Dynamic Behavior Analysis of Discrete Neural Networks with Delay

Abstract

The stability of recurrent neural networks is known to be bases of successful applications of the networks. Discrete Hopfield neural networks with delay are extension of discrete Hopfield neural networks without delay. In this paper, the stability of discrete Hopfield neural networks with delay is mainly investigated. The method, which does not make use of energy function, is simple and valid for the dynamic behavior analysis of the neural networks with delay. Several new sufficient conditions for the networks with delay converging towards a limit cycle with length 2 are obtained. All results established here generalize the existing results on the stability of both discrete Hopfield neural networks without delay and with delay in parallel updating mode.