File(s) not publicly available
Evolving spike-timing dependent plasticity for single-trial learning in robots
journal contribution
posted on 2023-06-07, 22:37 authored by Ezequiel Di PaoloSingle–trial learning is studied in an evolved robot model of synaptic spike–timing–dependent plasticity (STDP). Robots must perform positive phototaxis but must learn to perform negative phototaxis in the presence of a short–lived aversive sound stimulus. STDP acts at the millisecond range and depends asymmetrically on the relative timing of pre– and post–synaptic spikes. Although it has been involved in learning models of input prediction, these models require the iterated presentation of the input pattern, and it is hard to see how this mechanism could sustain single–trial learning over a time–scale of tens of seconds. An incremental evolutionary approach is used to answer this question. The evolved robots succeed in learning the appropriate behaviour, but learning does not depend on achieving the right synaptic configuration but rather the right pattern of neural activity. Robot performance during positive phototaxis is quite robust to loss of spike–timing information, but in contrast, this loss is catastrophic for learning negative phototaxis where entrained firing is common. Tests show that the final weight configuration carries no information about whether a robot is performing one behaviour or the other. Fixing weights, however, has the effect of degrading performance, thus demonstrating that plasticity is used to sustain the neural activity corresponding both to the normal phototaxis condition and to the learned behaviour. The implications and limitations of this result are discussed.
History
Publication status
- Published
Journal
Philosophical Transactions A: Mathematical, Physical and Engineering SciencesISSN
14712962Publisher
The Royal SocietyExternal DOI
Volume
361Page range
2299-2319Pages
21.0Department 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