Stabilization of Switched Dynamic Neural Networks with Discrete Delays

With the rapid development of intelligent control, switched systems have attracted great attention. This paper introduces the idea of the switched systems into the field of dynamic neural networks. First, a mathematical model of the switched dynamic neural networks is established , in which a set of dynamic neural networks are used as the subsystems. Secondly, a scalar function is constructed to develop a new methodology for stabilization of switched dynamic neural networks. This design guarantees the switched dynamic neural networks to be globally asymptotically stable and inverse optimality with respect to a meaningful cost functional. Finally, a numerical example is given to illustrate the results.