New Stability Criteria for Neural Networks with Time-varying Delay

The problem of delay-dependent asymptotic stability criteria for neural networks with time-varying delays is investigated. An improved delay dependent stability criteria are obtained in terms of linear matrix inequalities (LMIs) to ensure a large upper bound for time-delay. A new class of Lyapunov functional is constructed and the known bounds of the delay interval is split in two subintervals to derive some novel delay dependent stability criteria. Finally, three numerical examples are given that our results are less conservative than some existing ones.