Show simple item record

dc.contributor.authorAlbrecht, A.
dc.contributor.authorWong, C.K.
dc.date.accessioned2011-02-21T09:18:05Z
dc.date.available2011-02-21T09:18:05Z
dc.date.issued2001
dc.identifier.citationAlbrecht , A & Wong , C K 2001 , ' Combining the perception algorithm with logarithmic simulated annealing ' , Neural Processing Letters , vol. 14 , no. 1 , pp. 75-83 . https://doi.org/10.1023/A:1011369322571
dc.identifier.issn1370-4621
dc.identifier.otherPURE: 99144
dc.identifier.otherPURE UUID: 7b2f9c64-bb50-4395-864b-98dc0907633f
dc.identifier.otherdspace: 2299/5348
dc.identifier.otherScopus: 0035425768
dc.identifier.urihttp://hdl.handle.net/2299/5348
dc.descriptionThe original publication is available at www.springerlink.com Copyright Springer [Full text of this article is not available in the UHRA]
dc.description.abstractWe present results of computational experiments with an extension of the Perceptron algorithm by a special type of simulated annealing. The simulated annealing procedure employs a logarithmic cooling schedule (-), where (-) is a parameter that depends on the underlying configuration space. For sample sets S of n-dimensional vectors generated by randomly chosen polynomials (-), we try to approximate the positive and negative examples by linear threshold functions. The approximations are computed by both the classical Perceptron algorithm and our extension with logarithmic cooling schedules. For (-) and (-), the extension outperforms the classical Perceptron algorithm by about 15% when the sample size is sufficiently large. The parameter was chosen according to estimations of the maximum escape depth from local minima of the associated energy landscape.en
dc.language.isoeng
dc.relation.ispartofNeural Processing Letters
dc.subjectcooling schedules
dc.subjectneural networks
dc.subjectperceptron algorithm
dc.subjectsimulated annealing
dc.subjectthreshold functions
dc.titleCombining the perception algorithm with logarithmic simulated annealingen
dc.contributor.institutionSchool of Computer Science
dc.contributor.institutionScience & Technology Research Institute
dc.description.statusPeer reviewed
rioxxterms.versionofrecordhttps://doi.org/10.1023/A:1011369322571
rioxxterms.typeJournal Article/Review
herts.preservation.rarelyaccessedtrue


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record