| |
| |
| Preface | |
| |
| |
| Committees | |
| |
| |
| |
| Cognitive Science | |
| |
| |
| Learning the Structure of Similarity | |
| |
| |
| A Model of Spatial Representations in Parietal Cortex Explains Hemineglect | |
| |
| |
| Human Reading and the Curse of Dimensionality | |
| |
| |
| Extracting Tree-structured Representations of Trained Networks | |
| |
| |
| Harmony Networks Do Not Work | |
| |
| |
| Dynamics of Attention as Near Saddle-node Bifurcation Behavior | |
| |
| |
| Rapid Quality Estimation of Neural Network Input Representations | |
| |
| |
| A Model of Auditory Streaming | |
| |
| |
| |
| Neuroscience | |
| |
| |
| Modeling Interactions of the Rat's Place and Head Direction Systems | |
| |
| |
| Correlated Neuronal Response: Time Scales and Mechanisms | |
| |
| |
| Information through a Spiking Neuron | |
| |
| |
| Reorganization of Somatosensory Cortex after Tactile Training | |
| |
| |
| A Dynamical Model of Context Dependencies for the Vestibulo-Ocular Reflex | |
| |
| |
| The Role of Activity in Synaptic Competition at the Neuromuscular Junction | |
| |
| |
| When Is an Integrate-and-fire Neuron like a Poisson Neuron? | |
| |
| |
| How Perception Guides Production in Birdsong Learning | |
| |
| |
| The Geometry of Eye Rotations and Listing's Law | |
| |
| |
| Temporal Coding in the Submillisecond Range: Model of Barn Owl Auditory Pathway | |
| |
| |
| Cholinergic Suppression of Transmission May Allow Combined Associative Memory Function and Self-organization in the Neocortex | |
| |
| |
| A Predictive Switching Model of Cerebellar Movement Control | |
| |
| |
| Independent Component Analysis of Electroencephalographic Data | |
| |
| |
| Simulation of a Thalamocortical Circuit for Computing Directional Heading in the Rat | |
| |
| |
| Plasticity of Center-Surround Opponent Receptive Fields in Real and Artificial Neural Systems of Vision | |
| |
| |
| |
| Theory | |
| |
| |
| Learning Model Bias | |
| |
| |
| Statistical Theory of Overtraining -- Is Cross-Validation Asymptotically Effective? | |
| |
| |
| A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for the Training-test Split | |
| |
| |
| Learning with Ensembles: How Overfitting Can Be Useful | |
| |
| |
| Neural Networks with Quadratic VC Dimension | |
| |
| |
| Sample Complexity for Learning Recurrent Perceptron Mappings | |
| |
| |
| On the Computational Power of Noisy Spiking Neurons | |
| |
| |
| A Realizable Learning Task Which Exhibits Overfitting | |
| |
| |
| Stable Dynamic Parameter Adaptation | |
| |
| |
| Estimating the Bayes Risk from Sample Data | |
| |
| |
| Recursive Estimation of Dynamic Modular RBF Networks | |
| |
| |
| On Neural Networks with Minimal Weights | |
| |
| |
| Modern Analytic Techniques to Solve the Dynamics of Recurrent Neural Networks | |
| |
| |
| Implementation Issues in the Fourier Transform Algorithm | |
| |
| |
| Generalisation of a Class of Continuous Neural Networks | |
| |
| |
| Gradient and Hamiltonian Dynamics Applied to Learning in Neural Networks | |
| |
| |
| Optimization Principles for the Neural Code | |
| |
| |
| Strong Unimodality and Exact Learning of Constant Depth 5-Perceptron Networks | |
| |
| |
| Active Learning in Multilayer Perceptrons | |
| |
| |
| Dynamics of On-line Gradient Descent Learning for Multilayer Neural Networks | |
| |
| |
| Worst-case Loss Bounds for Single Neurons | |
| |
| |
| Exponentially Many Local Minima for Single Neurons | |
| |
| |
| Adaptive Back-Propagation in On-line Learning of Multilayer Networks | |
| |
| |
| Optimizing Cortical Mappings | |
| |
| |
| Quadratic-type Lyapunov Functions for Competitive Neural Networks with Different Time-scales | |
| |
| |
| Examples of Learning Curves from a Modified VC-formalism | |
| |
| |
| Bayesian Methods for Mixtures of Experts | |
| |
| |
| Some Results on Convergent Unlearning Algorithm | |
| |
| |
