A new stability criterion of neutral neural networks with time-varying delays

Abstract

In this paper, we study the global stability problem for neutral neural networks with time delays. Firstly, we extend the existing neutral networks to a much general class of such networks. Then, by constructing suitable Lyapunov-Krasovskii-type functionals and using linear matrix inequality (LMI) optimization techniques, we obtain new sufficient conditions for global asymptotic stability of the neural networks. The obtained results are related to some positive real-value parameters rather than positive symmetric matrices which are much complicated computationally. Finally, we demonstrate the results' validity via a numerical example and its simulations.