New stability results for delayed neural networks

This paper is concerned with the stability for delayed neural networks. By more fully making use of the information of the activation function, a new Lyapunov-Krasovskii functional (LKF) is constructed. Then a new integral inequality is developed, and more information of the activation function is taken into account when the derivative of the LKF is estimated. By Lyapunov stability theory, a new stability result is obtained. Finally, three examples are given to illustrate the stability result is less conservative than some recently reported ones.