A New Delay-Dependent Approach to Robust Stability for Uncertain Hybrid Bidirectional Associative Memory Neural Networks with Time-Varying Delays

This paper considers the problem of global robust stability analysis for a class of bidirectional associative memory time-varying delayed neural networks 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 some relaxation matrices which can be chosen properly to lead to a less conservative result. Numerical examples are given to illustrate the significant improvement on the conservativeness of the delay bound over some reported results in the literature