992. 
NIPS-5 
Advances in Neural Information Processing Systems 5: Proceedings of the 1992 Conference, 
Stephen J. Hanson, Jack D. Cowan and C. Lee Giles, eds., 1993. 
NIPS-6 
Advances in Neural Information Processing Systems 6: Proceedings of the 1993 Conference, 
Jack D. Cowan, Gerald Tesauro and Joshua Alspector, eds., 1994. 
Published by The MIT Press 
NIPS -7 
Advances in Neural Information Processing Systems 7: Proceedings of the 1994 Conference, 
Gerald Tesauro, David S. Touretzky and Todd K. Leen, eds., 1995. 
NIPS-$ 
Advances in Neural Information Processing Systems 8: Proceedings of the 1995 Conference, 
David S. Touretzky, Michael C. Mozer and Michael E. Hasselmo, eds., 1996. 
NIPS -9 
Advances in Neural Information Processing Systems 9: Proceedings of the 1996 Conference, 
Michael C. Mozer, Michael I. Jordan and Thomas Petsche, eds., 1997. 
NIPS-10 
Advances in Neural Information Processing Systems 10: Proceedings of the 1997 Conference, 
Michael I. Jordan, Michael J. Kearns and Sara A. Solla, eds., 1998. 
ADVANCES IN NEURAL INFORMATION 
PROCESSING SYSTEMS 10 
Proceedings of the 1997 Conference 
edited by 
Michael I. Jordan, Michael J. Keams and Sara A. Solla 
A Bradford Book 
The MIT Press 
Cambridge, Massachusetts 
London, England 
() 1998 Massachusetts Institute of Technology 
All rights reserved. No part of this book may be reproduced in any form by any electronic or 
mechanical means (including photocopying, recording or information storage and retrieval) 
without permission in writing from the publisher. 
This book was printed and bound in the United States of America. 
ISSN: 1049-5258 
ISBN: 0-262-10076-2 
Contents 
NIPS Committees ................................ xv 
Reviewers .................................... xvii 
Part I Cognitive Science 
Synchronized Auditory and Cognitive 40 Hz Attentional Streams, and the Impact 
of Rhythmic Expectation on Auditory Scene Analysis, Bill Baird .......... 3 
On Parallel versus Serial Processing: A Computational Study of Visual Search, 
Eyal Cohen and Eytan Ruppin .......................... 10 
Task and Spatial Frequency Effects on Face Specialization, 
Matthew N. Dailey and Garrison W. Cottrell ................... 17 
Neural Basis of Object-Centered Representations, 
Sophie Deneve and Alexandre Pouget ...................... 24 
A Neural Network Model of Naive Preference and Filial Imprinting in the 
Domestic Chick, Lucy E. Hadden ......................... 31 
Adaptation in Speech Motor Control, John F. Houde and Michael I. Jordan .... 38 
Learning Human-like Knowledge by Singular Value Decomposition.' A Progress 
Report, Thomas K. Landauer, Darrell Laham and Peter Foltz ........... 45 
Multi-modular Associative Memory, Nit Levy, David Horn and Eytan Ruppin 52 
Serial Order in Reading Aloud.' Connectionist Models and Neighborhood 
Structure, Jeanne C. Milostan and Garrison W. Cottrell .............. 59 
A Superadditive-Impairment Theory of Optic Aphasia, 
Michael C. Mozer, Mark Sitton and Martha Farah ................ 66 
A Hippocampal Model of Recognition Memory, 
Randall C. O'Reilly, Kenneth A. Norman and James L. McClelland ........ 73 
Correlates of Attention in a Model of Dynamic Visual Recognition, 
Rajesh P. N. Rao ................................. 80 
Recurrent Neural Networks Can Learn to Implement Symbol-Sensitive Counting, 
Paul Rodriguez and Janet Wiles ......................... 87 
Comparison of Human and Machine Word Recognition, 
Markus Schenkel, Cyril Latimer and Marwan Jabri ................ 94 
Part II Neuroscience 
Coding of Naturalistic Stimuli by Auditory Midbrain Neurons, 
Hagai Attias and Christoph E. Schreiner ..................... 