| Geometry of Early Stopping in Linear Networks | |
| |
| |
| Absence of Cycles in Symmetric Neural Networks | |
| |
| |
| |
| Algorithms and Architectures | |
| |
| |
| Adaptive Mixture of Probabilistic Transducers | |
| |
| |
| REMAP: Recursive Estimation and Maximization of A Posteriori Probabilities -- Application to Transition-based Connectionist Speech Recognition | |
| |
| |
| Recurrent Neural Networks for Missing or Asynchronous Data | |
| |
| |
| Family Discovery | |
| |
| |
| Discriminant Adaptive Nearest Neighbor Classification and Regression | |
| |
| |
| Clustering Data through an Analogy to the Potts Model | |
| |
| |
| Generalized Learning Vector Quantization | |
| |
| |
| Stochastic Hillclimbing as a Baseline Method for Evaluating Genetic Algorithms | |
| |
| |
| Symplectic Nonlinear Component Analysis | |
| |
| |
| A Unified Learning Scheme: Bayesian-Kuilback Ying-Yang Machine | |
| |
| |
| Universal Approximation and Learning of Trajectories Using Oscillators | |
| |
| |
| A Smoothing Regularizer for Recurrent Neural Networks | |
| |
| |
| EM Optimization of Latent-Variable Density Models | |
| |
| |
| Factorial Hidden Markov Models | |
| |
| |
| Boosting Decision Trees | |
| |
| |
| Exploiting Tractable Substructures in Intractable Networks | |
| |
| |
| Hierarchical Recurrent Neural Networks for Long-term Dependencies | |
| |
| |
| Discovering Structure in Continuous Variables Using Bayesian Networks | |
| |
| |
| Using Pairs of Data Points to Define Splits for Decision Trees | |
| |
| |
| Gaussian Processes for Regression | |
| |
| |
| Pruning with Generalization Based Weight Saliencies: �OBD, �OBS | |
| |
| |
| Fast Learning by Bounding Likelihoods in Sigmoid Type Belief Networks | |
| |
| |
| Generating Accurate and Diverse Members of a Neural-network Ensemble | |
| |
| |
| Improved Gaussian Mixture Density Estimates Using Bayesian Penalty Terms and Network Averaging | |
| |
| |
| Explorations with the Dynamic Wave Model | |
| |
| |
| The Capacity of a Bump | |
| |
| |
| Tempering Backpropagation Networks: Not All Weights Are Created Equal | |
| |
| |
| Investment Learning with Hierarchical PSOMS | |
| |
| |
| Learning Long-term Dependencies Is Not as Difficult with NARX Networks | |
| |
| |
| Constructive Algorithms for Hierarchical Mixtures of Experts | |
| |
| |
| An Information-theoretic Learning Algorithm for Neural Network Classification | |
| |
| |
| A Practical Monte Carlo Implementation of Bayesian Learning | |
| |
| |
| From Isolation to Cooperation: An Alternative View of a System of Experts | |
| |
| |
| Finite State Automata that Recurrent Cascade-Correlation Cannot Represent | |
| |
| |
| SPERT-II: A Vector Microprocessor System and Its Application to Large Problems in Backpropagation Training | |
| |
| |
| Softassign versus Softmax: Benchmarks in Combinatorial Optimization | |
| |
| |
| A Multiscale Attentional Framework for Relaxation Neural Networks | |
| |
| |
| Is Learning the n-th Thing Any Easier Than Learning the First? | |
| |
| |
| Using Unlabeled Data for Supervised Learning | |
| |
| |
| Learning Sparse Perceptrons | |
| |
| |
| Does the Wake-sleep Algorithm Produce Good Density Estimators? | |
| |
| |
| |
| Implementations | |
| |
| |
| Improved Silicon Cochlea Using Compatible Lateral Bipolar Transistors | |
| |
| |
| Adaptive Retina with Center-Surround Receptive Field | |
| |
| |
| Neuron-MOS Temporal Winner Search Hardware for Fully-parallel Data Processing | |
| |
| |
| Analog VLSI Processor Implementing the Continuous Wavelet Transform | |
| |
| |
| Silicon Models for Auditory Scene Analysis | |
| |
| |
| VLSI Model of Primate Visual Smooth Pursuit | |
| |
| |
| Model Matching and SFMD Computation | |
| |
| |
| Parallel Analog VLSI Architectures for Computation of Heading Direction and Time-to-contact | |
| |
| |
| |
| Speech and Signal Processing | |
| |
| |
| Onset-based Sound Segmentation | |
