Mean‐square exponential input‐to‐state stability of stochastic delayed recurrent neural networks with local Lipschitz condition

Abstract

We consider the global existence of solutions and input‐to‐state stability for a class of stochastic delayed recurrent neural networks without uniform Lipschitz condition. Under local Lipschitz condition, we find new sufficient conditions that ensure the solutions of given neural networks exist globally and are mean‐square exponentially input‐to‐state stable. Furthermore, we highlight the advantages of our novel results by comparing with some known results as well as a numerical example.