103 
vi Contents 
Refractoriness and Neural Precision, Michael J. Berry II and Markus Meister 110 
Statistical Models of Conditioning, Peter Dayan and Theresa Long ........ 117 
Characterizing Neurons in the Primary Auditory Cortex of the Awake Primate 
Using Reverse Correlation, R. Christopher deChamas and Michael M. Merzenich 
Using Helmholtz Machines to Analyze Multi-channel Neuronal Recordings, 
Virginia R. de Sa, R. Christopher deCharms and Michael M. Merzenich ...... 
124 
131 
Instabilities in Eye Movement Control: A Model of Periodic Alternating 
Nystagmus, Ernst R. Dow and Thomas J. Anastasio ................ 
Hippocampal Model of Rat Spatial Abilities Using Temporal Difference 
Learning, David J. Foster, Richard G. M. Morris and Peter Dayan ......... 
138 
145 
Gradients for Retinotectal Mapping, Geoffrey J. Goodhill ............. 152 
A Mathematical Model of Axon Guidance by Diffusible Factors, 
Geoffrey J. Goodhill ............................... 
159 
Computing with Action Potentials (Invited Talk), 
John J. Hopfield, Carlos D. Brody and Sam Roweis ................ 
166 
A Model of Early Visual Processing, 
Laurent Itti, Jochen Braun, Dale K. Lee and Christof Koch ............ 
173 
Perturbative M-Sequences for Auditory Systems Identification, 
Mark Kvale and Christoph E. Schreiner ..................... 
180 
Effects of Spike Timing Underlying Binocular Integration and Rivalry in a 
Neural Model of Early Visual Cortex, Erik D. Lumer ............... 
187 
Dynamic Stochastic Synapses as Computational Units, 
Wolfgang Maass and Anthony M. Zador ..................... 
194 
Synaptic Transmission: An Information-Theoretic Perspective, 
Amit Manwani and Christof Koch ........................ 201 
Toward a Single-Cell Account for Binocular Disparity Tuning: An Energy Model 
May Be Hiding in Your Dendrites 
Bartlett W. Mel, Daniel L. Ruderman and Kevin A. Archie ............ 208 
Just One View: Invariances in Inferotemporal Cell Tuning, 
Maximilian Riesenhuber and Tomaso Poggio ................... 215 
On the Separation of Signals from Neighboring Cells in Tetrode Recordings 
Maneesh Sahani, John S. Pezaris and Richard A. Andersen ............ 222 
Independent Component Analysis for Identification of Artifacts in 
MagnetoencephaIographic Recordings, 
Ricardo Xrgfirio, Veikko Jousmfiki, Matti H'amrd'ninen, Riitta Hari and Erkki Oja 
229 
Modeling Complex Cells in an Awake Macaque during Natural Image Viewing, 
William E. Vinje and Jack L. Gallant ....................... 236 
Contents vii 
Part III Theory 
The Canonical Distortion Measure in Feature Space and 1-NN Classification, 
Jonathan Baxter and Peter Bartlett ........................ 
Multiple Threshold Neural Logic, Vasken Bohossian and Jehoshua Bruck ..... 
Generalization in Decision Trees and DNF: Does Size Matter? 
Mostefa Golea, Peter Bartlett, Wee Sun Lee and Llew Mason ........... 
Selecting Weighting Factors in Logarithmic Opinion Pools, Tom Heskes ..... 
New Approximations of Differential Entropy for Independent Component 
Analysis and Projection Pursuit, Aapo Hyv'firinen ................. 
Boltzmann Machine Learning Using Mean Field Theory and Linear Response 
Correction, Hilbert J. Kappen and F. B. Rodrfguez ................ 
Relative Loss Bounds for Multidimensional Regression Problems, 
Jyrki Kivinen and Manfred K. Warmuth ..................... 
Asymptotic Theory for Regularization: One-Dimensional Linear Case, 
Petri Koistinen .................................. 
Two Approaches to Optimal Annealing, 
Todd K. Leen, Bernhard Schottky and David Saad 
Structural Risk Minimization for Nonparametric Time Series Prediction, 
Ron Meir .................................... 
Analytical Study of the Interplay between Architecture and Predictability, 
Avner Priel, Ido Kanter and David A. Kessler ................... 
Globally Optimal On-line Learning Rules, Magnus Rattray and David Saad .... 
Minimax and Hamiltonian Dynamics of Excitatory-Inhibitory Networks, 
H. Sebastian Seung, Tom J. Richardson, Jeffrey C. Lagarias and John J. Hopfield 
Data-Dependent Structural Risk Minimization for Perceptron Decision Trees, 
John Shawe-Taylor and Nello Cristianini ..................... 
