A delay-dependent approach to design state estimator for discretestochastic recurrent neural network with interval time-varying delays

This paper deals with the problem of state estimation for discretestochastic recurrent neural network with interval time-delays. The activationfunctions are assumed to be globally Lipschitz continuous. Attention is focusedon the design of a state estimator which ensures the global stability of theestimation error dynamics. A delay-dependent condition with dependence on theupper and lower bounds of the delays is given in terms of a linear matrixinequality (LMI) to solve the neuron state estimation problem. When this LMI isfeasible, the expression of a desired state estimator is also presented. Inaddition, slack matrices are introduced to reduce the conservatism of thecondition. A numerical example is provided to demonstrate the applicability ofthe proposed approach. ICIC International