SPAN: Spike Pattern Association Neuron for learning spatio-temporal sequences

Simple item page
aut.relation.endpage16
aut.relation.issue4 (2012)
aut.relation.startpage1
aut.relation.volume22
aut.researcherMohemmed, Ammar
dc.contributor.authorMohemmed, A
dc.contributor.authorSchliebs, S
dc.contributor.authorMatsuda, S
dc.contributor.authorKasabov, N
dc.contributor.editorHojjat Adeli
dc.date.accessioned2012-10-01T04:34:20Z
dc.date.available2012-10-01T04:34:20Z
dc.date.copyright2012
dc.date.issued2012
dc.description.abstractSpiking Neural Networks (SNN) were shown to be suitable tools for the processing of spatio-temporal information. However, due to their inherent complexity, the formulation of efficient supervised learning algorithms for SNN is difficult and remains an important problem in the research area. This article presents SPAN – a spiking neuron that is able to learn associations of arbitrary spike trains in a supervised fashion allowing the processing of spatio-temporal information encoded in the precise timing of spikes. The idea of the proposed algorithm is to transform spike trains during the learning phase into analog signals so that common mathematical operations can be performed on them. Using this conversion, it is possible to apply the well-known Widrow-Hoff rule directly to the transformed spike trains in order to adjust the synaptic weights and to achieve a desired input/output spike behavior of the neuron. In the here presented experimental analysis, the proposed learning algorithm is evaluated regarding its learning capabilities, its memory capacity, its robustness to noisy stimuli and its classification performance. Differences and similarities of SPAN regarding two related algorithms, ReSuMe and Chronotron, are discussed.
dc.identifier.citationInternational Journal of Neural Systems, Vol. 22, No. 4 (2012) 1250012 (17 pages)
dc.identifier.doi10.1142/S0129065712500128
dc.identifier.urihttps://hdl.handle.net/10292/4619
dc.publisherWorld Scientific Publishing Company
dc.relation.isreplacedby10292/4620
dc.relation.isreplacedbyhttp://hdl.handle.net/10292/4620
dc.relation.urihttp://dx.doi.org/10.1142/S0129065712500128
dc.rightsElectronic version of an article published as [see Citation] [see Publisher version] © [copyright World Scientific Publishing Company] [see Publisher version]
dc.rights.accessrightsOpenAccess
dc.subjectSpiking Neural Network
dc.subjectTemporal coding
dc.subjectSpike pattern association
dc.subjectLearning
dc.titleSPAN: Spike Pattern Association Neuron for learning spatio-temporal sequences
dc.typeJournal Article
pubs.organisational-data/AUT
pubs.organisational-data/AUT/Design & Creative Technologies
pubs.organisational-data/AUT/Design & Creative Technologies/School of Computing & Mathematical Science
pubs.organisational-data/AUT/PBRF Researchers
pubs.organisational-data/AUT/PBRF Researchers/Design & Creative Technologies PBRF Researchers
pubs.organisational-data/AUT/PBRF Researchers/Design & Creative Technologies PBRF Researchers/DCT C & M Computing
pubs.organisational-data/AUT/PBRF Researchers/Design & Creative Technologies PBRF Researchers/DCT Kedri
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ijns_11.pdf
Size:
482.95 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
KEDRI - the Knowledge Engineering and Discovery Research Institute