Global asymptotic stability of stochastic neural networks with time-varying delays

This paper is concerned with asymptotic stability of stochastic neural networks with time-varying delay. Distinct difference from other analytical approach lies in ldquolinearizationrdquo of neural network model, by which the considered neural network model is transformed into a linear time-variant system. A sufficient condition is derived such that for all admissible disturbance, the considered neural network is asymptotic stability in the mean square. The stability criterion is formulated by means of the feasibility of a LMI, which can be easily checked in practice. Finally, a numerical example is given to illustrate the effectiveness of the developed method.