Error passivation to filtering for a general class of switched recurrent neural networks with noise disturbance

In this paper, error passivation to filtering is considered for a general class of switched recurrent neural networks with noise disturbance. Based on Lyapunov-Krasovskii stability theory, and linear matrix inequality, a new sufficient criterion is established such that the filtering error system is globally asymptotically stable and passive from the noise disturbance to the output error, which can be easily facilitated by using some standard numerical packages.