Mean-square exponential input-to-state stability of stochastic quaternion-valued neural networks with time-varying delays

Abstract In this paper, we first consider the stability problem for a class of stochastic quaternion-valued neural networks with time-varying delays. Next, cannot explicitly decompose systems into equivalent real-valued systems; by using Lyapunov functional and analysis techniques, can obtain sufficient conditions mean-square exponential input-to-state networks. Our results are completely new. Finally, numerical example is given to illustrate feasibility our results.