Advances in Neural Information Processing Systems 8: Proceedings of the 1995 Conference / Edition 1

Hardcover (Print)
Buy New
Buy New from BN.com
$73.33
Used and New from Other Sellers
Used and New from Other Sellers
from $4.78
Usually ships in 1-2 business days
(Save 94%)
Other sellers (Hardcover)
  • All (10) from $4.78   
  • New (4) from $15.90   
  • Used (6) from $4.78   

Overview

The past decade has seen greatly increased interaction between theoretical work in neuroscience, cognitive science and information processing, and experimental work requiring sophisticated computational modeling. The 152 contributions in NIPS 8 focus on a wide variety of algorithms and architectures for both supervised and unsupervised learning. They are divided into nine parts: Cognitive Science, Neuroscience, Theory, Algorithms and Architectures, Implementations,Speech and Signal Processing, Vision, Applications, and Control.Chapters describe how neuroscientists and cognitive scientists use computational models of neural systems to test hypotheses and generate predictions to guide their work. This work includes models of how networks in the owl brainstem could be trained for complex localization function, how cellular activity may underlie rat navigation, how cholinergic modulation may regulate cortical reorganization, and how damage to parietal cortex may result in neglect.Additional work concerns development of theoretical techniques important for understanding the dynamics of neural systems, including formation of cortical maps, analysis of recurrent networks, and analysis of self- supervised learning.Chapters also describe how engineers and computer scientists have approached problems of pattern recognition or speech recognition using computational architectures inspired by the interaction of populations of neurons within the brain. Examples are new neural network models that have been applied to classical problems, including handwritten character recognition and object recognition, and exciting new work that focuses on building electronic hardware modeled after neural systems.A BradfordBook

Human reading & dimensionality, family discovery, memory-based stochastic optimization, etc.

Read More Show Less

Product Details

  • ISBN-13: 9780262201070
  • Publisher: MIT Press
  • Publication date: 6/11/1996
  • Series: Bradford Books Series
  • Edition description: New Edition
  • Edition number: 1
  • Pages: 1120
  • Product dimensions: 7.00 (w) x 10.00 (h) x 2.40 (d)

Meet the Author

Michael C. Mozer is a Professor in the Department of Computer Science and the Institute ofCognitive Science at the University of Colorado, Boulder. In 1990 he received the Presidential YoungInvestigator Award from the National Science Foundation.

Michael E. Hasselmo is Professor of Psychology and Director of the ComputationalNeurophysiology Laboratory at Boston University, where he is also a faculty member in the Center forMemory and Brain and the Program in Neuroscience and principal investigator on grants from theNational Institute of Mental Health and the Office of Naval Research.

Read More Show Less

Table of Contents

Preface
Committees
Part I 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
Part II 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
Part III Theory
Learning Model Bias
Statistical Theory of Overtraining -- Is Cross-ValidationAsymptotically 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
Part IV 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: γOBD, γOBS
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?
Part V 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
Part VI 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
Part VII 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
Part VIII 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
Part IX 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(λ) 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
Read More Show Less

Customer Reviews

Be the first to write a review
( 0 )
Rating Distribution

5 Star

(0)

4 Star

(0)

3 Star

(0)

2 Star

(0)

1 Star

(0)

Your Rating:

Your Name: Create a Pen Name or

Barnes & Noble.com Review Rules

Our reader reviews allow you to share your comments on titles you liked, or didn't, with others. By submitting an online review, you are representing to Barnes & Noble.com that all information contained in your review is original and accurate in all respects, and that the submission of such content by you and the posting of such content by Barnes & Noble.com does not and will not violate the rights of any third party. Please follow the rules below to help ensure that your review can be posted.

Reviews by Our Customers Under the Age of 13

We highly value and respect everyone's opinion concerning the titles we offer. However, we cannot allow persons under the age of 13 to have accounts at BN.com or to post customer reviews. Please see our Terms of Use for more details.

What to exclude from your review:

Please do not write about reviews, commentary, or information posted on the product page. If you see any errors in the information on the product page, please send us an email.

Reviews should not contain any of the following:

  • - HTML tags, profanity, obscenities, vulgarities, or comments that defame anyone
  • - Time-sensitive information such as tour dates, signings, lectures, etc.
  • - Single-word reviews. Other people will read your review to discover why you liked or didn't like the title. Be descriptive.
  • - Comments focusing on the author or that may ruin the ending for others
  • - Phone numbers, addresses, URLs
  • - Pricing and availability information or alternative ordering information
  • - Advertisements or commercial solicitation

Reminder:

  • - By submitting a review, you grant to Barnes & Noble.com and its sublicensees the royalty-free, perpetual, irrevocable right and license to use the review in accordance with the Barnes & Noble.com Terms of Use.
  • - Barnes & Noble.com reserves the right not to post any review -- particularly those that do not follow the terms and conditions of these Rules. Barnes & Noble.com also reserves the right to remove any review at any time without notice.
  • - See Terms of Use for other conditions and disclaimers.
Search for Products You'd Like to Recommend

Recommend other products that relate to your review. Just search for them below and share!

Create a Pen Name

Your Pen Name is your unique identity on BN.com. It will appear on the reviews you write and other website activities. Your Pen Name cannot be edited, changed or deleted once submitted.

 
Your Pen Name can be any combination of alphanumeric characters (plus - and _), and must be at least two characters long.

Continue Anonymously

    If you find inappropriate content, please report it to Barnes & Noble
    Why is this product inappropriate?
    Comments (optional)