| Preface |
|
xv | |
| NIPS Committees |
|
xvii | |
| Reviewers |
|
xix | |
| Part I Cognitive Science |
|
|
Evidence for a Forward Dynamics Model in Human Adaptive Motor Control |
|
|
3 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Perceiving without Learning: From Spirals to Inside/Outside Relations |
|
|
10 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A Model for Associative Multiplication |
|
|
17 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Facial Memory Is Kernel Density Estimation (Almost) |
|
|
24 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Multiple Paired Forward-Inverse Models for Human Motor Learning and Control |
|
|
31 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Utilizing Time: Asynchronous Binding |
|
|
38 | (7) |
|
|
|
|
|
|
Mechanisms of Generalization in Perceptual Learning |
|
|
45 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A Principle for Unsupervised Hierarchical Decomposition of Visual Scenes |
|
|
52 | (7) |
|
|
|
|
|
|
Bayesian Modeling of Human Concept Learning |
|
|
59 | (10) |
|
|
|
|
|
| Part II Neuroscience |
|
|
Temporally Asymmetric Hebbian Learning, Spike Timing and Neural Response Variability |
|
|
69 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Contrast Adaptation in Simple Cells by Changing the Transmitter Release Probability |
|
|
76 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Where Does the Population Vector of Motor Cortical Cells Point during Reaching Movements? |
|
|
83 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Recurrent Cortical Amplification Produces Complex Cell Responses |
|
|
90 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Neuronal Regulation Implements Efficient Synaptic Pruning |
|
|
97 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Divisive Normalization, Line Attractor Networks and Ideal Observers |
|
|
104 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Synergy and Redundancy among Brain Cells of Behaving Monkeys |
|
|
111 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Analyzing and Visualizing Single-Trial Event-Related Potentials |
|
|
118 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Spike-Based Compared to Rate-Based Hebbian Learning |
|
|
125 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Signal Detection in Noisy Weakly-Active Dendrites |
|
|
132 | (7) |
|
|
|
|
|
|
|
|
|
|
|
The Role of Lateral Cortical Competition in Ocular Dominance Development |
|
|
139 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Multi-Electrode Spike Sorting by Clustering Transfer Functions |
|
|
146 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Modeling Surround Suppression in VI Neurons with a Statistically Derived Normalization Model |
|
|
153 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Information Maximization in Single Neurons |
|
|
160 | (7) |
|
|
|
|
|
|
|
|
|
|
|
The Effect of Correlations on the Fisher Information of Population Codes |
|
|
167 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Distributional Population Codes and Multiple Motion Models |
|
|
174 | (9) |
|
|
|
|
|
|
|
|
|
|
| Part III Theory |
|
|
Tractable Variational Structures for Approximating Graphical Models |
|
|
183 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Almost Linear VC Dimension Bounds for Piecewise Polynomial Networks |
|
|
190 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Dynamics of Supervised Learning with Restricted Training Sets |
|
|
197 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Dynamically Adapting Kernels in Support Vector Machines |
|
|
204 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Phase Diagram and Storage Capacity of Sequence-Storing Neural Networks |
|
|
211 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Finite-Dimensional Approximation of Gaussian Processes |
|
|
218 | (7) |
|
Giancarlo Ferrari-Trecate |
|
|
|
|
|
Christopher K. I. Williams |
|
|
|
|
|
|
|
|
|
|
Linear Hinge Loss and Average Margin |
|
|
225 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Unsupervised and Supervised Clustering: The Mutual Information between Parameters and Observations |
|
|
232 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Convergence of the Wake-Sleep Algorithm |
|
|
239 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
246 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Optimizing Classifers for Imbalanced Training Sets |
|
|
253 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Inference in Multilayer Networks via Large Deviation Bounds |
|
|
260 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Stationarity and Stability of Autoregressive Neural Network Processes |
|
|
267 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Computational Differences between Asymmetrical and Symmetrical Networks |
|
|
274 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A Precise Characterization of the Class of Languages Recognized by Neural Nets under Gaussian and Other Common Noise Distributions |
|
|
281 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Direct Optimization of Margins Improves Generalization in Combined Classifiers |
|
|
288 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
On the Optimality of Incremental Neural Network Algorithms |
|
|
295 | (7) |
|
|
|
|
|
|
|
|
|
|
|
General Bounds on Bayes Errors for Regression with Gaussian Processes |
|
|
302 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Mean Field Methods for Classification with Gaussian Processes |
|
|
309 | (7) |
|
|
|
|
|
|
|
|
|
|
|
On-Line Learning with Restricted Training Sets: Exact Solution as Benchmark for General Theories |
|
|
316 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Tight Bounds for the VC-Dimension of Piecewise Polynomial Networks |
|
|
323 | (7) |
|
|
|
|
|
|
Shrinking the Tube: A New Support Vector Regression Algorithm |
|
|
330 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Discontinuous Recall Transitions Induced by Competition Between Short-and Long-Range Interactions in Recurrent Networks |
|
|
337 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Learning Curves for Gaussian Processes |
|
|
344 | (7) |
|
|