From Regularization Operators to Support Vector Kernels, 
Alex J. Smola and Bernhard Sch61kopf ...................... 
The Rectified Gaussian Distribution, 
Nicholas D. Socci, Daniel D. Lee and H. Sebastian Seung 
On-line Learning from Finite Training Sets in Nonlinear Networks, 
Peter Sollich and David Barber .......................... 
Competitive On-line Linear Regression, Volodya Vovk .............. 
On the Infeasibility of Training Neural Networks with Small Squared Errors, 
Van H. Vu .................................... 
The Storage Capacity of a Fully-Connected Committee Machine, 
Yuansheng Xiong, Chulan Kwon and Jong-Hoon Oh ............... 
245 
252 
259 
266 
273 
280 
287 
294 
301 
308 
315 
322 
329 
336 
343 
350 
357 
364 
371 
378 
viii Contents 
The Efficiency and the Robustness of Natural Gradient Descent Learning Rule, 
Howard H. Yang and Shun-ichi Amari ...................... 385 
Part IV Algorithms and Architecture 
Ensemble Learning for Multi-Layer Networks, 
David Barber and Christopher M. Bishop ..................... 395 
Radial Basis Functions: A Bayesian Treatment, 
David Barber and Bernhard Schottky ....................... 402 
Shared Context Probabilistic Transducers, 
Yoshua Bengio, Samy Bengio, Jean-Franqois Isabelle and Yoram Singer ..... 409 
Approximating Posterior Distributions in Belief Networks Using Mixtures, 
Christopher M. Bishop, Nell Lawrence, Tommi Jaakkola and Michael I. Jordan 416 
Receptive Field Formation in Natural Scene Environments: Comparison of 
Single Cell Learning Rules, 
Brian S. Blais, Nathan Intrator, Harel Shouval and Leon N. Cooper ........ 423 
An Annealed Self-Organizing Map for Source Channel Coding, 
Matthias Burger, Thore Graepel and Klaus Obermayer .............. 430 
Incorporating Test Inputs into Learning, 
Zehra Cataltepe and Malik Magdon-Ismail .................... 437 
On Efficient Heuristic Ranking of Hypotheses, 
Steve Chien, Andre Stechert and Darren Mutz .................. 
Learning to Order Things, 
Wfiliam W. Cohen, Robert E. Schapire and Yoram Singer ............. 451 
Regularisation in Sequential Learning Algorithms, 
JoAo F. G. de Freitas, Mahesan Niranjan and Andrew H. Gee ........... 458 
Agnostic Classification of Markovian Sequences, 
Ran EI-Yaniv, Shai Fine and Naftali Tlshby .................... 465 
Ensemble and ModularApproaches for Face Detection: A Comparison, 
Raphael Feraud and Olivier Bernier ....................... 472 
A Revolution: Belief Propagation in Graphs with Cycles, 
Brendan J. Frey and David J. C. MacKay ..................... 479 
Hierarchical Non-linear Factor Analysis and Topographic Maps, 
Zoubin Ghahramani and Geoffrey E. Hinton ................... 486 
Regression with Input-dependent Noise: A Gaussian Process Treatment, 
Paul W. Goldberg, Christopher K. I. Williams and Christopher M. Bishop ..... 493 
Linear Concepts and Hidden Variables: An Empirical Study, 
Adam J. Grove and Dan Roth .......................... 500 
Classification by Pairwise Coupling, Trevor Hastie and Robert Tibshirani ..... 507 
Contents ix 
Unsupervised On-line Learning of Decision Trees for Hierarchical Data 
Analysis, Marcus Held and Joachim M. Buhmann ................. 514 
Nonlinear Markov Networks for Continuous Variables, 
Reimar Holmann and Volker Tresp ........................ 521 
Active Data Clustering, Thomas Hofmann and Joachim M. Buhmann ....... 528 
Function Approximation with the Sweeping Hinge Algorithm, 
Don R. Hush, Fernando Lozano and Bill Home .................. 535 
The Error Coding and Substitution PaCTs, Gareth James and Trevor Hastie .... 542 
S-Map: A Network with a Simple Self-Organization Algorithm for Generarive 
Topographic Mappings, Kimmo Kiviluoto and Erkki Oja ............. 549 
Learning Nonlinear Overcomplete Representations for Efficient Coding, 
Michael S. Lewicki and Terrence J. Sejnowski .................. 556 
Factorizing Multivariate Function Classes, Juan K. Lin .............. 563 
A Framework for Multiple-Instance Learning, 
Oded Maron and Tonaris Lozano-P6rez ...................... 570 
An Application of Reversible-Jump MCMC to Multivariate Spherical Gaussian 
Mixtures, Alan D. Marts ............................. 577 
Estimating Dependency Structure as a Hidden Variable, 
Marina Meil,5 and Michael I. Jordan ....................... 584 
