Abstract
We show how to construct a Lyapunov function for a discrete recurrent neural network using the variable-gradient method. This method can also be used to obtain the Hopfield energy function. Using our Lyapunov function, we compute an upper bound for the transient length for our neural network dynamics. We also show how our Lyapunov function can provide insights into the effect that the introduction of self-feedback weights to our neural network has on the sizes of the basins of attraction of the equilibrium points of the neural network state space.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
F. Csáki. Modern Control Theory. Akadémiai Kiado Budapest, 1971.
P. Floréen. Worst-case convergence times for hopfield memories. IEEE Trans. on Neural Networks, 2(5):533–535, 1991.
F. Fogelman-Soulie et. al. Transient length in sequential iteration of threshold functions. Discrete Applied Mathematics, 6:95–98, 1983.
E. Goles and S. Martínez. Neural and Automata Networks. Kluwer Academic Publisher, 1990.
E. Goles et. al. Decreasing energy functions as a tool for studying threshold networks. Discrete Applied Mathematics, 12:261–277, 1985.
M. Hirsch and S. Smale. Differential Equations, Dynamical Systems and Linear Algebra. Academic Press, 1974.
J. Hopfield. Neural networks and physical systems with emergent collective computational abilities. Proc. of Nat. Acad. Sci, U.S.A., 79:2554–2558, 1982.
Y. Kamp and M. Hasler. Recursive Neural Networks for Associative Memory. Wiley, 1990.
J. Komlós and R. Paturi. Convergence results in associative memory model. Neural Networks, 1:239–250, 1988.
A. Michel et. al. Qualitative analysis of neural networks. IEEE Trans. on Circuits and Systems, 36(2):229–243, 1989.
R. R. Mohler. Nonlinear Systems:Dynamics and Control. Prentice Hall, 1991.
P. C. Parks. A. M. Lyapunov's stability theory—100 years on. IMA Journal of Mathematical Control and Information, 9:275–303, 1992.
N. Peterfreud and Y. Baram. Second-order bounds on the domain of attraction and the rate of convergence of nonlinear dynamical systems and neural networks. IEEE Trans. on Neural Networks, 5(4):551–560, 1994.
J.-J. E. Slotine and Li W. Applied Nonlinear Control. Prentice Hall, 1991.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ho, A.M.C.L., De Wilde, P. (1995). General transient length upper bound for recurrent neural networks. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_176
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_176
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive