File(s) not publicly available
Associative learning on a continuum in evolved dynamical networks
journal contribution
posted on 2023-06-08, 10:01 authored by Eduardo Izquierdo, Inman HarveyInman Harvey, Randall D BeerThis article extends previous work on evolving learning without synaptic plasticity from discrete tasks to continuous tasks. Continuous-time recurrent neural networks without synaptic plasticity are artificially evolved on an associative learning task. The task consists in associating paired stimuli: temperature and food. The temperature to be associated can be either drawn from a discrete set or allowed to range over a continuum of values. We address two questions: Can the learning without synaptic plasticity approach be extended to continuous tasks? And if so, how does learning without synaptic plasticity work in the evolved circuits? Analysis of the most successful circuits to learn discrete stimuli reveal finite state machine (FSM) like internal dynamics. However, when the task is modified to require learning stimuli on the full continuum range, it is not possible to extract a FSM from the internal dynamics. In this case, a continuous state machine is extracted instead
History
Publication status
- Published
Journal
Adaptive BehaviorISSN
1059-7123External DOI
Issue
6Volume
16Page range
361-384Pages
24.0Department 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