Abstract
Several new conditions for exponential convergence of DNN were proposed in this paper. These conditions guarantee the existence and uniqueness of equilibrium of DNN with certain different activation functions. To demonstrate the differences and features of the new criteria, some remarks are presented.
This work is supported by the Natural Science Foundation of China under grant 10271035 and by the Foundation of HIT under grant 2002.53.
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
Arik, S.: An improved global stability result for delayed cellular neural networks. IEEE Trans Circuits Syst. I 49, 1211–1214 (2002)
Forti, M.: On global asymptotic stability of a class of nonlinear systems arising in neural network theory. J. Differential Equations 113, 246–264 (1994)
Joy, M.: On the global convergence of a class of functional differential equatoins with applications in neural network theory. J. Math. Anal. Appl. 232, 61–81 (1999)
Liao, X., Wang, J.: Algebraic criteria for global exponential stability of cellular neural networks with multiple time delays. IEEE Trans Circuits Syst. I 50, 268–275 (2003)
Liao, T., Wang, F.: Global stability for cellular neural networks with time delay. IEEE Trans Neural Networks 11, 1481–1484 (2000)
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall, New Jersey (1999)
Rajapakse, J.C., Wang, L.P. (eds.): Neural Information Processing: Research and Development. Springer, Berlin (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xue, X. (2005). Exponential Convergence of Delayed Neural Networks. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3610. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539087_59
Download citation
DOI: https://doi.org/10.1007/11539087_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28323-2
Online ISBN: 978-3-540-31853-8
eBook Packages: Computer ScienceComputer Science (R0)