A state estimator of stochastic delayed neural networks

The problem of state estimation for stochastic Hopfield neural networks with time-varying delay is investigated in this paper. Based on an auxiliary vector and free-weighting matrix technique, a delay-dependent Luenbergertype state estimator, which ensures mean-square asymptotic stability of the resulting filtering error state system, is designed. In this paper, the model transformations and cross terms bounding techniques are avoided. A numerical example is proposed to show the validity of the method.