Global robust exponential stability for Hopfield neural networks with non-Lipschitz activation functions

Abstract

We consider the problem of global robust exponential stability for Hopfield neural networks with norm-bounded parameter uncertainties and inverse Holder neuron activation functions. By using the Brouwer degree properties and some analysis techniques, we investigate the existence and uniqueness of an equilibrium point. Based on the Lyapunov stability theory, we derive a global robust exponential-stability criterion in terms of a linear matrix inequality (LMI). Two numerical examples are provided to demonstrate the efficiency and validity of the proposed robust stability results.