|
|
|
|
A Theory of Mean Field Approximation |
|
|
351 | (10) |
|
|
|
|
|
| Part IV Algorithms and Architecture |
|
|
Learning a Hierarchical Belief Network of Independent Factor Analyzers |
|
|
361 | (7) |
|
|
|
|
|
|
Semi-Supervised Support Vector Machines |
|
|
368 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Lazy Learning Meets the Recursive Least Squares Algorithm |
|
|
375 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
382 | (7) |
|
|
|
|
|
|
Learning Multi-Class Dynamics |
|
|
389 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Approximate Learning of Dynamic Models |
|
|
396 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Fisher Scoring and a Mixture of Modes Approach for Approximate Inference and Learning in Nonlinear State Space Models |
|
|
403 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Global Optimisation of Neural Network Models via Sequential Sampling |
|
|
410 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Efficient Bayesian Parameter Estimation in Large Discrete Domains |
|
|
417 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A Randomized Algorithm for Pairwise Clustering |
|
|
424 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Learning Nonlinear Dynamical Systems Using an EM Algorithm |
|
|
431 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Classification on Pairwise Proximity Data |
|
|
438 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Outcomes of the Equivalence of Adaptive Ridge with Least Absolute Shrinkage |
|
|
445 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Visualizing Group Structure |
|
|
452 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Source Separation as a By-Product of Regularization |
|
|
459 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Learning from Dyadic Data |
|
|
466 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Sparse Code Shrinkage: Denoising by Nonlinear Maximum Likelihood Estimation |
|
|
473 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Restructuring Sparse High Dimensional Data for Effective Retrieval |
|
|
480 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Exploiting Generative Models in Discriminative Classifiers |
|
|
487 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Maximum Conditional Likelihood via Bound Maximization and the CEM Algorithm |
|
|
494 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A Polygonal Line Algorithm for Constructing Principal Curves |
|
|
501 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Unsupervised Classification with Non-Gaussian Mixture Models Using ICA |
|
|
508 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Learning a Continuous Hidden Variable Model for Binary Data |
|
|
515 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Neural Networks for Density Estimation |
|
|
522 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Exploratory Data Analysis Using Radial Basis Function Latent Variable Models |
|
|
529 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Kernel PCA and De-Noising in Feature Spaces, Sebastian Mika |
|
|
536 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Very Fast EM-Based Mixture Model Clustering Using Multiresolution Kd-Trees |
|
|
543 | (7) |
|
|
|
|
|
|
Replicator Equations, Maximal Cliques, and Graph Isomorphism |
|
|
550 | (7) |
|
|
|
|
|
|
Using Analytic QP and Sparseness to Speed Training of Support Vector |
|
|
557 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
564 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Boxlets: A Fast Convolution Algorithm for Signal Processing and Neural Network |
|
|
571 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Batch and On-Line Parameter Estimation of Gaussian Mixtures Based on the Joint Entropy |
|
|
578 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Semiparametric Support Vector and Linear Programming Machines |
|
|
585 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Probabilistic Visualisation of High-Dimensional Binary Data |
|
|
592 | (7) |
|
|
|
|
|
|
SMEM Algorithm for Mixture Models |
|
|
599 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Learning Mixture Hierachies |
|
|
606 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Discovering Hidden Features with Gaussian Processes Regression |
|
|
613 | (7) |
|
|
|
|
|
|
Christopher K. I. Williams |
|
|
|
|
|
The Bias-Variance Tradeoff and the Randomized GACV, Grace Wahba |
|
|
620 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Basis Selection for Wavelet Regression |
|
|
627 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
634 | (7) |
|
Christopher K. I. Williams |
|
|
|
|
|
|
|
|
|
|
Convergence Rates of Algorithms for Visual Search: Detecting Visual Contours |
|
|
641 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Blind Separation of Filtered Sources Using State-Space Approach |
|
|
648 | (9) |
|
|
|
|
|
|
|
|
|
|
| Part V Implementation |
|
|
Analog VLSI Cellular Implementation of the Boundary Contour System |
|
|
657 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Active Noise Canceling Using Analog Neuro-Chip with On-Chip Learning Capability |
|
|
664 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A Micropower CMOS Adaptive Amplitude and Shift Invariant Vector Quantiser |
|
|
671 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Optimizing Correlation Algorithms for Hardware-Based Transient Classification |
|
|
678 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
VLSI Implementation of Motion Centroid Localization for Autonomous Navigation |
|
|
685 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
A Neuromorphic Monaural Sound Localizer |
|
|
692 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
An Integrated Vision Sensor for the Computation of Optical Flow Singular Points |
|
|
699 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Computation of Smooth Optical Flow in a Feedback Connected Analog Network |
|
|
706 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A High Performance k-NN Classifier Using a Binary Correlation Matrix Memory |
|
|
713 | (10) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Part VI Speech, Handwriting and Signal Processing |