Combining Classifiers Using Correspondence Analysis, Christopher J. Metz . . 591 
Learning Path Distributions Using Nonequilibrium Diffusion Networks, 
Paul Mineiro, Javier Movellan and Ruth J. %rfiliams ............... 598 
Learning Generarive Models with the Up-Propagation Algorithm, 
Jong-Hoon Oh and H. Sebastian Seung ...................... 605 
An Incremental Nearest Neighbor Algorithm with Queries, Joel Ratsaby ..... 612 
RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions, 
Mark Ring .................................... 619 
EM Algorithms for PCA and SPCA, Sam Roweis ................. 626 
Local Dimensionality Reduction, 
Stefan Schaal, Sethu Xqjayakumar and Christopher G. Atkeson .......... 633 
Prior Knowledge in Support Vector Kernels, 
Bernhard Sch61kopf, Patrice Simard, Alex J. Smola and Vladimir Vapnik ..... 640 
Training Methods for Adaptive Boosting of Neural Networks, 
Holger Schwenk and Yoshua Bengio ....................... 647 
Learning Continuous Attractors in Recurrent Networks, H. Sebastian Seung 654 
Monotonic Networks, Joseph Sill ......................... 661 
Stacked Density Estimation, Padhraic Smyth and David Wolpert ......... 668 
x Contents 
Bidirectional Retrieval from Associative Memory, 
Friedrich T. Sommer and G'anther Palm ...................... 675 
Mapping a Manifold of Perceptual Observations, Joshua B. Tenenbaum ...... 682 
Graph Matching with Hierarchical Discrete Relaxation, 
Richard C. W'fison and Edwin R. Hancock .................... 689 
Multiplicative Updating Rule for Blind Separation Derived from the Method of 
Scoring, Howard H. Yang ............................ 696 
Part V Implementation 
A 1,000-Neuron System with One Million 7-bit Physical Interconnections, 
Yuzo Hirai .................................... 705 
Silicon Retina with Adaptive Filtering Propertie& Shih-Chii Liu ......... 712 
Analog VLSI Model of lntersegmental Coordination with Nearest-Neighbor 
Coupling, Girish N. Patel, Jeremy H. Holleman and Stephen P. DeWeerth ..... 719 
An Analog VLSI Neural Network for Phase-based Machine Vision, 
Bertram E. Shi and Kwok Fai Hui ........................ 726 
Part VI Speech, Handwriting and Signal Processing 
Analysis of Drifting Dynamics with Neural Network Hidden Markov Models, 
Jens Kohlmorgen, Klaus-Robert Mtiller and Klaus Pawelzik ........... 735 
Bayesian Robustification for Audio Visual Fusion, 
Javier MoveRan and Paul Mineiro ........................ 742 
Modeling Acoustic Correlations by Factor Analysis, 
Lawrence Saul and Mazin Rahim ......................... 749 
Blind Separation of Radio Signals in Fading Channels, Karl Torkkola ....... 756 
Hybrid NN/I-IMM-Based Speech Recognition with a Discriminant Neural Feature 
Extraction, Daniel Willett and Gerhard Rigoll .................. 763 
Part VII Visual Processing 
A Non-Parametric Multi-Scale Statistical Model for Natural Images, 
Jeremy S. De Bonet and Paul A. Viola ...................... 773 
Recovering Perspective Pose with a Dual Step EM Algorithm, 
Andrew D. J. Cross and Edwin R. Hancock .................... 780 
Bayesian Model of Surface Perception, %rfiliam T Freeman and Paul A. Viola 787 
Features as Sufficient Statistics, 
Davi Geiger, Archismart Rudra and Laurarice T. Maloney ............. 794 
Detection of First and Second Order Motion, 
Alexander Gmnewald and Heiko Neumann .................... 801 
Contents xi 
A Simple and Fast Neural Network Approach to Stereovision, Rolf D. Henkel 808 
Inferring Sparse, Overcomplete Image Codes Using an Efficient Coding 
Framework, Michael S. Lewicki and Bruno A. Olshausen ............. 815 
Visual Navigation in a Robot Using Zig-Zag Behavior, M. Anthony Lewis ..... 822 
2D Observers for Human 3D Object Recognition? Zili Liu and Daniel Kersten 829 
Self-similarity Properties of Natural Images, 
Antonio Turiel, Germfin Mato, N6stor Parga and Jean-Pierre Nadal ........ 836 
Multiresolution Tangent Distance for Affine-invariant Classification, 
Nuno Vasconcelos and Andrew Lippman ..................... 843 
Phase Transitions and the Perceptual Organization of Video Sequences, 
Yak Weiss .................................... 850 
Part VIH Applications 
Using Expectation to Guide Processing: A Study of Three Real-World 
