A new stability condition of neural networks with time-varying delay

Abstract

This paper discusses stability of neural networks (NNs) with time-varying delay. Delay-fractioning Lyapunov-Krasovskii functional (LKF) method and convex analysis are applied to establish a new stability condition. Two possible cases for the delay are taken into account when the delay interval is equivalently divided into two subintervals. The maximal allowable delay that ensures global asymptotical stability of the neural network under consideration can be computed by solving a set of linear matrix inequalities (LMIs). The advantage of the method is illustrated by numerical examples.