New approach to stability criteria for generalized neural networks with interval time-varying delays

• The stability problem is considered for generalized neural networks with time delay.
• Improved stability criteria are derived by using a modified Lyapunov functional.
• Numerical examples are given to show the effectiveness of the proposed method.

This paper is concerned with the problem of delay-dependent stability of delayed generalized continuous neural networks, which include two classes of fundamental neural networks, i.e., static neural networks and local field neural networks, as their special cases. It is assumed that the state delay belongs to a given interval, which means that the lower bound of delay is not restricted to be zero. An improved integral inequality lemma is proposed to handle the cross-product terms occurred in derivative of constructed Lyapunov–Krasovskii functional. By using the new lemma and delay partitioning method, some less conservative stability criteria are obtained in terms of LMIs. Numerical examples are finally given to illustrate the effectiveness of the proposed method over the existing ones.