Read more
Adaptive Analog VLSI Neural Systems is the first practical book on neural networks learning chips and systems. It covers the entire process of implementing neural networks in VLSI chips, beginning with the crucial issues of learning algorithms in an analog framework and limited precision effects, and giving actual case studies of working systems.
The approach is systems and applications oriented throughout, demonstrating the attractiveness of such an approach for applications such as adaptive pattern recognition and optical character recognition.
Dr Jabri and his co-authors from AT&T Bell Laboratories, Bellcore and the University of Sydney provide a comprehensive introduction to VLSI neural networks suitable for research and development staff and advanced students.
List of contents
Overview. Introduction to neural computing. MOS devices and circuits. Analogue VLSI building blocks. Kakadu - a micropower neural network. Supervised learning in an analog framework. A micropower intracardiac electrogram classifier. On-chip perturbation based learning. An analog memory technique. Switched capacitor techniques. A high speed image understanding system. A Boltzmann machine learning system. References. Index.
About the author
Marwan Jabri is a Reader,
Richard Coggins is a Research Engineer and
Barry Flower is a Research Fellow at SEDAL, Sydney University Electrical Engineering, Australia.
Summary
Using case studies to show the full process of VLSI implementation of a network, this book approaches VLSI neural networks from a practical viewpoint. It also addresses the important issues of learning algorithms and limited precision effects.
