Mean square asymptotic behavior of stochastic neural networks with infinitely distributed delays

In this paper, according to classic MM-matrix method, integral–differential inequality technique and Ito formula, we study asymptotic behavior in mean square sense of stochastic neural networks with infinitely distributed delays by establishing a generalized Halanay inequality. This is a new means for investigating asymptotic behavior of stochastic differential equation. Some useful results are derived. Especially, our methods can be extended to research pp-moment asymptotic behavior easily. At last, example and simulations demonstrate the power of our methods.