Abstract
We study the representation of static patterns and temporal sequences in neural networks with signal delays and a stochastic parallel dynamics. For a wide class of delay distributions, the asymptotic network behavior can be described by a generalized Gibbs distribution, generated by a novel Lyapunov functional for the determination dynamics. We extend techniques of equilibrium statistical mechanics so as to deal with time-dependent phenomena, derive analytic results for both retrieval quality and storage capacity, and compare them with numerical simulations.
Item Type: | Journal article |
---|---|
Form of publication: | Publisher's Version |
Faculties: | Biology > Department Biology II > Neurobiology |
Subjects: | 500 Science > 570 Life sciences; biology |
URN: | urn:nbn:de:bvb:19-epub-14829-2 |
ISSN: | 0031-9007 |
Language: | English |
Item ID: | 14829 |
Date Deposited: | 26. Mar 2013, 14:56 |
Last Modified: | 04. Nov 2020, 12:55 |