Abstract
The stability analysis of Cohen-Grossberg neural networks with multiple delays is given. An approach combining the Lyapunov functional with the linear matrix inequality (LMI) is taken to obtain the sufficient conditions for the globally asymptotic stability of equilibrium point. By using the properties of matrix norm, a practical corollary is derived. All results are established without assuming the differentiability and monotonicity of activation functions. The simulation samples have proved the effectiveness of the conclusions.
Similar content being viewed by others
References
M. Cohen, S. Grossberg. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks[J]. IEEE Trans. on Systems, Man and Cybernetics, 1983, 13(5): 815–826.
J. Cao, J. Wang. Global asymptotic stability of a general class of recurrent neural networks with time-varying delays[J]. IEEE Trans. on Circuits and Systems-I, 2003, 50(1): 34–44.
T. Chen, L. Rong. Robust global exponential stability of Cohen-Grossberg neural networks with time delays[J]. IEEE Trans. on Neural Networks, 2004, 15(1): 203–206.
C. Ji, H. Zhang, Z. Wang. Dynamic analysis for the generalized neural networks with time delay and asymmetric structure[J]. Control and Decision, 2004, 19(12): 1416–1419.
H. Ye, A. N. Michel, K. Wang. Analysis of Cohen-Grossberg neural networks with multiple delays[J]. Physical Review E, 1995, 51: 2611–2618.
L. Wang, X. Zou. Harmless delays in Cohen-Grossberg neural networks[J]. Physica D, 2002, 170: 162–173.
T. Chen, L. Rong. Delay-independent stability analysis of Cohen-Grossberg neural networks[J]. Physics Letters A, 2003, 317: 436–449.
A. N. Michel, K. Wang, B. Hu. Qualitative Theory of Dynamical Systems-The Role of Stability Preserving Mappings[M]. 2nd Edition. New York: Marcel Dekker, 2001.
S. Boyd, L. E. Ghaoui, E. Feron. Linear Matrix Inequalities in System and Control Theory[M]. Philadelphia: SIAM, 1994.
Author information
Authors and Affiliations
Additional information
This work was supported by the National Natural Science Foundation of China(No. 60534010, 60572070), Liaoning Natural Science Foundation of China(No.20052027), and the Program for Changjiang Scholars and Innovative Research Team in University.
Ce JI was born in Shenyang, China. She received the M.S. degree and Ph.D. degree in control theory and control engineering in Northeastern University in 1997 and 2005 respectively. Now she works in Northeastern University. Her main research interests include neural networks and nonlinear system.
Huaguang ZHANG was born in Jilin, China. He received the Ph.D. degree in thermal power engineering and automation in Southeastern University in 1991. He entered Automatic Control Department, Northeastern University in 1992, as a postdoctoral fellow. Since 1994, he has been a professor and head of the Electric Automation Institute, Northeastern University. His main research interests include fuzzy control, chaos control, neural networks based control, nonlinear control, signal processing, and their industrial application.
Rights and permissions
About this article
Cite this article
Ji, C., Zhang, H., Guan, H. et al. Analysis for Cohen-Grossberg neural networks with multiple delays. J. Control Theory Appl. 4, 392–396 (2006). https://doi.org/10.1007/s11768-006-4199-z
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/s11768-006-4199-z