Learning transmission delays in spiking neural networks: A novel approach to sequence learning based on spike delay variance

Wright, Paul W. and Wiles, Janet (2012). Learning transmission delays in spiking neural networks: A novel approach to sequence learning based on spike delay variance. In: The 2012 International Joint Conference on Neural Networks (IJCNN). WCCI 2012 IEEE World Congress on Computational Intelligence, Brisbane, Australia, (1-8). 10-15 June 2012. doi:10.1109/IJCNN.2012.6252371

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Wright, Paul W.
Wiles, Janet
Title of paper Learning transmission delays in spiking neural networks: A novel approach to sequence learning based on spike delay variance
Conference name WCCI 2012 IEEE World Congress on Computational Intelligence
Conference location Brisbane, Australia
Conference dates 10-15 June 2012
Proceedings title The 2012 International Joint Conference on Neural Networks (IJCNN)   Check publisher's open access policy
Journal name International Joint Conference on Neural Networks. Proceedings   Check publisher's open access policy
Place of Publication Piscataway, NJ, United States
Publisher IEEE
Publication Year 2012
Sub-type Fully published paper
DOI 10.1109/IJCNN.2012.6252371
Open Access Status
ISBN 9781467314909
9781467314886
ISSN 2161-4393
Volume 10.1109/IJCNN.2012.6252371
Start page 1
End page 8
Total pages 8
Collection year 2013
Language eng
Abstract/Summary Transmission delays are an inherent component of spiking neural networks (SNNs) but relatively little is known about how delays are adapted in biological systems and studies on computational learning mechanisms have focused on spike-timing-dependent plasticity (STDP) which adjusts synaptic weights rather than synaptic delays. We propose a novel algorithm for learning temporal delays in SNNs with Gaussian synapses, which we call spike-delay-variance learning (SDVL). A key feature of the algorithm is adaptation of the shape (mean and variance) of the postsynaptic release profiles only, rather than the conventional STDP approach of adapting the network's synaptic weights. The algorithm's ability to learn temporal input sequences was tested in three studies using supervised and unsupervised learning within feed-forward networks. SDVL was able to successfully classify forty spatiotemporal patterns without supervision by providing robust, effective adaption of the postsynaptic release profiles. The results demonstrate how delay learning can contribute to the stability of spiking sequences, and that there is a potential role for adaption of variance as well as mean values in learning algorithms for spiking neural networks.
Keyword STDP
Delay learning
Sequence learning
Spike-delay-variance learning
Spiking neural networks
Transmission delays
Dynamics
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ
Additional Notes 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Sun, 02 Dec 2012, 00:25:49 EST by System User on behalf of Scholarly Communication and Digitisation Service