Evolving spike-timing dependent plasticity for single-trial learning in robots

Di Paolo, Ezequiel (2003) Evolving spike-timing dependent plasticity for single-trial learning in robots. Philosophical Transactions A: Mathematical, Physical and Engineering Sciences, 361. pp. 2299-2319. ISSN 14712962

Full text not available from this repository.

Abstract

Single–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.

Item Type: Article
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Ezequiel Alejandro Di Paolo
Date Deposited: 06 Feb 2012 19:20
Last Modified: 07 Jun 2012 09:33
URI: http://sro.sussex.ac.uk/id/eprint/20172
📧 Request an update