Global asymptotic stability of stochastic neural networks with distributed and time-varying delays

Abstract

This paper is concerned with the asymptotic stability analysis problem for stochastic neural networks with distributed and time-varying delays. By using the stochastic analysis approach, employing some free-weighting matrices and introducing an appropriate type of Lyapunov functional which take into account the ranges of delays, a new stability criterion is established in terms of linear matrix inequalities (LMIs) to guarantee the delayed neural networks to be robustly asymptotically stable in the mean square. And the new criterion is applicable to both fast and slow time-varying delays. One numerical example has been used to demonstrate the usefulness of the main results.