Input-to-state stability analysis of impulsive stochastic neural networks based on average impulsive interval

This paper addresses the input-to-state stability (ISS) properties, including pth moment ISS (p-ISS) and stochastic ISS (SISS) for a class of impulsive stochastic neural networks with external inputs. Employing Lyapunov functions and stochastic analysis techniques, sufficient conditions in forms of linear matrix inequalities for the p-ISS and SISS are established based on the average impulsive interval concept. Moreover, a criterion on the pth moment globally asymptotic stability and globally asymptotic stability in probability is derived as a corollary. Finally, an example is provided to illustrate the effectiveness of the obtained results.