Applications, Shumeet Baluja ......................... 859 
Structure Driven Image Database Retrieval, 
Jeremy S. De Bonet and Paul A. Viola ...................... 866 
A General Purpose Image Processing Chip: Orientation Detection, 
Ralph Etienne-Cummings and Donghui Cai ................... 873 
An Analog VLSI Model of the Fly Elementary Motion Detector, 
Reid R. Harrison and Christof Koch ....................... 880 
MELONET I: Neural Nets for Inventing Baroque-Style Chorale Variations, 
Dominik H6rnel ................................. 887 
Extended ICA Removes Artifacts from Electroencephalographic Recordings, 
Tzyy-Ping Jung, Colin Humphties, Te-Won Lee, Scott Makeig, 
Manfin J. McKeown, Vicente Iragui and Terrence J. Sejnowski .......... 894 
A Generic Approach for Identification of Event Related Brain Potentials via a 
Competitive Neural Network Structure, 
Daniel H. Lange, Hava T. Siegelmann, Hillel Pratt and Gideon F. Inbar ...... 901 
A Neural Network Based Head Tracking System, 
Daniel D. Lee and H. Sebastian Seung ...................... 908 
Wavelet Models for Video Time-Series, Sheng Ma and Chuanyi Ji ......... 915 
Reinforcement Learning for Call Admission Control and Routing in Integrated 
Service Networks, 
Peter Marbach, Oliver Mihatsch, Miriam Schulte and John N. Tsitsildis ...... 922 
Learning to Schedule Straight-Line Code, Eliot Moss, Paul Utgoff, 
John Cavazos, Doina Precup, Darko Stefanovid, Carla Brodley and David Scheeff . 929 
Enhancing Q-Learning for Optimal Asset Allocation, Ralph Neuneier ....... 936 
xii Contents 
Intrusion Detection with Neural Networks, 
Jake Ryan, Meng-Jang Lin and Risto M'fikkulainen ................ 943 
Incorporating Contextual Information in White Blood Cell Identification, 
Xubo Song, Yaser Abu-Mostafa, Joseph Sill and Harvey Kasdan ......... 950 
Bach in a Box--Real-7ime Harmony, 
Randall R. Spangler, Rodney M. Goodman and Jim Hawkins ........... 957 
Experiences with Bayesian Learning in a Real Worm Application, 
Peter Sykacek, Georg Dorffner, Peter Rappelsberger and Josef Zeitlhofer ..... 964 
A Solution for Missing Data in Recurrent Neural Networks with an Application 
to Blood Glucose Prediction, Volker Tresp and Thomas Briegel .......... 971 
Use of a Multi-Layer Perceptron to Predict Malignancy in Ovarian Tumors, 
Herman Verrelst, Yves Moreau, Joos Vandewalle and Dirk Ttmmemmn ...... 978 
Modelling Seasonality and Trends in Daily Rainfall Data, Peter M. Williams . . 985 
The Observer-Observation Dilemma in Neuro-Forecasting, 
Hans Georg Zimmermann and Ralph Netmeier .................. 992 
Part IX Control, Navigation and Planning 
Generalized Prioritized Sweeping, David Andre, Nir Friedman and Ronald Parr . 1001 
Nonparametric Model-Based Reinforcement Learning, Christopher G. Atkeson 1008 
An Improved Policy Iteration Algorithm for Partially Observable MDPS, 
Eric A. Hansen .................................. 1015 
Automated Aircraft Recovery via Reinforcement Learning: Initial Experiments, 
Jeffrey F. Monaco, David G. Ward and Andrew G. Barto ............. 1022 
Reinforcement Learning for Continuous Stochastic Control Problems, 
R6nai Munos and Paul Bourgine ......................... 1029 
Adaptive Choice of Grid and 7ime in Reinforcement Learning, Stephan Pareigis 1036 
Reinforcement Learning with Hierarchies of Machines, 
Ronald Parr and Smart Russell .......................... 1043 
Multi-time Models for Temporally Abstract Planning, 
Doina Precup and Richard S. Sutton ....................... 1050 
How to Dynamically Merge Markov Decision Processes, 
Satinder Singh and David Cohn ......................... 1057 
The Asymptotic Convergence-Rate of Q-learning, Csaba Szepesvfiri ........ 1064 
HybrM Reinforcement Learning and Its Application to Biped Robot Control, 
Satoshi Yamada, Akira Watanabe and Michio Nakashima ............. 1071 
Index of Authors ................................. 1079 
Keyword Index .................................. 1083 
Preface 
The papers in this volume describe the work presented at the Eleventh Annual Conference 
on Neural Information Processing (NIPS), held in Denver, Colorado from December 1 to 
December 6, 1997. The usual competitive standards for acceptance held again, with the 
150 papers presented having been selected from 491 submissions. 
