Delay-dependent filtering of static neural networks with time-varying delay

This paper is concerned with the generalized H₂ filtering problem of static neural networks with time-varying delay. A delay-dependent design criterion with less conservatism is derived by employing the reciprocally convex combination technique. It is shown that the gain matrix and the optimal generalized H₂ performance index can be simultaneously obtained by solving a convex optimization problem subject to some linear matrix inequalities. An example is finally exploited to show the advantage of the developed condition over some existing results.