New delay-dependent asymptotic stability conditions concerning BAM neural networks of neutral type

This paper deals with the problem of the delay-dependent asymptotic stability analysis for bidirectional associative memory (BAM) neural networks of neutral type. Two cases of time delays in which whether the neutral delays are equal to the state delays or not are involved. The activation functions are supposed to be bounded and globally Lipschitz continuous, which are more general than the usual bounded monotonically increasing ones such as the activation functions of the sigmoidal type. By introducing some new integral inequalities and resorting to the Lyapunov–Krasovskii functional approach, one novel delay-dependent condition is established checking the asymptotic stability for a given BAM neural system. All the conditions are presented in terms of linear matrix inequalities (LMIs), which can be easily checked by using recently developed algorithms in solving LMIs. Two numerical examples are provided to show the reduced conservatism of the main results.