Exponential transients in continuous-time symmetric Hopfield nets
Abstract
We establish a fundamental result in the theory of continuous-time neural computation, by showing that so called continuous-time symmetric Hopfield nets, whose asymptotic convergence is always guaranteed by the existence of a Liapunov function may, in the worst case, possess a transient period that is exponential in the network size. The result stands in contrast to e.g. the use of such network models in combinatorial optimization applications.
Main Authors
Format
Conferences
Conference paper
Published
2001
Series
Subjects
Publication in research information system
Publisher
Springer-Verlag
The permanent address of the publication
https://urn.fi/URN:NBN:fi:jyu-201807173589Use this for linking
Parent publication ISBN
978-3-540-42486-4
Review status
Peer reviewed
DOI
https://doi.org/10.1007/3-540-44668-0_112
Conference
International Conference on Artificial Neural Networks
Language
English
Published in
Lecture Notes in Computer Science
Is part of publication
ICANN 2001 : Artificial Neural Networks. Proceedings of the International Conference Vienna, Austria, August 21-25, 2001
Citation
- Sima, J., & Orponen, P. (2001). Exponential transients in continuous-time symmetric Hopfield nets. In G. Dorffner, H. Bischof, & K. Hornik (Eds.), ICANN 2001 : Artificial Neural Networks. Proceedings of the International Conference Vienna, Austria, August 21-25, 2001 (pp. 806-813). Springer-Verlag. Lecture Notes in Computer Science, 2130. https://doi.org/10.1007/3-540-44668-0_112
License
Copyright© Springer-Verlag Berlin Heidelberg 2001