File(s) not publicly available
Hebbian Learning using Fixed Weight Evolved Dynamical 'Neural' Networks
presentation
posted on 2023-06-07, 19:13 authored by Eduardo Izquierdo-Torres, Inman HarveyInman HarveyWe evolve small continuous-time recurrent neural networks with fixed weights that perform Hebbian learning behavior. We describe the performance of the best and smallest successful system, providing an in-depth analysis of its evolved mechanisms. Learning is shown to arise from the interaction between the multiple timescale dynamics. In particular, we show how the fast-time dynamics alter the slow-time dynamics, which in turn shapes the local behavior around the equilibrium points of the fast components by acting as a parameter to them.
History
Publication status
- Published
Publisher
IEEE PressPages
8.0Presentation Type
- paper
Event name
Proceedings of the First IEEE Symposium on Artificial Life. (IEEE-ALife'07)Event location
HawaiiEvent type
conferenceISBN
1-4244-0698-6Department affiliated with
- Informatics Publications
Full text available
- No
Peer reviewed?
- Yes
Legacy Posted Date
2012-02-06Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC