Mean-square stabilization of impulsive neural networks with mixed delays by non-fragile feedback involving random uncertainties

Abstract

In this paper, we consider a class of neural networks with mixed delays and impulsive interferences. Firstly, a sufficient condition is given to ensure the existence and uniqueness of the equilibrium point of the proposed neural networks by employing the contraction mapping theorem. Secondly, we discuss the issue of the exponential stability in mean-square of the equilibrium point by a non-fragilely delayed output coupling feedback which involves stochastically occurring gain oscillations. The designed feedback input can be tolerant of limited stochastic fluctuations of control gains and be robust against potential errors caused by factors like round-off. By combining methods of Lyapunov–Krasovskii functional and free-weighting matrix, a delay-dependent output coupling feedback with stochastically occurring uncertainties is designed and linear-matrix-inequalities(LMIs)-based sufficient conditions for the exponential stabilization in mean square are derived. Finally, three numerical examples are presented to illustrate the feasibility of theoretical results with a benchmark real-world problem.