|
|
An Entropic Estimator for Structure Discovery |
|
|
723 | (7) |
|
|
|
|
|
|
Coding Time-Varying Signals Using Sparse, Shift-Invariant Representations |
|
|
730 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Controlling the Complexity of HMM Systems by Regularization |
|
|
737 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Maximum-Likelihood Continuity Mapping (MALCOM): An Alternative to HMMs |
|
|
744 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Markov Processes on Curves for Automatic Speech Recognition |
|
|
751 | (10) |
|
|
|
|
|
|
|
|
|
|
| Part VII Visual Processing |
|
|
A Phase Space Approach to Minimax Entropy Learning and the Minutemax Approximations |
|
|
761 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Example-Based Image Synthesis of Articulated Figures |
|
|
768 | (7) |
|
|
|
|
|
|
Learning to Estimate Scenes from Images |
|
|
775 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Learning to Find Pictures of People |
|
|
782 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Attentional Modulation of Human Pattern Discrimination Psychophysics Reproduced by a Quantitative Model |
|
|
789 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
A VI Model of Pop Out and Asymmetry in Visual Search |
|
|
796 | (7) |
|
|
|
|
|
|
Support Vector Machines Applied to Face Recognition |
|
|
803 | (7) |
|
|
|
|
|
|
Learning Lie Groups for Invariant Visual Perception |
|
|
810 | (7) |
|
|
|
|
|
|
|
|
|
|
|
General-Purpose Localization of Textured Image Regions |
|
|
817 | (7) |
|
|
|
|
|
|
Probabilistic Image Sensor Fusion |
|
|
824 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour |
|
|
831 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Classification in Non-Metric Spaces |
|
|
838 | (9) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Part VIII Applications |
|
|
Making Templates Rotationally Invariant: An Application to Rotated Digit Recognition |
|
|
847 | (7) |
|
|
|
|
|
|
Probabilistic Modeling for Face Orientation Discrimination: Learning from Labeled and Unlabeled Data |
|
|
854 | (7) |
|
|
|
|
|
|
Adding Constrained Discontinuities to Gaussian Process Models of Wind Fields |
|
|
861 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Christopher K.I. Williams |
|
|
|
|
|
Vertex Identification in High Energy Physics Experiments |
|
|
868 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Familiarity Discrimination of Radar Pulses |
|
|
875 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Fast Neural Network Emulation of Dynamical Systems for Computer Animation |
|
|
882 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Call-Based Fraud Detection in Mobile Communication Networks Using a Hierarchical Regime-Switching Model |
|
|
889 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Graph Matching for Shape Retrieval |
|
|
896 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Scheduling Straight-Line Code Using Reinforcement Learning and Rollouts |
|
|
903 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Bayesian Modeling of Facial Similarity |
|
|
910 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Reinforcement Learning for Trading |
|
|
917 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Graphical Models for Recognizing Human Interactions |
|
|
924 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Independent Component Analysis of Intracellular Calcium Spike Data |
|
|
931 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Applications of Multi-Resolution Neural Networks to Mammography |
|
|
938 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Robot Docking Using Mixtures of Gaussians |
|
|
945 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Using Collective Intelligence to Route Internet Traffic |
|
|
952 | (9) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Part IX Control, Navigation and Planning |
|
|
Robust, Efficient, Globally-Optimized Reinforcement Learning with the Parti-Game Algorithm |
|
|
961 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Gradient Descent for General Reinforcement Learning |
|
|
968 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Non-Linear PI Control Inspired by Biological Control Systems |
|
|
975 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Optimizing Admission Control while Ensuring Quality of Service in Multimedia Networks via Reinforcement Learning |
|
|
982 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Viewing Classifier Systems as Model Free Learning in POMDPs |
|
|
989 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms |
|
|
996 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Exploring Unknown Environments with Real-Time Search or Reinforcement Learning |
|
|
1003 | (7) |
|
|
|
|
|
|
The Effect of Eligibility Traces on Finding Optimal Memoryless Policies in Partially Observable Markov Decision Processes |
|
|
1010 | (7) |
|
|
|
|
|
|
Learning Instance-Independent Value Functions to Enhance Local Search |
|
|
1017 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Barycentric Interpolators for Continuous Space and Time Reinforcement Learning |
|
|
1024 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Risk Sensitive Reinforcement Learning |
|
|
1031 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Coordinate Transformation Learning of Hand Position Feedback Controller by Using Change of Position Error Norm |
|
|
1038 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Learning Macro-Actions in Reinforcement Learning |
|
|
1045 | (7) |
|
|
|
|
|
|
Reinforcement Learning Based on On-Line EM Algorithm |
|
|
1052 | (7) |
|
|
|
|
|
|
|
|
|
|
|
A Reinforcement Learning Algorithm in Partially Observable Environments Using Short-Term Memory |
|
|
1059 | (7) |
|
|
|
|
|
|
|
|
|
|
|
Improved Switching among Temporally Abstract Actions |
|
|
1066 | (7) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Experimental Results on Learning Stochastic Memoryless Policies for Partially Observable Markov Decision Processes |
|
|
1073 | (8) |
|
|
|
|
|
|
|
|
|
|
| Index of Authors |
|
1081 | (4) |
| Keyword Index |
|
1085 | |
Other versions by this Author