UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Wide learning: Using an ensemble of biologically-plausible spiking neural networks for unsupervised parallel classification of spatio-temporal patterns

Kozdon, K; Bentley, P; (2018) Wide learning: Using an ensemble of biologically-plausible spiking neural networks for unsupervised parallel classification of spatio-temporal patterns. In: Bonissone, PP and Fogel, D, (eds.) 2017 IEEE Symposium Series on Computational Intelligence (SSCI). (pp. pp. 3183-3190). IEEE Green open access

[img]
Preview
Text
08285167.pdf - Accepted version

Download (1MB) | Preview

Abstract

Spiking neural networks have been previously used to perform tasks such as object recognition without supervision. One of the concerns relating to the spiking neural networks is their speed of operation and the number of iterations necessary to train and use the network. Here, we propose a biologically plausible model of a spiking neural network which is used in multiple, separately trained copies to process subsets of data in parallel. This ensemble of networks is tested by applying it to the task of unsupervised classification of spatio-temporal patterns. Results show that despite different starting weights and independent training, the networks produce highly similar spiking patterns in response to the same class of inputs, enabling classification with fast training time.

Type: Proceedings paper
Title: Wide learning: Using an ensemble of biologically-plausible spiking neural networks for unsupervised parallel classification of spatio-temporal patterns
Event: IEEE Symposium Series on Computational Intelligence (IEEE SSCI), 27 November - 1 December 2017, Honolulu, Hawaii, US
Location: Honolulu, HI
Dates: 27 November 2017 - 01 December 2017
ISBN-13: 9781538627273
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/SSCI.2017.8285167
Publisher version: https://doi.org/10.1109/SSCI.2017.8285167
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: spiking neural network; spike timing dependent plasticity; pattern detection; parallel computing; ensemble network
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10047812
Downloads since deposit
157Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item