State estimation for neural networks with mixed interval time-varying delays

In this paper, the state estimation problem is investigated for neural networks with discrete interval time-varying delays and distributed time-varying delays as well as general activation functions. By constructing appropriate Lyapunov–Krasovskii functional and employing Newton–Leibniz formulation and linear matrix inequality (LMI) technique, a delay-interval-dependent condition is developed to estimate the neuron state with some available output measurements such that the error-state system is global asymptotically stable. Two examples are given to show the effectiveness and decreased conservatism of the proposed criterion in comparison with some existing results. It is noteworthy that the traditional assumptions on the differentiability of the time-varying delays and the boundedness of their derivative are removed.