State Estimation for Static Neural Networks with Time-Varying Delay via Quadratic Function Negative-Determination Lemma

The H-infinity performance state estimation for static neural networks with time-varying delays is studied in this paper. Firstly, an augmented Lyapunov-Krasovskii functional (LKF) with the triple integral term and the delay-product-type term is constructed. Secondly, a generalized reciprocally convex matrix inequality is employed to deal with the derivative of the LKF. After that, by utilizing the relaxed quadratic function negative-definiteness determination method to dispose of the time derivative of the delay-product-type term, a less conservative state estimation criterion is obtained. Finally, the effectiveness of the proposed method is shown through a numerical example.