New approach to state estimator for discrete-time BAM neural networks with time-varying delay

In this paper, state estimation for discrete-time BAM neural networks with time-varying delay is discussed. Under a weaker assumption on activation functions, by constructing a novel Lyapunov-Krasovskii functional (LKF), a set of sufficient conditions are derived in terms of linear matrix inequality (LMI) for the existence of state estimator such that the error system is global exponentially stable. Based on the delay partitioning method and the reciprocally convex approach, some less conservative stability criteria along with lower computational complexity are obtained. Finally, a numerical example is given to show the effectiveness of the derived result.