Recursive Neural Networks for Associative Memory: (Wiley Interscience Series in Systems & Optimization)

Titles of related interest Simulated Annealing and Boltzmann Machines Emile Aarts, Philips Research Laboratories, Eindhoven, and Eindhoven University of Technology, The Netherlands Jan Korst, Philips Research Laboratories, Eindhoven, The Netherlands Simulated annealing is a solution method in the field of combinatorial optimization based on a simulation of the physical process of annealing. A substantial reduction of the computational effort required to use this method may be achieved by using a computational model based on massively parallel execution, such as the Boltzmann machine, which is a neural network model. This book is intended as an introduction to the theory and applications of simulated annealing and Boltzmann machines. It will be of great interest to students and researchers in combinatorial optimization and neural networks, as well as to all those using optimization techniques in practice. 1988 The Metaphorical Brain 2, Neural Networks and Beyond Michael A. Arbib, Program in Neural, Informational and Behavioral Sciences, University of Southern California, USA This book combines two exciting quests, the quest to understand the workings of the human brain and the quest to build intelligent machines. It shows how each quest can provide insights vital to the success of the other. It develops basic ideas about neural networks, both artificial and biological, and introduces the language of schema theory to describe the distributed interactions that underlie intelligence in the brain of human, animal or robot. It reaffirms the paradigm of highly distributed cooperative computation, showing how it not only deepens our understanding of human mind/brain, but also catalyzes the development of a new generation of computing machinery. The book presents many new results, both from my own group and elsewhere, that have enriched that paradigm during the last fifteen years. The book as a whole, although by no means light reading, should be accessible overall to anyone who reads Scientific American; but it is hoped that much of the material merits the attention not only of "the intelligent laymen" but also of experts and serious students of artificial intelligence, neural networks, robotics, cognitive science, or neuroscience'. - From the Author's Preface 1989

Table of Contents:
Principles, Problems and Approaches. The Deterministic Approach. The Statistical Approach. Thermodynamic Extension. Higher Order Networks. Network Design. Bibliography. Index.

About the Author :
Wiley-Interscience Series in Systems and Optimization Advisory Editors Peter Whittle Sheldon Ross The concept of a system as an entity in its own right has emerged with increasing force in the past few decades in, for example, the areas of electrical and control engineering, economics, ecology, urban structures, automaton theory, operational research and industry. The more definite concept of a large-scale system is implicit in these applications, but is particularly evident in fields such as the study of communication networks, computer networks and neural networks. The Wiley--Interscience Series in Systems and Optimization has been established to serve the needs of researchers in these rapidly developing fields. It is intended for works concerned with developments in quantitative systems theory, applications of such theory in areas of interest, or associated methodology. Titles in the Series Multi-Armed Bandit Allocation Indices J.C. Gittins, Statistics Department, Oxford University, UK 1989 Risk-Sensitive Optimal Control Peter Whittle, Statistical Laboratory, University of Cambridge, UK 1990 Recursive Neural Networks for Associative Memory Yves Kamp, Philips Research Laboratory, Louvain-la-Neuve, Belgium Martin Hasler, Ecole Polytechnique FEdErale de Lausanne, Switzerland 1990