Neural Computing - An Introduction

by R Beale (Department of Computer Science, University of York, UK)

Neural computing is one of the most interesting and rapidly growing areas of research, attracting researchers from a wide variety of scientific disciplines. Starting from the basics, Neural Computing covers all the major approaches, putting each in perspective in terms of their capabilities, advantages, and disadvantages. The book also highlights the applications of each approach and explores the relationships among models developed and between the brain and its function.

A comprehensive and comprehensible introduction to the subject, this book is ideal for undergraduates in computer science, physicists, communications engineers, workers involved in artificial intelligence, biologists, psychologists, and physiologists.

"It is clear that any introductory book must explain what the leaders of the current revival have done. This is well done by Beale and Jackson." Igor Aleksander, Imperial College of Science, Technology and Medicine "Neural Computing is easy on the eye with a good layout and use of graphical icons to draw attention to mathematical proofs, algorithms (in clear format, which would lend itself to computer implementation) and summary sections." Denise Gorse, Times Higher Education Supplement clear that any introductory book must explain what the leaders of the current revival have done. This is well done by Beale and Jackson." Igor Aleksander, Imperial College of Science, Technology and Medicine "Neural Computing is easy on the eye with a good layout and use of graphical icons to draw attention to mathematical proofs, algorithms (in clear format, which would lend itself to computer implementation) and summary sections." Denise Gorse, Times Higher Education Supplement ..." most accessible. ... I was most impressed with the quality of this book. ... hard pressed to beat ..." David Williams, The Australian Computer Journal st accessible. ... I was most impressed with the quality of this book. ... hard pressed to beat ..." David Williams, The Australian Computer Journal

INTRODUCTION
Humans and computers
The structure of the brain
Learning in machines
The differences
Summary

PATTERN RECOGNITION
Introduction
Pattern recognition in perspective
Pattern recognition-a definition
Feature vectors and feature space
Discriminant functions
Classification techniques
Linear classifiers
Statistical techniques
Pattern recognition-a summary

THE BASIC NEURON
Introduction
Modeling the single neuron
Learning in simple neurons
The perceptron: a vectorial perspective
The perceptron learning rule: proof
Limitations of perceptrons
The end of the line?
Summary

THE MULTILAYER PERCEPTRON
Introduction
Altering the perceptron model
The new model
The new learning rule
The multilayer perceptron algorithm
The XOR problem revisited
Visualizing network behavior
Multilayer perceptrons as classifiers
Generalization
Fault tolerance
Learning difficulties
Radial basis functions
Applications
Summary

KOHONEN SELF-ORGANIZING NETWORKS
Introduction
The Kohonen algorithm
Weight training
Neighborhoods
Reducing the neighborhood
Learning vector quantization (LVQ)
The phonetic typewriter
Summary

HOPFIELD NETWORKS
Introduction
The Hopfield model
The energy landscape
The Boltzmann machine
Constraint satisfaction
Summary

ADAPTIVE RESONANCE THEORY
Introduction
Adaptive resonance theory (ART)
Architecture and operation
ART algorithm
Training the ART network
Classification
Conclusion
Summary of ART

ASSOCIATIVE MEMORY
Standard computer memory
Implementing associative memory
Implementation in RAMs
RAMs and N-tupling
Willshaw's associative net
The ADAM system
Kanerva's sparse distributed memory
Bidirectional associative memories
Conclusion
Summary

INTO THE LOOKING GLASS
Overview
Hardware and software implementations
Optical computing
Optical computing and neural networks

INDEX