Show simple item record

dc.contributor.authorSchliebs, S
dc.contributor.authorDefoin-Platel, M
dc.contributor.authorKasabov, N
dc.contributor.editorKoppen, M
dc.contributor.editorKasabov, N
dc.contributor.editorCoghill, G
dc.date.accessioned2011-08-04T00:36:51Z
dc.date.available2011-08-04T00:36:51Z
dc.date.copyright2009
dc.date.issued2011-08-04
dc.identifier.citation15th International Conference, ICONIP 2008, Auckland, New Zealand, November 25-28, 2008, Revised Selected Papers, Part I, Lecture Notes in Computer Science Volume 5506, 2009, pages 1229 - 1236
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/10292/1567
dc.description.abstractThis study extends the recently proposed Evolving Spiking Neural Network (ESNN) architecture by combining it with an optimization algorithm, namely the Versatile Quantum-inspired Evolutionary Algorithm (vQEA). Following the wrapper approach, the method is used to identify relevant feature subsets and simultaneously evolve an optimal ESNN parameter setting. Applied to carefully designed benchmark data, containing irrelevant and redundant features of varying information quality, the ESNN-based feature selection procedure lead to excellent classification results and an accurate detection of relevant information in the dataset. Redundant and irrelevant features were rejected successively and in the order of the degree of information they contained.
dc.publisherSpringer
dc.rights© Springer-Verlag Berlin Heidelberg 2009. An author may self-archive an author-created version of his/her article on his/her own website and or in his/her institutional repository.
dc.subjectNeurons
dc.titleIntegrated feature and parameter optimization for an evolving spiking neural network
dc.typeConference Contribution
dc.rights.accessrightsOpenAccess
dc.identifier.doi10.1007/978-3-642-02490-0_149


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record