Neural Network Architecture for Control

Abstract

Two important computational features of neural networks are (1) associative storage and retrieval of knowledge and (2) uniform rate of convergence of network dynamics, independent of network dimension. This paper indicates how these properties can be used for adaptive control through the use of neural network computation algorithms and outlines resulting computational advantages. The neuromorphic control approach is compared to model reference adaptive control on a specific example. The utilization of neural networks for adaptive control offers definite speed advantages over traditional approaches for very large scale systems. © 1988 IEEE