Abstract
This paper deals with the problem on Lagrange stability of Cohen-Grossberg neural networks (CGNNs) with both mixed time delays and general activation functions. By virtue of Lyapunov functional and Halanay delay differential inequality, several criteria in linear matrix inequality form for Lagrange stability of CGNNs are obtained. Meanwhile, the limitation on the activation functions being bounded, monotonous and differentiable is released and detailed estimation of the globally exponentially attractive sets are also given out. Finally, concluding remark is given.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cohen, M.A., Grossberg, S.: Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. Syst. Man Cybern. 13, 815–826 (1983)
Li, J.X., Yan, J.R., Jia, X.C.: Dynamical analysis of Cohen-Grossberg neural networks with time-delays and impulses. Comput. Math. Appl. 58, 1142–1151 (2009)
Huang, C.X., Cao, J.D.: Covergence dynamics of stochastic Cohen-Grossberg neural networks with unbounded distributed delays. IEEE Trans. Neural Netw. 22(4), 561–572 (2011)
Wang, Z.S., Zhang, H.G.: Global asymptotic stability of reaction-diffusion Cohen-Grossberg neural networks with continuously distributed delays. IEEE Trans. Neural Netw. 21(1), 39–49 (2010)
Wang, Z.S., Zhang, H.G., Li, P.: An LMI approach to stability analysis of reaction-diffusion Cohen-Grossberg neural networks concerning dirichlet boundary conditions and distributed delays. IEEE Trans. Syst. Man Cyber. 40(6), 1596–1606 (2010)
Li, X.D., Fu, X.L., Balasubramaniamc, P., et al.: Existence, uniqueness and stability analysis of recurrent neural networks with time delay in the leakage term under impulsive perturbations. Nonlinear Anal. RWA 11, 4092–4108 (2010)
Song, Q.K.: Exponential stability of recurrent neural networks with both time-varying delays and general activation functions via LMI approach. Neurocomputing 71, 2823–2830 (2008)
Yu, P., Liao, X.X., Xie, S.L., Fu, Y.L.: A constructive proof on the existence of globally exponentially attractive set and positive invariant set of general Lorenz family. Commun. Nonlinear Sci. Numer. Simulat. 14(7), 2886–2896 (2009)
Liao, X.X., Luo, Q., Zeng, Z.G., Guo, Y.X.: Global exponential stability in Lagrange sense for recurrent neural networks with time delays. Nonlinear Anal. RWA 9, 1535–1557 (2008)
Wang, X.H., Jiang, M.H., Fang, S.L.: Stability analysis in Lagrange sense for a non-autonomous Cohen-Grossberg neural network with mixed delays. Nonlinear Anal. TMA 70, 4294–4306 (2009)
Luo, Q., Zeng, Z.G., Liao, X.X.: Global exponential stability in Lagrange sense for neutral type recurrent neural networks. Neurocomputing 74, 638–645 (2011)
Liao, X.X., Luo, Q., Zeng, Z.G.: Positive invariant and global exponential attractive sets of neural networks with time-varying delays. Neurocomputing 71, 513–518 (2008)
Gu, K., Kharitonov, V., Chen, J.: Stability of time-delay systems. Birkhauser, Boston (2003)
Boyd, B., Ghoui, L., Feron, E., Balakrishnan, V.: Linear Matrix Inequalities in System and Control Theory. SIAM, Philadelphia (1994)
Halanay, A.: Differential Equations: Stability, Oscillations, Time Lags. Academic Press, New York (1966)
Liao, X., Fu, Y., Xie, S.: Globally exponential stability of Hopfied networks. Adv. Syst. Sci. Appl. 5, 533–545 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, X., Qi, H. (2012). LMI-Based Lagrange Stability of CGNNs with General Activation Functions and Mixed Delays. In: Tan, Y., Shi, Y., Ji, Z. (eds) Advances in Swarm Intelligence. ICSI 2012. Lecture Notes in Computer Science, vol 7331. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30976-2_52
Download citation
DOI: https://doi.org/10.1007/978-3-642-30976-2_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-30975-5
Online ISBN: 978-3-642-30976-2
eBook Packages: Computer ScienceComputer Science (R0)