$$H_{\infty }$$ State Estimation of Static Neural Networks with Mixed Delay

Abstract

This paper focuses on studying the $$H_{\infty }$$ state estimation of static neural networks with mixed delay in which leakage time-varying delay and distributed delay are taken into account, simultaneously. By constructing several suitable Lyapunov–Krasovskii functionals and linear matrix inequality technique, the delay-independent and delay-dependent criteria are established in order that the error system is globally asymptotically stable with $$H_{\infty }$$ performance, respectively. In addition, with the skills to construct Lyapunov–Krasovskii functionals, we obtain the results in which we constitutionally drop the differentiability requirement of transmission delays. Some numerical examples are given to show the effectiveness and advantages of the obtained results.