Robust state estimation for neutral-type neural networks with mixed time delays

In this paper, the state estimation problem is dealt with a class of neutraltype Markovian neural networks with mixed time delays. The network systems have a finite number of modes, and the modes may jump from one state to another according to a Markov chain. We are devoted to design a state estimator to estimate the neuron states, through available output measurements, such that the dynamics of the estimation error is globally asymptotically stable in the mean square. From the Lyapunov Krasovskii functional and linear matrix inequality (LMI) approach, we establish sufficient conditions to guarantee the existence of the state estimators. Furthermore, it is shown that the traditional stability analysis issue for delayed neural networks with Markovian chains can be included as a special case of our main results. A simulation shows the usefulness of the derived LMI-based stability conditions.