Abstract
By using the positive linearity of the activation functions of neurons in recurrent neural networks, and by adopting the method of decomposing the state space to sub-regions, the mathematical equations of delayed recurrent neural networks are rewritten to be the form of linear differential difference equations in the neighbourhood of each equilibrium, which is an interior point of some sub-region. Based on this linear form and by using the stability theory of linear differential difference equations and the tool of M-matrix, delay-dependent and delay-independent stability algebraic criteria are obtained. All results obtained in this paper need only to compute the eigenvalues of some matrices or to examine the matrices to be M-matrix or to verify some inequalities to be holden.
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
Chua, L., Yang, L.: Cellular Neural Networks: Theory. IEEE Trans. Circuits and Systems 35, 1257–1272 (1988)
Slavova, A.: Stability Analysis of Cellular Neural Networks with Nonlinear Dynamics. Nonlinear Analysis: Real World Applications 2, 93–103 (2001)
Liao, W., Liao, X.: Stability Analysis of Cellular Neural Networks. Control Theory and Applications 20, 89–92 (2003)
Civalleri, P., Gill, M., Pandolfli, L.: On Stability of Cellular Neural Networks with Delay. IEEE Trans. Circuits and Systems 40, 157–165 (1993)
Cao, J., Zhou, D.: Stability Analysis of Delayed Celluar Neural Networks. Neural Networks 11, 1601–1605 (1998)
Takahashi, N.: A New Sufficient Condition for Complete Stability of Cellular Neural Networks with Delay. IEEE Trans. Circuits and Systems-1: Fundamental Theory and Applications 47, 793–799 (2000)
Liao, T., Wang, F.: Global Stability for Cellular Neural Networks with Time Delay. IEEE Trans. Neural Networks 11, 1481–1484 (2000)
Liao, X.: Mathematical Theory of Cellular Neural Networks 1. China Science 24, 902–910 (1994)
Hale, J.: Theory of Functional Differential Equations. Springer, New York (1977)
Qin, Y., Liu, Y., Wang, L.: Motion Stability of Dynamical Systems with Time-Delays, 2nd edn. Science Press, Beijing (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, D., Wang, Y. (2009). Stability Conditions of Delayed Recurrent Neural Networks with Positive Linear Activation Functions. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5551. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01507-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-01507-6_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01506-9
Online ISBN: 978-3-642-01507-6
eBook Packages: Computer ScienceComputer Science (R0)