Abstract
In this paper, we propose a new approach to investigate the incrementally exponentially asymptotically stability and contraction property of the switched recurrently connected neural networks with time-varying delays. This method of contraction theory extends the current result from ordinary differential systems to delayed differential systems. Thus, we derive sufficient conditions of incremental stability of a class of neural networks with time-varying parameters and time-delays and its asymptotical periodicity as a consequence when the time-variation is periodic. Numerical examples are presented to illustrate the power of theoretical results.
This work is jointly supported by the National Natural Sciences Foundation of China under Grant No. 61673119.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aleksander, I., Morton, H.: An Introduction to Neural Computing. Chapman and Hall, London (1990)
Angeli, D.: A lyapunov approach to incremental stability properties. IEEE Trans. Autom. Control 47(3), 410–421 (2002)
Arik, S., Tavsanoglu, V.: On the global asymptotic stability of delayed cellular neural networks. IEEE Trans. Circuits Syst. I: Fundam. Theory Appl. 47(4), 571–574 (2000)
di Bernardo, M., Liuzza, D., Russo, G.: Contraction analysis for a class of nondifferentiable systems with applications to stability and network synchronization. SIAM J. Control Optim. 52(5), 3203–3227 (2014)
Chen, T., Amari, S.I.: Exponential convergence of delayed dynamical systems. Neural Comput. 13(3), 621–635 (2001)
Chen, T., Lu, W., Chen, G.: Dynamical behaviors of a large class of general delayed neural networks. Neural Comput. 17(4), 949–968 (2005)
Chen, T., Chen, H., Liu, R.: A constructive proof and an extension of Cybenko’s approximation theorem. In: Page, C., LePage, R. (eds.) Computing Science and Statistics. Springer, New York (1992). https://doi.org/10.1007/978-1-4612-2856-1_21
Chen, T.: Global exponential stability of delayed hopfield neural networks. Neural Netw. 14(8), 977–980 (2001)
Chen, T., Chen, H.: Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. IEEE Trans. Neural Netw. 6(4), 911–917 (1995)
Chen, T., Lu, W.: Stability analysis of dynamical neural networks. In: Proceedings of the 2003 International Conference on Neural Networks and Signal Processing, vol. 1, pp. 112–116 (Dec 2003)
Chua, L.O.: Cellular neural network: applications. IEEE Trans. Circ. Syst. 35(10), 1273–1290 (1988)
Chua, L.O.: Cellular neural network: theory. IEEE Trans. Circ. Syst. 35, 1257–1272 (1988)
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4), 303–314 (1989)
Forni, F., Sepulchre, R.: A differential lyapunov framework for contraction analysis. IEEE Trans. Autom. Control 59(3), 614–628 (2014)
Gopalsamy, K., He, X.Z.: Stability in asymmetric hopfield nets with transmission delays. Physica D 76(4), 344–358 (1994)
Hecht-Nielsen, R.: Neurocomputing. Nature 359(6394) (1990)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Nat. Acad. Sci. U.S.A. 81(10), 3088–3092 (1984)
Hopfield, J.J., Tank, D.W.: Computing with neural circuits: a model. Science 233(4764), 625–633 (1986)
Lewis, D.C.: Metric properties of differential equations. Am. J. Math. 71(2), 294–312 (1949)
Liao, T.L., Wang, F.C.: Global stability for cellular neural networks with time delay. IEEE Trans. Neural Netw. 11(6), 1481–1484 (2000)
Liu, Z., Liao, L.: Existence and global exponential stability of periodic solution of cellular neural networks with time-varying delays. J. Math. Anal. Appl. 290(1), 247–262 (2004)
Lohmiller, W., Slotine, J.J.E.: On contraction analysis for non-linear systems. Automatica 34(6), 683–696 (1998)
Lu, W., di Bernardo, M.: Contraction and incremental stability of switched carathéodory systems using multiple norms. Automatica 70, 1–8 (2016)
Lu, W., Rong, L., Chen, T.: Global convergence of delayed neural network systems. Int. J. Neural Syst. 13(03), 193–204 (2003). pMID: 12884452
Russo, G., di Bernardo, M.: Contraction theory and master stability function: linking two approaches to study synchronization of complex networks. IEEE Trans. Circuits Syst. II Express Briefs 56(2), 177–181 (2009)
Russo, G., di Bernardo, M., Slotine, J.J.E.: A graphical approach to prove contraction of nonlinear circuits and systems. IEEE Trans. Circuits Syst. I Regul. Pap. 58(2), 336–348 (2011)
Wenlian, L.U., Chen, T.: On periodic dynamical systems. Chin. Ann. Math. 25(4), 455–462 (2004)
Xu, Z.B., Kwong, C.P.: Global convergence and asymptotic stability of asymmetric hopfield neural networks. J. Math. Anal. Appl. 191(3), 405–427 (1995)
Zheng, Y., Chen, T.: Global exponential stability of delayed periodic dynamical systems. Phys. Lett. A 322(5), 344–355 (2004)
Zhou, J., Liu, Z., Chen, G.: Dynamics of periodic delayed neural networks. Neural Netw. 17(1), 87–101 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Qiang, H., Lu, W. (2018). Incremental Stability of Neural Networks with Switched Parameters and Time Delays via Contraction Theory of Multiple Norms. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11302. Springer, Cham. https://doi.org/10.1007/978-3-030-04179-3_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-04179-3_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04178-6
Online ISBN: 978-3-030-04179-3
eBook Packages: Computer ScienceComputer Science (R0)