Adaptive tracking in nonlinear systems using neural networks

Abstract

Neural networks potentially offer a general framework for modeling and control of nonlinear systems. The conventional neural network models are a parody of biological neural structures, and have the disadvantage of very slow learning. In this paper, we develop a dynamic neural network structure which is based upon the collective computation of subpopulation of neurons, thus different from the conventionally assumed structure of neural networks. The architecture and the learning algorithm to modify weights of the proposed neural model are elucidated. Three applications of this dynamic neural network, namely (i) functional approximation, (ii) control of unknown nonlinear dynamic systems, and (iii) coordination and control of multiple systems, are described through computer simulations. >