Current Neurocontrol Techniques

Abstract

The use of neural networks in control applications (including process control, robotics and aerospace applications, among others) which is referred to as neurocontrol, has begun a pattern of very rapid growth [209]. Neurocontrol can enable the automated control of systems, which could not be controlled in the past for two reasons: the physical cost of implementing a known control algorithm, or the difficulty of finding such an algorithm for complex, noisy, nonlinear problems. The neural network approach is very attractive because of their ability to learn, to approximate functions, to classify patterns and because of their potential for massively parallel hardware implementation.

Besides the electrical engineering theory of the transmission of messages, there is a larger field which includes not only the study of language but the study of messages as a means of controlling machinery and society. the development of computing machines and other such automata, certain reflections upon psychology and the nervous system, and a tentative new theory of scientific method.

Norbert Wiener

(The Human Use of Human Beings)