×

LMI conditions for stability of neural networks with distributed delays. (English) Zbl 1146.34331

This paper presents new sufficient conditions for global asymptotic stability of neural networks with discrete and distributed delays. By using appropriate Lyapunov-Krasovskii functionals, authors derive stability conditions in terms of linear matrix inequalities (LMIs). This is convenient for numerical checking the stability of the network using the powerful MATLAB LMI Toolbox. Moreover, existing conditions are mostly based on certain diagonal dominance or \(M\) matrix conditions on weight matrices of the neural networks, which only make use of absolute values of the weights and ignore their sign, and hence are somewhat conservative. The LMI-based results obtained here can get rid of this disadvantage and give less conservative stability conditions. The authors illustrate this with numerical examples.

MSC:

34K20 Stability theory of functional-differential equations
37N25 Dynamical systems in biology
92B20 Neural networks for/in biological studies, artificial life and related topics

Software:

LMI toolbox; Matlab
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Tank, D. W.; Hopfield, J. J., Neural computation by concentrating information in time, Proc Acad Sci USA, 84, 1896-1900 (1987)
[2] Marcus, C. M.; Westervelt, R. M., Stability of analog neural networks with delay, Phys Rev A, 39, 1, 347-359 (1989)
[3] Roska, T.; Wu, C. W.; Balsi, M.; Chua, L. O., Stability and dynamics of delay-type general cellular neural networks, IEEE Trans Circ Syst I, 39, 6, 487-490 (1992) · Zbl 0775.92010
[4] Chu, T., An exponential convergence estimate for analog neural networks with delay, Phys Lett A, 283, 113-118 (2001) · Zbl 0977.68071
[5] Chu, T.; Wang, Z.; Wang, L., Exponential convergence estimates for neural networks with multiple delays, IEEE Trans Circ Syst I, 49, 12, 1829-1832 (2002)
[6] Chu, T.; Zhang, Z.; Wang, Z., A decomposition approach to analysis of competitive-cooperative neural networks with delay, Phys Lett A, 312, 339-347 (2003) · Zbl 1050.82541
[7] Jiang, H.; Teng, Z., Some new results for recurrent neural networks with varying-time coefficients and delays, Phys Lett A, 338, 6, 446-460 (2005) · Zbl 1136.34337
[8] Xu, S.; Lam, J.; Ho, D. W.C.; Zou, Y., Delay-dependent exponential stability for a class of neural networks with time delays, J Comput Appl Math, 183, 1, 16-28 (2005) · Zbl 1097.34057
[9] Gopalsamy, K.; He, X., Stability in asymmetric Hopfield nets with transmission delays, Physica D, 76, 344-358 (1994) · Zbl 0815.92001
[10] Zhang, J.; Jin, X., Global stability analysis in delayed Hopfield neural network models, Neural Networks, 13, 745-753 (2000)
[11] Feng, C.; Plamondon, R., On the stability analysis of delayed neural networks systems, Neural Networks, 14, 1181-1188 (2001)
[12] Chen, Y., Global stability of neural networks with distributed delays, Neural Networks, 15, 867-871 (2002)
[13] Zhang, Q.; Wei, X.; Xu, J., Global exponential stability of Hopfield neural networks with continuously distributed delays, Phys Lett A, 315, 431-436 (2003) · Zbl 1038.92002
[14] Zhao, H., Global asymptotic stability of Hopfield neural network involving distributed delays, Neural Networks, 17, 47-53 (2004) · Zbl 1082.68100
[15] Yang, X.; Liao, X.; Evans, D. J.; Tang, Y., Existence and stability of periodic solution in impulsive Hopfield neural networks with finite distributed delays, Phys Lett A, 343, 1-3, 108-116 (2005) · Zbl 1184.34080
[16] Song, Q.; Zhao, Z., Global dissipativity of neural networks with both variable and unbounded delays, Chaos, Solitons & Fractals, 25, 393-401 (2005) · Zbl 1072.92005
[17] Wang, Z.; Liu, Y.; Liu, X., On global asymptotic stability of neural networks with discrete and distributed delays, Phys Lett A, 345, 299-308 (2005) · Zbl 1345.92017
[18] Liao, X.; Chen, G.; Sanchez, E., LMI-Based approach for asymptotically stability analysis of delayed neural networks, IEEE Trans Circ Syst I, 49, 7, 1033-1039 (2002) · Zbl 1368.93598
[19] Zhang, Q.; Wei, X.; Xu, J., Global asymptotic stability of Hopfield neural networks with transmission delays, Phys Lett A, 318, 399-405 (2003) · Zbl 1030.92003
[20] Singh, V., Simplified LMI condition for global asymptotic stability of delayed neural networks, Chaos, Solitons & Fractals, 29, 470-473 (2006) · Zbl 1188.34099
[21] Yang H, Chu T, Zhang C. Exponential stability of neural networks with variable delays via LMI approach. Chaos, Solitons & Fractals, in press, doi:10.1016/j.chaos.2005.08.134; Yang H, Chu T, Zhang C. Exponential stability of neural networks with variable delays via LMI approach. Chaos, Solitons & Fractals, in press, doi:10.1016/j.chaos.2005.08.134
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.