Design of An Arcak-Type Generalized Filter for Delayed Static Neural Networks
Additional Document Info
2014, Springer Science+Business Media New York. In this paper, an Arcak-type generalized (Formula presented.) filter is designed for a class of static neural networks with time-varying delay. By employing some inequalities and constructing a suitable Lyapunov functional, a delay-dependent condition is derived by means of linear matrix inequalities such that the filtering error system is globally asymptotically stable and a prescribed generalized (Formula presented.) performance is achieved. It is shown that the design of such a desired filter for a delayed static neural network is successfully transformed into solving a convex optimization problem subject to some linear matrix inequalities. It is thus facilitated readily by some standard algorithms. A numerical example is finally provided to show the effectiveness of the developed approach. A comparison on the generalized (Formula presented.) performance for different gain parameters of the activation function is also given.