Show simple item record

dc.contributor.authorGlackin, Cornelius
dc.contributor.authorMaguire, Liam
dc.contributor.authorMcDaid, Liam
dc.contributor.authorSayers, Heather
dc.date.accessioned2013-01-14T15:29:14Z
dc.date.available2013-01-14T15:29:14Z
dc.date.issued2011-04
dc.identifier.citationGlackin , C , Maguire , L , McDaid , L & Sayers , H 2011 , ' Receptive field optimisation and supervision of a fuzzy spiking neural network ' , Neural Networks , vol. 24 , no. 3 , pp. 247-56 . https://doi.org/10.1016/j.neunet.2010.11.008
dc.identifier.issn1879-2782
dc.identifier.otherPURE: 734160
dc.identifier.otherPURE UUID: 22c204b8-4db0-41e8-9382-f4efbebd14dc
dc.identifier.otherPubMed: 21277162
dc.identifier.otherScopus: 79951514022
dc.identifier.urihttp://hdl.handle.net/2299/9625
dc.descriptionCopyright © 2010 Elsevier Ltd. All rights reserved.
dc.description.abstractThis paper presents a supervised training algorithm that implements fuzzy reasoning on a spiking neural network. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to certain spike train firing rates and behave in a similar manner as fuzzy membership functions. The connectivity of the hidden and output layers in the fuzzy spiking neural network (FSNN) is representative of a fuzzy rule base. Fuzzy C-Means clustering is utilised to produce clusters that represent the antecedent part of the fuzzy rule base that aid classification of the feature data. Suitable cluster widths are determined using two strategies; subjective thresholding and evolutionary thresholding respectively. The former technique typically results in compact solutions in terms of the number of neurons, and is shown to be particularly suited to small data sets. In the latter technique a pool of cluster candidates is generated using Fuzzy C-Means clustering and then a genetic algorithm is employed to select the most suitable clusters and to specify cluster widths. In both scenarios, the network is supervised but learning only occurs locally as in the biological case. The advantages and disadvantages of the network topology for the Fisher Iris and Wisconsin Breast Cancer benchmark classification tasks are demonstrated and directions of current and future work are discussed.en
dc.format.extent10
dc.language.isoeng
dc.relation.ispartofNeural Networks
dc.rightsOpen
dc.subjectAction Potentials
dc.subjectAnimals
dc.subjectArtificial Intelligence
dc.subjectFemale
dc.subjectFuzzy Logic
dc.subjectHumans
dc.subjectNeural Networks (Computer)
dc.subjectNeurons
dc.titleReceptive field optimisation and supervision of a fuzzy spiking neural networken
dc.contributor.institutionSchool of Computer Science
dc.description.statusPeer reviewed
dc.relation.schoolSchool of Computer Science
dc.description.versiontypeFinal Accepted Version
dcterms.dateAccepted2011-04
rioxxterms.versionAM
rioxxterms.versionofrecordhttps://doi.org/10.1016/j.neunet.2010.11.008
rioxxterms.typeJournal Article/Review
herts.preservation.rarelyaccessedtrue
herts.rights.accesstypeOpen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record