Abstract
The existence, uniqueness and global asymptotic stability for the equilibrium of Hopfield-type neural networks with diffusion effects are studied. When the activation functions are monotonously nondecreasing, differentiable, and the interconnected matrix is related to the Lyapunov diagonal stable matrix, the sufficient conditions guaranteeing the existence of the equilibrium of the system are obtained by applying the topological degree theory. By means of constructing the suitable average Lyapunov functions, the global asymptotic stability of the equilibrium of the system is also investigated. It is shown that the equilibrium (if it exists) is globally asymptotically stable and this implies that the equilibrium of the system is unique.
Similar content being viewed by others
References
Hopfield J J. Neural networks and physical systems with emergent collective computional abilities[J]. Pro Natl Acad Sci, 1982, 79(2):2554–2558.
Hopfield J J. Neurons with graded response have collective computional properties like those of two-state neurons[J]. Pro Natl Acda Sci, 1984, 81(10):3088–3092.
Liao Xiaoxin. The stability of Hopfield neural networks[J]. Science in China, Ser A, 1993, 23(10):1032–1035 (in Chinese)
Liang Xuebin, Wu Lide. The global expoential stability and applications of Hopfield-type neural networks[J]. Science in China, Ser A, 1995, 25(5):523–532 (in Chinese).
Forti M, Tesi A. New conditions for global stability of neural networks with application to linear and quadratic programming problems[J]. IEEE Trans Circuits Sys, 1995, 42(7):354–366.
Liang Xuebin, Wu Lide. Comment on “New conditions for global stability of neural networks with application to linear and quadratic programming problems”[J]. IEEE Trans Circuits Sys, 1997, 44(1):1099–1101.
Liang X B, Wang J. Absolute exponential stability of neural networks with a general class of activation functions[J]. IEEE Trans Circuits Sys, 2000, 47(8):1258–1263.
He Qiming, Kang Lishan. Existence and stability of global solution for generalized Hopfield neural networks[J]. Neural, Parallel Scientific Computations, 1994, 2(2):165–176.
Carpenter G A. A geometric approach to singular perturbation to never impulse equations[J]. J Diff Equs, 1977, 23(3):355–367.
Evans J W. Nerve axon egus II: stability at rest[J]. Indiana Univ Math J, 1972, 22(1):75–90.
Liao Xiaoxin, Yang Shuzi, Cheng Shijie, et al. The stability of the generalized neural networks with reaction-diffusion[J]. Science in China, Ser E, 2002, 32(1):88–94 (in Chinese).
Cao J, Wang J. Absolute exponential stability of recurrent neural networks with Lipschitzcontinuous activation and time delays[J]. Nueral Networks, 2004, 17(3):379–390.
Guo Daiun, Sun Jingxian, Lin Zhaoli. The functional method of nonlinear ordinary differential equations[M]. Jinan: Shandong Science and Technology Press, 1995 (in Chinese).
Hu Shigeng. Nonlinear analysis and method[M]. Wuhan: Huazhong University of Science and Tecology Press, 1996 (in Chinese).
Guo Dajun. Nonlinear functional analysis[M]. Jinan: Shandong Science and Technology Press, 2002 (in Chinese).
Fiedler M. Special matrices and their applications in numerical mathematics[M]. Dordrecht: Martinus Nijhoff, 1986.
Horn R A, Johnson C R. Topics in matrix analysis[M]. Cambridge: Cambridge University Press, 1991.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by LI Ji-bin
Project supported by the National Natural Science Foundation of China (No.10571078) and the Natural Science Foundation of Gansu Province of China (No.3ZX062-B25-012)
Rights and permissions
About this article
Cite this article
Yan, Xp., Li, Wt. Global asymptotic stability for Hopfield-type neural networks with diffusion effects. Appl Math Mech 28, 361–368 (2007). https://doi.org/10.1007/s10483-007-0309-x
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/s10483-007-0309-x