State estimation for discrete-time neural networks with time-varying delays

In this paper, the problem of state estimation for discrete-time neural networks with time-varying delays is investigated. Attention is focused on the design of a state estimator to estimate the neuron states, through available output measurements. First, a linear matrix inequality (LMI) approach is developed to establish sufficient conditions for the existence of admissible state estimators. These conditions are expressed in the form of LMIs, which guarantee the estimation error to be globally exponentially stable in the presence of time-varying delays. Then, the desired estimator matrix gain is characterized in terms of the solution to these LMIs. Finally, a numerical example is given to demonstrate the effectiveness of the proposed design method.