NIPS is arguably one of the strongest and most ambitious interdisciplinary conferences, 
consistently bringing together top researchers in computer science, neuroscience, physics, 
statistics, and many related areas. The unifying topics are broad, such as the study of the 
brain, or interest in biological or computational mechanisms for learning. With such di- 
verse participants and such large themes, it is natural to ask what holds NIPS together, and 
how it became the central technical gathering for so many of its participants. One way of 
expressing the answer is to say that the "relatedness graph" of the work presented at NIPS 
is not a clique, but is strongly connected. Thus, while it is an easy task to find two papers in 
these proceedings and ask how in the world they came to lie in the same volume, that same 
challenge can be met by a list of other papers that fill in the scientific "distance" between the 
initial pair. Thus the entry "Spectrotemporal Receptive Fields for Neurons in the Primary 
Auditory Cortex of the Awake Primate" (DeCharms and Merzenich), which describes the 
application of a clever reverse correlation technique to identify receptive fields for auditory 
neurons, is related in statistical spirit to "Using Helmholtz Machines to Analyze Multi- 
Channel Neuronal Recordings" (De Sa, DeCharms, and Merzenich), which models spike 
train data with multilayer generative models. This latter paper, in turn, shares an interest 
in hidden-variable representations of probability distributions with "A Revolution: Belief 
Propagation in Graphs with Cycles" (Frey and MacKay); which then has a common interest 
in information theory with 'l'he Canonical Distortion Measure in Feature Space and 1-NN 
Classification" (Baxter and Bartlet0. The point is not that the bonds between adjacent pa- 
pers in this sequence are inherent and unbreakable; rather, it is that although the first and 
last papers are on rather different topics and from rather different communities, one can 
see how the interests of a single researcher might easily straddle any one of the links. We 
leave it as exercises for the ambitious reader to construct similar paths between "A Neural 
Network Model of Naive Preference and Filial Imprinting in the Domestic Chick" (Had- 
den) and "Phase Transitions and Perceptual Organization of Video Sequences" (Weiss), 
and between "Modeling Seasonality and Trends in Daily Rainfall Data" (Williams) and 
"Extended ICA Removes Artifacts in White Blood Cell Identification" (Song et al.). While 
we have not worked these particular examples out, we are confident that reasonably short 
solutions exist. 
In addition to the strong program of submitted papers, the conference also featured a lively 
schedule of invited speakers. Ken Nakayama of Harvard gave the banquet talk on "Psy- 
chological Studies of Visual Perception", and invited talks were given by Yoav Freund of 
AT&T Labs ("Boosting: A New Method for Combining Classifiers"), John Hopfield of 
Princeton University ("Computing with Action Potentials"), John Kauer of Tufts Univer- 
sity ("Odor Encoding by the Olfactory System m from Biology to a Receptorless Artifi- 
cial Nose"), Stuart Russell of U.C. Berkeley ("Learning in Rational Agents"), and Man- 
fred Warmuth of U.C. Santa Cruz ("Relative Loss Bounds, the Minimum Relative Entropy 
Principle, and EM"). As is traditional, the main conference was again preceded by a day of 
tutorials introducing current topics of interest to the uninitiated, and followed by two days 
of intensive workshops on a collection of topics that again reflects the focused diversity 
xiv Preface 
that is the strength of NIPS. 
