Further analysis of global μ-stability of complex-valued neural networks with unbounded time-varying delays.
Journal:
Neural networks : the official journal of the International Neural Network Society
Published Date:
Mar 23, 2015
Abstract
In this paper, we consider the problem of global μ-stability for complex-valued neural networks (CVNNs) with unbounded time-varying delays and it has been widely investigated. Under mild conditions, some new sufficient conditions for global μ-stability of considered CVNNs are derived. Moreover, some new sufficient conditions are obtained to ensure the global μ-stability of CVNNs in the form of complex-valued LMIs as well as real-valued LMIs by using an appropriate Lyapunov-Krasovskii functional and linear matrix inequalities (LMIs). Both of complex-valued LMIs as well as real-valued LMIs are easily solved by using standard numerical algorithms. Finally, two numerical examples are presented to demonstrate the effectiveness and usefulness of our theoretical results.