Stability and L2-gain analysis for switched neutral recurrent neural networks

The perturbed switched neutral recurrent neural networks is investigated. Based on average dwell time approach and linear matrix inequality (LMI) technique, sufficient conditions are obtained to guarantee the exponential stability of switched recurrent neural networks without perturbation and the L2-gain stability of perturbed switched recurrent neural networks under the identified switching signal. An estimation of state decay can be obtained by corresponding LMIs. Augmented Lyapunov function is used to establish less conservation results. The examples illustrate the effectiveness of the proposed results.