Further Results on Mean-Square Exponential Input-to-State Stability of Stochastic Delayed Cohen-Grossberg Neural Networks

We consider the global existence of solutions and mean-square exponential input-to-state stability for a class of stochastic delayed Cohen-Grossberg neural networks without global 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 the results in Zhou et al. (2015) as well as a numerical example.