Show simple item record

dc.contributor.authorFrank, R.
dc.contributor.authorDavey, N.
dc.contributor.authorHunt, Stephen
dc.date.accessioned2011-10-18T15:01:10Z
dc.date.available2011-10-18T15:01:10Z
dc.date.issued2000
dc.identifier.citationFrank , R , Davey , N & Hunt , S 2000 , Input window size and neural network predictors . in Procs of the IEEE-INNS-ENNS Int Joint Conf on Neural Networks, 2000 (IJCNN 2000) . vol. 2 , IEEE , pp. 237-242 . https://doi.org/10.1109/IJCNN.2000.857903
dc.identifier.isbn0-7695-0619-4
dc.identifier.otherPURE: 422507
dc.identifier.otherPURE UUID: d84b5b6c-395d-4f22-870c-e49696c2bb8f
dc.identifier.otherdspace: 2299/838
dc.identifier.otherScopus: 0033687260
dc.identifier.urihttp://hdl.handle.net/2299/6719
dc.description.abstractNeural network approaches to time series prediction are briefly discussed, and the need to specify an appropriately sized input window identified. Relevant theoretical results from dynamic systems theory are briefly introduced, and heuristics for finding the correct embedding dimension, and hence window size, are discussed. The method is applied to two time series and the resulting generalisation performance of the trained feedforward neural network predictors is analysed. It is shown that the heuristics can provide useful information in defining the appropriate network architectureen
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofProcs of the IEEE-INNS-ENNS Int Joint Conf on Neural Networks, 2000 (IJCNN 2000)
dc.rightsOpen
dc.titleInput window size and neural network predictorsen
dc.contributor.institutionScience & Technology Research Institute
dc.contributor.institutionSchool of Computer Science
dc.relation.schoolSchool of Computer Science
dc.description.versiontypeFinal Accepted Version
dcterms.dateAccepted2000
rioxxterms.versionAM
rioxxterms.versionofrecordhttps://doi.org/10.1109/IJCNN.2000.857903
rioxxterms.typeOther
herts.preservation.rarelyaccessedtrue
herts.rights.accesstypeOpen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record