Stability analysis on delayed neural networks based on an improved delay-partitioning approach

In this paper, the asymptotical stability is investigated for a class of delayed neural networks (DNNs), in which one improved delay-partitioning idea is employed. By choosing an augmented Lyapunov–Krasovskii functional and utilizing general convex combination method, two novel conditions are obtained in terms of linear matrix inequalities (LMIs) and the conservatism can be greatly reduced by thinning the partitioning of delay intervals. Moreover, the LMI-based criteria heavily depend on both the upper and lower bounds on time-delay and its derivative, which is different from the existent ones. Though the results are not presented via standard LMIs, they still can be easily checked by resorting to Matlab LMI Toolbox. Finally, three numerical examples are given to demonstrate that our results can be less conservative than the present ones.