Asymptotic Stability of Stochastic Delayed Recurrent Neural Networks with Impulsive Effects

In this paper, the asymptotic stability for a class of stochastic neural networks with time‐varying delays and impulsive effects are considered. By employing the Lyapunov functional method, combined with linear matrix inequality optimization approach, a new set of sufficient conditions are derived for the asymptotic stability of stochastic delayed recurrent neural networks with impulses. A numerical example is given to show that the proposed result significantly improve the allowable upper bounds of delays over some existing results in the literature.