Premium
Novel stability criteria of Cohen–Grossberg neural networks with time‐varying delays
Author(s) -
Zheng ChengDe,
Shan QiHe,
Wang Zhanshan
Publication year - 2012
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/cta.719
Subject(s) - uniqueness , homeomorphism (graph theory) , monotonic function , artificial neural network , mathematics , nonlinear system , exponential stability , class (philosophy) , stability (learning theory) , linear matrix inequality , control theory (sociology) , matrix (chemical analysis) , measure (data warehouse) , computer science , mathematical optimization , mathematical analysis , discrete mathematics , artificial intelligence , physics , materials science , control (management) , quantum mechanics , machine learning , database , composite material
SUMMARY In this paper, a class of Cohen–Grossberg neural networks with time‐varying delays is investigated. Based on several new Lyapunov–Krasovskii functionals, by employing the homeomorphism mapping principle, the Halanay inequality, a nonlinear measure approach and linear matrix inequality techniques, several delay‐independent sufficient criteria are obtained for the existence, uniqueness and globally exponential stability of considered neural networks. Without assuming the boundedness and monotonicity of activation functions, the obtained conditions generalize some previous results in the literature. Two examples are also given to show the less conservativeness of the obtained conditions. Copyright © 2010 John Wiley & Sons, Ltd.