New results of H_∞ filtering for neural network with time-varying delay

A more effective Lyapunov functional has been constructed to investigate the Hoo filtering problems for a class of neural networks with time-varying delay. By combining with some inequality technic or free-weighting matrix approach, the delay-dependent conditions have been proposed such that the filtering error system is globally asymptotically stable with guaranteed ffoo performance. The time delay is divided into several subintervals; more information about time delay is utilized and less conservative results have been obtained. All results are expressed by the form of linear matrix inequalities, and the filter gain matrix can be determined easily by optimal algorithm. Examples and simulations have been provided to illustrate the less conservatism and effectiveness of the designed filter.