Robust delay-distribution-dependent stability of discrete-time stochastic neural networks with time-varying delay

Abstract

A robust delay-distribution-dependent stochastic stability analysis is conducted for a class of discrete-time stochastic delayed neural networks (DSNNs) with parameter uncertainties. The effects of both variation range and distribution probability of the time delay are taken into account in the proposed approach. The distribution probability of time delay is translated into parameter matrices of the transferred DSNNs model, in which the parameter uncertainties are norm-bounded, the stochastic disturbances are described in term of a Brownian motion, and the time-varying delay is characterized by introducing a Bernoulli stochastic variable. Some delay-distribution-dependent criteria for the DSNNs to be robustly globally exponentially stable in the mean square sense are achieved by Lyapunov method and introducing some new analysis techniques. Two numerical examples are provided to show the effectiveness and applicability of the proposed method.