| |
| |
| Laterally Interconnected Self-organizing Maps in Handwritten Digit Recognition | |
| |
| |
| Forward-backward Retraining of Recurrent Neural Networks | |
| |
| |
| Context-dependent Classes in a Hybrid Recurrent Network-HMM Speech Recognition System | |
| |
| |
| A New Learning Algorithm for Blind Signal Separation | |
| |
| |
| Handwritten Word Recognition Using Contextual Hybrid Radial Basis Function Network/Hidden Markov Models | |
| |
| |
| Selective Attention for Handwritten Digit Recognition | |
| |
| |
| Kodak Imagelink� | |
| |
| |
| OCR Alphanumeric Handprint Module | |
| |
| |
| The Gamma MLP for Speech Phoneme Recognition | |
| |
| |
| |
| Vision | |
| |
| |
| A Framework for Nonrigid Matching and Correspondence | |
| |
| |
| Control of Selective Visual Attention: Modeling the "Where" Pathway | |
| |
| |
| Unsupervised Pixel-prediction | |
| |
| |
| Learning to Predict Visibility and Invisibility from Occlusion Events | |
| |
| |
| Classifying Facial Action | |
| |
| |
| Modeling Saccadic Targeting in Visual Search | |
| |
| |
| A Model of Transparent Motion and Non-transparent Motion Aftereffects | |
| |
| |
| A Neural Network Model of 3-D Lightness Perception | |
| |
| |
| Empirical Entropy Manipulation for Real-world Problems | |
| |
| |
| Active Gesture Recognition Using Learned Visual Attention | |
| |
| |
| Seemore: A View-based Approach to 3-D Object Recognition Using Multiple Visual Cues | |
| |
| |
| |
| Applications | |
| |
| |
| Human Face Detection in Visual Scenes | |
| |
| |
| Improving Committee Diagnosis with Resampling Techniques | |
| |
| |
| Primitive Manipulation Learning with Connectionism | |
| |
| |
| Beating a Defender in Robotic Soccer: Memory-based Learning of a Continuous Function | |
| |
| |
| Visual Gesture-based Robot Guidance with a Modular Neural System | |
| |
| |
| A Novel Channel Selection System in Cochlear Implants Using Artificial Neural Network | |
| |
| |
| Prediction of Beta Sheets in Proteins | |
| |
| |
| A Neural Network Autoassociator for Induction Motor Failure Prediction | |
| |
| |
| Using Feedforward Neural Networks to Monitor Alertness from Changes in EEG Correlation and Coherence | |
| |
| |
| A Neural Network Classifier for the I1000 OCR Chip | |
| |
| |
| Predictive Q-Routing: A Memory-based Reinforcement Learning Approach to Adaptive Traffic Control | |
| |
| |
| Optimal Asset Allocation Using Adaptive Dynamic Programming | |
| |
| |
| Using the Future to "Sort Out" the Present: Rankprop and Multitask Learning for Medical Risk Evaluation | |
| |
| |
| Stock Selection via Nonlinear Multi-factor Models | |
| |
| |
| Experiments with Neural Networks for Real Time Implementation of Control | |
| |
| |
| High-speed Airborne Particle Monitoring Using Artificial Neural Networks | |
| |
| |
| |
| Control | |
| |
| |
| A Dynamical Systems Approach for a Learnable Autonomous Robot | |
| |
| |
| Parallel Optimization of Motion Controllers via Policy Iteration | |
| |
| |
| Learning Fine Motion by Markov Mixtures of Experts | |
| |
| |
| Neural Control for Nonlinear Dynamic Systems | |
| |
| |
| Improving Elevator Performance Using Reinforcement Learning | |
| |
| |
| High-performance Job-Shop Scheduling with a Time-delay TD(�) Network | |
| |
| |
| Competence Acquisition in an Autonomous Mobile Robot Using Hardware Neural Techniques | |
| |
| |
| Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding | |
| |
| |
| Stable Linear Approximations to Dynamic Programming for Stochastic Control Problems with Local Transitions | |
| |
| |
| Stable Fitted Reinforcement Learning | |
| |
| |
| Improving Policies without Measuring Merits | |
| |
| |
| Memory-based Stochastic Optimization | |
| |
| |
| Temporal Difference in Learning in Continuous Time and Space | |
| |
| |
| Reinforcement Learning by Probability Matching | |
| |
| |
| Author Index | |
| |
| |
| Keyword Index | |