Abstract
This paper considers the problem of global stability of neural networks with delays. By combining Lie algebra and the Lyapunov function with the integral inequality technique, we analyze the globally asymptotic stability of a class of recurrent neural networks with delays and give an estimate of the exponential stability. A few new sufficient conditions and criteria are proposed to ensure globally asymptotic stability of the equilibrium point of the neural networks. A few simulation examples are presented to demonstrate the effectiveness of the results and to improve feasibility.
Similar content being viewed by others
References
Geman S, Bienenstock E, Doursat R (1992) Neural networks and the bias/variance dilemma. Neural Comput 4:1–58
Grossberg S (1988) Nonlinear neural networks: principles, mechanisms, and architectures. Neural Netw 1:17–61
Kerlirzin P, Vallet F (1993) Robustness in multilayer perceptrons. Neural Comput 5(3):473–482
Lu W, Rong L, Chen T (2003) Global convergence of delayed dynamical systems [J]. Int J Neural Syst 13:1–12
Li X, Huang L, Zhu H (2003) Global stability of cellular neural networks with constant and variable delays. Nonlinear Anal 53:319–333
Ren F, Cao J (2006) LMI-based criteria for stability of high-order neural networks with time-varying delay. Nonlinear Anal Real World Appl 7:967–979
Abarbanel HDI (1996) Analysis of observed chaotic data. Springer, New York
Arik S, Tavsanoglu V (2000) On the global asymptotic stability of delayed cellular neural networks. IEEE Trans Circuits Syst I 47:571–574
Singh V (2007) Improved global robust stability criterion for delayed neural networks. Chaos Solitons Fractals 31:224–229
Arik S (2002) An improved global stability result for delayed cellular neural networks. IEEE Trans Circuits Syst-I 49:1211–1214
Arik S (2002) An analysis of global asymptotic stability of delayed cellular neural networks. IEEE Trans Neural Netw 13:1239–1242
Arik S (2003) Global asymptotic stability of a larger class of neural networks with constant time delay. Phys Lett A 311:504–511
Cao J (2001) Global stability conditions for delayed CNNs. IEEE Trans Circuits Syst I 48:1330–1333
Huang H, Teng Z (2005) A new criterion on global exponential stability for cellular neural networks with multiple time-varying delays. Phys Lett A 338:461–471
He Y, Wang Q, Wu M, Lin C (2006) Delay-dependent state estimation for delayed neural networks. IEEE Trans Neural Netw 17:1077–1081
Arik S (2000) Global asymptotic stability of a class of dynamical neural networks. IEEE Trans Circuits Syst I 47:568–571
Meyer-Bäse A, Sergei S, Pilyugin SS (2003) Global asymptotic stability of a class of dynamical neural networks. Int J Neural Syst 13(1):47–53
Liao X, Chen G, Sanchez EN (2002) LMI-based approach for asymptotic stability analysis of delayed neural networks. IEEE Trans Circuits Syst I 49:1033–1039
Cao J, Wang J (2003) Global asymptotic stability of a general class of recurrent neural networks with time-varying delays. IEEE Trans Circuits Syst I 50:34–44
Sagle A, Walde R (1973) Introduction to Lie groups and Lie algebras. Academic Press, New York
Chu T, Zhang C, Zhang Z (2003) Necessary and sufficient condition for absolute stability of normal neural networks. Neural Netw 16:1223–1227
Matsuoka K (1992) Stability conditions for nonlinear continuous neural networks with asymmetric connection weights. Neural Netw 5:495–500
Chu T, Zhang C (2007) New necessary and sufficient conditions for absolute stability of neural networks. Neural Netw 20:94–101
Xu S, Lam J (2006) A new approach to exponential stability analysis of neural networks with time-varying delays. Neural Netw 19:76–83
Acknowledgments
This work was supported by the National Natural Science Foundation of China (50975059/61005080), the Doctoral Foundation of China (20100480994), the Doctoral Foundation of Heilongjiang Province, and the“111” Project (B07018).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Song, X., Gao, H., Ding, L. et al. The globally asymptotic stability analysis for a class of recurrent neural networks with delays. Neural Comput & Applic 22, 587–595 (2013). https://doi.org/10.1007/s00521-012-0888-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-0888-3