$$H_\infty $$ H ∞ state estimation of stochastic neural networks with mixed time-varying delays

Abstract

This paper is concerned with $$H_\infty $$Hź state estimation problem of stochastic neural networks with discrete interval and distributed time-varying delays. The time-varying delay is need to be bounded and continuous. By constructing a suitable Lyapunov---Krasovskii functional with triple integral terms and linear matrix inequality technique, the delay-dependent criteria are conferred so that the error system is stochastically asymptotically mean-square stable with $$H_\infty $$Hź performance. The desired estimator gain matrix can be characterized in terms of the solution to linear matrix inequalities, which can be easily solved by some standard numerical algorithms. Numerical simulations are given to demonstrate the effectiveness of the proposed method. The results are also compared with existing methods.