The continued success of NIPS is the result of many hours of hard work by a large and 
distributed group of devoted individuals. We extend many thanks to the members of the 
organizing committee, the program committee, the publicity committee and the NIPS Foun- 
dation board. Special gratitude is due to the referees, whose efforts are clearly shown in 
the quality of the papers gathered here. Thanks to the workshop chairs Steven Nowlan and 
Richard Zemel, tutorials chair Satinder Singh, publicity chair Tony Bell, treasurer Bartlett 
Mel, and local arrangements chair Amn Jagota. A special thanks to Thomas Petsche, who 
in his role of Publication Chair for NIPS*96 developed an excellent and comprehensive 
set of formatting tools for the production of both the Conference Program and the NIPS 
Proceedings. Finally, many thanks to Denise Prell of Conference Consulting Associates 
for her excellent and professional work, and to the many student volunteers who helped 
with conference logistics. We are also grateful to the Office of Naval Research for provid- 
ing financial support to allow many graduate students and young investigators to attend the 
meeting. 
Michael I. Jordan, Massachusetts Institute of Technology 
Michael J. Keams, AT&T Labs - Research 
Sara A. Solla, Northwestern University 
January 24, 1998 
NIPS Committees 
Organizing Committee 
General Chair 
Program Chair 
Workshop Co-Chairs 
Tutorials Chaff 
Publicity Chair 
Publications Chair 
Treasurer 
Local Arrangements Chaff 
Program Committee 
Program Chair 
Algorithms and Architectures 
Theory 
Vision 
Speech and Signal Processing 
Control and Navigation 
Artificial Intelligence 
& Cognitive Science 
Neuroscience 
Applications 
Implementations 
Publicity Committee 
Publicity Chair 
Liason for Australia, Singapore 
and India 
Liason for Europe 
Liason for Hong Kong, China 
and Taiwan 
Liason for Israel 
Liason for Japan 
Liason for Turkey 
Liason for United Kingdom 
Liason for South America 
Web Master 
Michael Jordan, MIT 
Michael Kearns, AT&T Labs - Research 
Steven Nowlan, Lexicus Division, Motorola 
Richard Zemel, University of Arizona 
Satinder Singh, University of Colorado 
Tony Bell, Salk Institute 
Sara Solla, Northwestern University 
Bartlett Mel, University of Southern California 
Arun Jagota, UC Santa Cruz 
Michael Kearns, AT&T Labs - Research 
Joachim Buhmann, University of Bonn 
Tom Dietterich,'Oregon State University 
Lawrence Saul, AT&T Labs - Research 
Jude Shavlik, University of Wisconsin 
Nailall Tishby, Hebrew University 
Michael Turmon, Jet Propulsion Lab 
Paul Viola, MIT 
Richard Lippmann, MIT Lincoln Lab 
Rich Sutton, University of Massachusetts 
Sue Becker, McMaster University 
Tony Zador, Salk Institute 
John Wawrzynek, UC Berkeley 
John Wawrzynek, UC Berkeley 
Tony Bell, Salk Institute 
Marwan Jabri, University of Sydney 
Joachim Buhmann, University of Bonn 
Lei Xu, Chinese University of Hong Kong 
Hava Siegelmann, Technion 
Kenji Doya, ATR Research Laboratories 
Ethem Alpaydin, Bogazici University 
Alan Murray, Edinburgh Univesity 
Andreas Meier, Simon Bolivar University 
Doug Baker, Carnegie Mellon University 
xvi NIPS Committees 
NIPS Foundation Board Members 
President 
Vice President for Development 
