Systems and Control
Broad in scope, this text shows the multidisciplinary role of dynamics and control, presents neural networks, fuzzy systems, and genetic algorithms, and provides a self-contained introduction to chaotic systems.
TABLE OF CONTENTS Systems and Control
Chapter 9: Neural Networks
We tend to regard forgetting as a failure of memory, the result of an inadequacy in the machinery for remembering, but a moment's reflection shows that that cannot always be right. If we were to remember every telephone number we have ever used, every scene we have ever looked at, every conversation we have ever heard, every sentence we have ever read, we should be overwhelmed with memories. In fact we transfer to our long-term memory stores only a tiny fraction of the contents of our short-term stores. We retain only what is likely to buseful.
An Anatomy of Thought [101, p. 331]
Overview
This chapter is concerned with neurocomputing, which is also called brainlike computation. The motivation behind studying artificial neural networks, commonly referred to as neural networks, or just neural nets, is to build computers whose construction would mimic the organization of the brain. The brain is the most complex natural information processing system. It is capable of organizing its building blocks, called neurons, to perform computations in a very efficient way. A drawing of a typical biological neuron is given in Figure 9.1. The neuron collects signals from other neurons through its dendrites and receptor sites. The signals have the form of electrical pulses. The pulses received by the dendrites travel to the neuron's cell body where they are being processed. The surface of the cell body of the neuron is dotted with numerous receptor sites that can receive messages from other neurons in a...
Copyright Oxford University Press, Inc. 2003 under license agreement with Books24x7
