Further Result on H ∞ Performance State Estimation of Delayed Static Neural Networks Based on an Improved Reciprocally Convex Inequality

Abstract

In this brief, an improved reciprocally convex inequality is presented to analyse the problem of $H_{\infty }$ performance state estimation for static neural networks. A tight upper bound of time-derivative for the Lyapunov functional is handled by the improved reciprocally convex inequality. Then, a less conservative $H_{\infty }$ performance state estimation criterion is derived. As a result, the criterion is employed to present a method for designing suitable estimator gain matrices. A numerical example is used to illustrate the effectiveness of the proposed method.