This book provides a powerful tool for collecting and correlating related bodies of research in modelling control and processing in distributed networks. While traditional publications in the field of network models have focussed on specific areas, this successfully intersects many related fields. These cover: control processes, modelling features and operations of biological neural networks and neurons, simulation of biological experimentation, and representation of artificial neural networks (ANNs) Within the fields mentioned, the topics discussed include: control solutions using theoretical computational learning models, learning algorithms and polynomial networks; simulating biological experimentation and physical mechanisms with computer-assisted and hardware models of biological neural networks and neurons; improving processes for representing artificial neural networks by verification from SPICE and global optimization techniques.
Table of Contents:
Contents
Editor's Preface iii
1 Learning in Time Varying Environments p.1
Anthony Kuh and Thomas Petsche
2 Cortical Inhibition as Explained by the Competitive Distribution Hypothesis p.31
James A. Reggia, Granger G. Sutton III, C. Lynne D'Autrechy, Sungzoon Choo and Steve L. Armentrout
3 Implementation of Hartline Pools and Neural-Type Cells by VLSI Circuits p.63
Suan-Wei Tsay and Robert W. Newcomb
4 Self-Organizing Parallel Distributed Neural Network Models p.83
A. Garliauskas and A. Malickas
5 Behavioural Simulation of Neural Networks: An Approach Based upon SPICE P.109
Dario D'Amore and Vincenzo Piuri
6 Induction and Polynomial Networks p.143
John F. Elder IV and Donald E. Brown
About the Author :
Martin D. Fraser is Professor and Chair, Department of Computer Science at Georgia State University. He was Statistical Analysis Manager at American Greetings Corp. and Chief of Software Acceptance Testing at the Air Force Satellite Test Center in Sunnyvale, California. He received a PhD in Mathematics, major Statistics, from St. Louis University and his research interests include software engineering, artificial neural networks, and simulation.
