Further results on state estimation of neural networks with multiple time delays

Abstract

This paper considers the problem of state estimation for neural networks with multiple time delays. By constructing a suitable Lyapunov–Krasovskii functional and some effective integral inequalities, the activation function dividing approach is modified with the introductory of a tuning parameter. Some conditions are formulated in terms of linear matrix inequalities, which can be checked efficiently by using some standard numerical packages. Numerical examples are given to illustrate the effectiveness of the proposed method.