On the stability analysis of delayed neural networks systems

In this paper, the problems of stability of delayed neural networks are inv estigated, including the stability of discrete and distributed delayed neur al networks. Under the generalization of dropping the Lipschitzian hypothes es for output functions, some stability criteria are obtained by using the Liapunov functional method. We do not assume the symmetry of the connection matrix and we establish that the system admits a unique equilibrium point in which the output functions do not satisfy the Lipschitz conditions and d o not require them to be differential or strictly monotonously increasing. These criteria can be used to analyze the dynamics of biological neural sys tems or to design globally stable artificial neural networks. (C) 2001 Else vier Science Ltd. All rights reserved.