Sampled-data state-estimation of delayed complex-valued neural networks

Abstract

This paper studies the sampled-data state-estimation problem of delayed complex-valued neural networks (CVNNs). By using Lyapunov–Krasovskii functional (LKF), standard integral inequality together with the reciprocal convex approach, a delay-dependent condition is established in terms of the solution to linear matrix inequalities (LMIs) such that the consider CVNNs is asymptotically stable. As a result, an estimator gain matrix can be obtained through sampling instant. Finally, a simulation example is given to illustrate the theoretical analysis.