Improved Delay-Dependent Globally Asymptotic Stability Criteria for Neural Networks With a Constant Delay

• Published in: IEEE transactions on circuits and systems. II, Express briefs Vol. 55; no. 10; pp. 1071 - 1075
• Main Author: Shao, Hanyong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-10-2008; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Asymptotic stability; Asymptotically stable; Delay lines; delay-dependent; Linear matrix inequalities; linear matrix inequality (LMI); Lyapunov functional; neural network; Neural networks; Neutrons; Pattern recognition; Signal processing; Stability analysis; Stability criteria; Symmetric matrices
• ISSN: 1549-7747; 1558-3791
• DOI: 10.1109/TCSII.2008.2001981

This paper considers the stability analysis problem for neural networks with a constant delay. Based on the dividing of the delay, a new Lyapunov functional is constructed, and a novel delay-dependent stability criterion is derived to guarantee the globally asymptotic stability of the neural network. It is established theoretically that the criterion is less conservative than recently reported ones. Expressed in terms of linear matrix inequalities (LMIs), the stability condition can be checked using the numerically efficient Matlab LMI control toolbox. An example is provided to demonstrate the effectiveness and the reduced conservatism of the analysis result.