Abstract:This paper performs a global robust stability analysis of a particular class of hybrid bidirectional associative memory time-varying delayed neural network with norm-bounded time-
varying parameter uncertainties. The activation functions are assumed to be globally Lipschitz continuous. Globally delay-dependent robust stability criteria are derived in the form of linear matrix inequalities by introducing relaxation matrices which, when chosen properly, produce a less conservative result. Two numerical examples are given to illustrate the significant improvement obtained in the conservativeness of
the delay bound.