State estimation of complex-valued neural networks with two additive time-varying delays

This paper aims at the problem on state estimation of complex-valued neural networks with two additive time-varying delays. Via selecting appropriate Lyapunov-Krasovskii functionals and utilizing reciprocally convex approach and applying matrix inequality technique to analysis, a delay-dependent sufficient condition is derived in the form of linear matrix inequalities (LMIs) to estimate the neuron state with some observed output measurements so as to guarantee the global asymptotic stability of the error-state system. A numerical example is provided to illustrate the feasibility of the obtained result.