Exponential passive filtering for a class of neutral-type neural networks with time-varying mixed delays

This paper is concerned with the problem of the exponential passive filter design for neutral-type neural networks with time-varying mixed delays. First, a Luenberger-type filter is designed for estimating the network states. Second, by constructing an appropriate Lyapunov-Krasovskii functional and using the so-called Wirtinger-based integral inequality to estimate its derivative, a delay-range-dependent and delay-rate-dependent criterion is presented to ensure the filtering error dynamic system to be exponentially stable and passive with an expected dissipation. Third, since the criterion is presented in the form of linear matrix inequalities with nonlinear constraints, a cone complementarity linearization algorithm is proposed to solve the nonlinear problem. Finally, a numerical example are given to demonstrate the effectiveness of the proposed method.