On robust stability of BAM neural networks with constant delays

The problems of determining the robust stability of bidirectional associative memory neural networks with delays are investigated in this paper. An approach combining the Lyapunov-Krasovskii stability theorem with the linear matrix inequality (LMI) technique is taken to study the problems, which provide bounds on the interconnection matrix and the activation functions. Some criteria for the robust stability, which give information on the delay, independence property, are derived. The results obtained in this paper provide one more set of easily verified guidelines for determining the robust stability of delayed BAM (DBAM) neural networks, which are less conservative and less restrictive than the ones reported recently in the literature. Some typical examples are presented to show the effectiveness of results.