Rowcliffe, Phill and Feng, Jianfeng. (2008) Training spiking neuronal networks with applications in engineering tasks. IEEE Transactions on Neural Networks, Vol.19 (No.9). pp. 1626-1640. ISSN 1045-9227

Full text not available from this repository.

Abstract

In this paper, spiking neuronal models employing means, variances, and correlations for computation are introduced. We present two approaches in the design of spiking neuronal networks, both of which are applied to engineering tasks. In exploring the input-output relationship of integrate-and-fire (IF) neurons with Poisson inputs, we are able to define mathematically robust learning rules, which can be applied to multilayer and time-series networks. We show through experimental applications that it is possible to train spike-rate networks on function approximation problems and on the dynamic task of robot arm control.

Item Type:	Journal Article
Subjects:	Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software Q Science > QP Physiology T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Science > Centre for Scientific Computing Faculty of Science > Computer Science
Library of Congress Subject Headings (LCSH):	Neural circuitry, Neural networks (Computer science), Computational neuroscience, Robotics
Journal or Publication Title:	IEEE Transactions on Neural Networks
Publisher:	IEEE
ISSN:	1045-9227
Date:	September 2008
Volume:	Vol.19
Number:	No.9
Number of Pages:	15
Page Range:	pp. 1626-1640
Identification Number:	10.1109/TNN.2008.2000999
Status:	Peer Reviewed
Publication Status:	Published
Access rights to Published version:	Restricted or Subscription Access
URI:	http://wrap.warwick.ac.uk/id/eprint/29302

Data sourced from Thomson Reuters' Web of Knowledge

Request changes to a record

Actions (login required)

View Item