Delay-dependent stability analysis for recurrent neural networks with time-varying delay

Abstract

A global stability analysis of a particular class of recurrent neural networks with time-varying delay is performed. Both Lipschitz continuous and monotone non-decreasing activation functions are considered. Globally asymptotically delay-dependent stability criteria are derived in the form of linear matrix inequalities through the use of Leibniz–Newton formula and relaxation matrices. Finally, two numerical examples are given to illustrate the effectiveness of the given criterion.