Exponential input-to-state stability of stochastic neural networks with mixed delays

This paper is concerned with the exponential input-to-state stability for a class of stochastic neural networks with mixed delays. Based on a new Lyapunov-Krasovskii functional, Ito’s formula, Dynkin’s formula and some inequality techniques, some novel sufficient conditions ensuring the exponential input-to-state stability in the mean square for the given stochastic neural networks are derived. Some existing results are extended. Two numerical examples are provided to illustrate the effectiveness of the proposed method.