An optimal control model of neural networks for constrained optimization problems

Optimization neural networks have been studied and applied in the literature, and the mechanism of such neural networks has been investigated from the point of view of optimization theory.(1) Yet, no studies have been found by the authors to investigate the mechanism from a control systems' perspective. In this communication, the mechanism of the optimization neural networks will be studied from the point of view of control systems. It will be shown that an optimization neural network can be modelled as an optimal control problem. Copyright (C) 1998 John Wiley & Sons, Ltd.