A DELAY-DEPENDENT APPROACH TO DESIGN STATE ESTIMATOR FOR DISCRETE STOCHASTIC RECURRENT NEURAL NETWORK WITH INTER V AL TIME-V ARYING DELAYS
Chin Wen Liao, Chien Yu Lu, Kai Zheng, C. Ting · ICIC Express Letters · 2009
This paper deals with the problem of state estimation for discrete stochastic recurrent neural network with interval time-delays. The activation functions are assumed to be globally Lipschitz continuous. Attention is focused on the design of a state estimator which ensures the global stability of the estimation error dynamics. A delay-dependent condition with dependence on the upper and lower bounds of the delays is given in terms of a linear matrix inequality (LMI) to solve the neuron state estimation problem. When this LMI is feasible, the expression of a desired state estimator is also presented. In addition, slack matrices are introduced to reduce the conservatism of the condition. A numerical example is provided to demonstrate the applicability of the proposed approach.