On Global Robust Stability of a Class of Delayed Neural Networks with Discontinuous Activation Functions and Norm-Bounded Uncertainty

Abstract

This paper considers the problem of global robust stability of a class of uncertain delayed neural networks with discontinuous activation functions. The uncertainties are assumed to be norm-bounded. In the form of linear matrix inequality (LMI), a new sufficient condition is obtained for the robust stability of this class of neural networks based on Lyapunov–Krasovskii stability theory as well as Filippov theory. Our conditions are independent of the delay and easy to check. A numerical example is given to show the effectiveness and superiority of our results.