Robust filtering of recurrent neural networks with time-varying delay

This paper studies the generalized H₂ filter design problem of recurrent neural networks with time-varying delay. A delay-dependent condition is derived to ensure the existence of a desired filter for the delayed neural networks. It is shown that the design of such a filter and the optimal performance index can be accomplished by solving two coupled linear matrix inequalities. A numerical example is provided to demonstrate that the developed result can be efficiently applied to delayed neural networks with chaotic dynamic behaviors.