Treasurer 
Secretary 
Members 
Emeritus 
NIPS *97 General Chair 
Terrence Sejnowski, Salk Institute 
John Moody, Oregon Graduate Institute 
Eric Mjolsness, UC San Diego 
Gerald Tesauro, IBM Research 
Gary Blasdel, Harvard Medical School 
Leo Breiman, UC Berkeley 
Jack Cowan, University of Chicago 
Stephen Hanson, Rutgers University 
Scott Kirkpatrick, IBM Research 
Richard Lippmann, MIT Lincoln Lab 
Michael Mozer, University of Colorado 
Dave Touretzky, Carnegie Mellon University 
Terrence Fine, Cornell University 
Eve Marder, Brandeis University 
Michael Jordan, MIT 
Reviewers 
Joshua Alspector 
Charles Anderson 
James Anderson 
Timothy Anderson 
Krste Asanovic 
Chris Atkeson 
Leemon Baird 
Pierre Baldi 
Shumeet Baluja 
Naama Barkai 
Marian Bartlett 
Peter Bartlett 
Hans-Ulrich Bauer 
Jon Baxter 
Francoise Beaufays 
Yoshua Bengio 
Michael Berry 
Bill Bialek 
Michael Biehl 
Kwabena Boahen 
Leon Bottou 
Herve Bourlard 
Matthew Brand 
Emanuela Bricolo 
Timothy Brown 
Nader Bshouty 
Neil Burgess 
Paul Bush 
Rich Camana 
Gert Cauwenberghs 
Eric Chang 
Gerald Cheang 
Corinna Cortes 
Gary Cottrell 
Mark Craven 
Peter Dayan 
Joachim Diederich 
Charles Elkan 
Terry Fine 
Gary Flake 
Paolo Frasconi 
Yoav Freund 
Brendan Frey 
Nit Friedman 
Juergen Fritsch 
Patrick Gallinari 
Davi Geiger 
Zoubin Ghahramani 
Lee Giles 
Federico Girosi 
Moises Goldszmidt 
Marco Gori 
Michael Gray 
Rod Grupen 
Isabelle Guyon 
David Hansel 
Lars Hansen 
John Harris 
Trevor Hastie 
Simon Haykin 
David Hemkennan 
John Hertz 
Andreas Herz 
Geoffrey Hinton 
Thomas Hofmann 
Sean Holden 
David Horn 
Nathan Intrator 
Tommi Jaakkola 
Marwan Jabri 
Robert Jacobs 
Charles Jankowski 
Mike Jones 
Michael Jordan 
Leslie Kaelbling 
Bert Kappen 
Mitsuo Kawato 
Hiroaki Kitano 
Adam Kowalczyk 
John Lazzaro 
Yvan Leclerc 
Yann LeCun 
Tai Sing Lee 
Todd Leen 
Zhaoping Li 
Jennifer Linden 
Christiane Linster 
Michael Littman 
David Lowe 
Gabor Lugosi 
Wolfgang Maass 
David Madigan 
Sridhar Mahadevan 
Zach Mainen 
Andrew McCallum 
Marina Meila 
Ron Meir 
Bartlett Mel 
Risto Miikkulainen 
David Miller 
Kenneth Miller 
Tom Mitchell 
Eric Mjolsness 
John Moody 
Andrew Moore 
Javier Movellan 
Michael Mozer 
Klaus Mueller 
Sayandev Mukherjee 
Paul Munro 
Alan Murray 
Venkatesh Murthy 
Radford Neal 
Kenney Ng 
Anna Nobre 
Bruno Olshausen 
David Opitz 
Manfred Opper 
Michael Oren 
Art Owen 
Klaus Pawelzik 
Barak Pearlmutter 
John Pearson 
Fernando Pereira 
Thomas Petsche 
James Pittman 
.iii Reviewers 
John Platt 
Alexandre Pouget 
Jose Principe 
Raj esh Rao 
Anand Rangarajan 
Steve Renals 
Martin Riedmiller 
Brian Ripley 
Raphael Ritz 
Tony Robinson 
David Saad 
Maneesh Sahani 
Stefan Schaal 
Dale Schuurmans 
Sebastian Seung 
Patrice Simard 
Eero Simoncelli 
Yoram Singer 
Satinder Singh 
Diana Smetters 
Padhraic Smyth 
Haim Sompolinsky 
Eduardo Sontag 
Paul Stolorz 
Gene Stoner 
Josh Tenenbaum 
Gerald Tesauro 
Geoffrey Towell 
Volker Tresp 
Todd Troyer 
John Tsitsiklis 
Ian Underwood 
Lyle Ungar 
Joachim Utans 
Benjamin VanRoy 
Rim Venturini 
Grace Wahba 
Eric Wan 
Manfred Warmuth 
Daphna Weinshall 
Yak Weiss 
Janet Wiles 
Christopher Williams 
Ronald Williams 
Laurenz Wiskott 
David Wolpert 
George Zavaliagkos 
Richard Zemel 
