Abstract
A universal stability analysis method on the basis of linear matrix inequality is proposed to solve the stability problem of recurrent neural networks with different kinds of multiple delays. Firstly, a universal neural networks model is analyzed to present a general framework for the stability study, in which a sufficient condition is derived. Secondly, by considering several special case of the universal model, a series of stability criteria are established, which have the same or similar structure and expression. All the obtained stability criteria present a general mode to study the stability of delayed dynamical systems.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Zheng, C.D., Zhang, H.G., Wang, Z.S.: An Augmented LKF Approach Involving Derivative Information of Both State and Delay. IEEE Trans. Neural Networks 21, 1100–1109 (2010)
Zhang, H.G., Wang, Z.S., Liu, D.R.: Global Asymptotic Stability of Recurrent Neural Networks with Multiple Time Varying Delays. IEEE Trans. Neural Networks 19, 855–873 (2008)
Zhang, H.G., Liu, Z.W., Huang, G.B., Wang, Z.S.: Novel Weighting-Delay-Based Stability Criteria for Recurrent Neural Networks with Time–Varying Delay. IEEE Trans. Neural Networks 21, 91–106 (2010)
Song, Q.K., Wang, Z.D.: Neural Networks with Discrete and Distributed Time Varying Delays: a General Stability Analysis. Chaos Solitons and Fractals 37, 1538–1547 (2008)
Yu, J., Zhang, K., Fei, S.M., Li, T.: Simplified Exponential Stability Analysis for Recurrent Neural Networks with Discrete and Distributed Time Varying Delays. Applied Mathematics and Computation 205, 465–474 (2008)
Cao, J.D., Yuan, K., Li, H.X.: Global Asymptotic Stability of Recurrent Neural Networks with Multiple Discrete Delays and Distributed Delays. IEEE Trans. Neural Networks 17, 1646–1651 (2006)
Gopalsamy, K., He, X.Z.: Delay-Independent Stability in Bidirectional Asociative Neural Networks. IEEE Trans. Neural Networks 5, 998–1002 (1994)
Liang, J.L., Cao, J.D.: Global Output Convergence of Recurrent Neural Networks with Distributed Delays. Nonlinear Analysis: Real World Applications 8, 187–197 (2007)
Wang, Z.S., Zhang, H.G.: Global Asymptotic Stability of Reaction-Diffusion Cohen-Grossberg Neural Networks with Continuously Distributed Delays. IEEE Trans. Neural Networks 21, 39–49 (2010)
Chen, T.P.: Universal Approach to Study Delayed Dynamical Systems. In: Wang, L., Chen, K., S. Ong, Y. (eds.) ICNC 2005. LNCS, vol. 3610, pp. 245–253. Springer, Heidelberg (2005)
Chen, T.P., Lu, W.L.: Stability Analysis of Dynamical Neural Networks. In: IEEE Int. Conf. Neural Networks and Signal Processing, Nanjing, China, December 14-17 (2003)
Chen, T.P., Lu, W.L., Chen, G.R.: Dynamical Behaviors of a Large Class of General Delayed Neural Networks. Neural Computation 17, 949–968 (2005)
Chen, T.P.: Universal Approach to Study Delayed Dynamical Systems. Studies in Computational Intelligence 35, 85–110 (2007)
Chen, T.P., Lu, W.L.: Global Asymptotical Stability of Cohen-Grossberg Neural Networks with Time-Varying and Distributed Delays. In: Wang, J., Yi, Z., Żurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3971, pp. 192–197. Springer, Heidelberg (2006)
Lu, W.L., Chen, T.P.: On Periodic Dynamical Systems. Chinese Annals of Mathematics Series B 25, 455–462 (2004)
Lu, W.L., Chen, T.P.: Global Exponential Stability of Almost Periodic Solution for a Large Class of Delayed Dynamical Systems. Science in China, Series A–Mathematics 48, 1015–1026 (2005)
Lu, W.L., Chen, T.P.: Almost Periodic Dynamics of a Class of Delayed Neural Networks with Discontinuous Activations. Neural Computation 20, 1065–1090 (2008)
Liao, X.F., Li, C.D.: Global Attractivity of Cohen-Grossberg Model with Finite and Infinite delays. J. Mathematical Analysis and Applications 315, 244–262 (2006)
Liu, P.C., Yi, F.Q., Guo, Q., Yang, J., Wu, W.: Analysis on Global Exponential Robust Stability of Reaction–Diffusion Neural Networks with S-Type Distributed Delays. Physica D 237, 475–485 (2008)
Wang, L.S., Zhang, R.J., Wang, Y.F.: Global Exponential Stability of Reaction–Diffusion Cellular Neural Networks with S-Type Distributed Time Delays. Nonlinear Analysis: Real World Applications 10, 1101–1113 (2009)
Wang, L.S., Xu, D.Y.: Global Asymptotic Stability of Bidirectional Associative Memory Neural Networks with S-Type Distributed Delays. Internat. J. Syst. Sci. 33, 869–877 (2002)
Wang, Z.S., Zhang, H.G., Liu, D.R., Feng, J.: LMI Based Global Asymptotic Stability Criterion for Recurrent Neural Networks with Infinite Distributed Delays. In: Yu, W., He, H., Zhang, N. (eds.) ISNN 2009. LNCS, vol. 5551, pp. 463–471. Springer, Heidelberg (2009)
Wang, Z.S., Zhang, H.G., Feng, J.: Stability Analysis of Recurrent Neural Networks with Distributed Delays Satisfying Lebesgue-Stieljies Measures. In: Zhang, L., Lu, B.-L., Kwok, J. (eds.) ISNN 2010. LNCS, vol. 6063, pp. 504–511. Springer, Heidelberg (2010)
Karimi, H.R., Gao, H.J.: New Delay-Dependent Exponential Synchronization for Uncertain Neural Networks with Mixed Time Delays. IEEE Trans. Systems, Man, and Cybernetics, B 40, 173–185 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, Z., Zhang, E., Yun, K., Zhang, H. (2011). Universal Analysis Method for Stability of Recurrent Neural Networks with Different Multiple Delays. In: Liu, D., Zhang, H., Polycarpou, M., Alippi, C., He, H. (eds) Advances in Neural Networks – ISNN 2011. ISNN 2011. Lecture Notes in Computer Science, vol 6675. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21105-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-21105-8_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21104-1
Online ISBN: 978-3-642-21105-8
eBook Packages: Computer ScienceComputer Science (R0)