An Introduction to Neural and Electronic Networks

This is a presentation of research and theory from the disciplines that provide the foundations of neural network research: neurobiology, physics, computer science, electrical engineering, mathematics and psychology. It shows how neural networks and neurocomputing represent radical departures from conventional approaches to digital computers, in terms of algorithms as well as architecture. More than 200 line drawings illustrate the many facets of and approaches to neural networks research. This second edition contains new chapters on computational models of hippocampal and cerebellar function, nonlinear information processing, adaptive filtering and pattern recognition, and digital VLSI architecture. Its interdisciplinary emphasis is aimed at a wide array of researchers and students - from neurobiologists to psychologists. This book: is written by the leading researchers in neural networks; provides an intermediate-level introduction to many important research topics in neuroscience and engineering; emphasizes computational neuroscience, with coverage of mathematical models of specific regions of the brain, such as the hippocampus, the visual system, the sensory neocortex and the olfactory cortex; and emphasizes engineering hardware models of neural networks, including discussions of VLSI and optical modelling principles, holography and resistive networks.

Table of Contents:
Reverse engineering the nervous system, J.M. Bower; brains, and their applications, R. Granger et al; information processing strategies and pathways in the primate visual system, D.C. Van Essen and C.G. Sanderson; neurocomputational theory of hippocampal function in stimulus representation and learning, M.A. Gluck and C.E. Myers; a computational model of the cerebellum and motor-reflex conditioning, M.A. Gluck et al; the design of intelligent robots as a federation of geometric machines, R. Eckmiller; new aproaches to nonlinear concepts in neural information processing, W.J. Freeman and K. Shimoide; neural computation of visual images, P. Mueller et al; models of the neural basis of insect behaviour, R.D. Beer et al; a silicon model of auditory localization, J. Lazzaro and C. Mead; selective recognition automata, G.N. Reeke, Jr. et al; an overview of neural networks, D.L. Reilly and L.N. Cooper; neural nets for adaptive filtering and adaptive pattern recognition, B. Widrow and R. Winter; a construction set for silicon neurons, R. Douglas and M. Mahowald; VLSI implementation of neural networks, F. Faggin and C. Mead; smart vision chips, C. Koch; a digital VLSI architecture for real world applications, D. Hammerstrom; synthetic neural systems in the 90s, L.A. Akers et al; covariance storage in the hippocampus, T.J. Sejnowski and P.K. Stanton; computation of motion by real neurons, N.M. Grzywacz and T. Poggio; brain style computation, D.E. Rumelhart; network self-organization in the ontogenesis of the mammalian visual system, C. von der Malsburg; a neural network architecture for autonomous learning, recognition and prediction in a nonstationary world, G.A. Carpenter and S. Grossberg.