DC FieldValueLanguage
dc.contributor.authorTodorovic, Branimiren
dc.contributor.authorStanković, Miomiren
dc.contributor.authorMoraga, Claudioen
dc.date.accessioned2020-12-11T13:04:36Z-
dc.date.available2020-12-11T13:04:36Z-
dc.date.issued2006-12-01en
dc.identifier.isbn1-4244-0433-9en
dc.identifier.urihttp://researchrepository.mi.sanu.ac.rs/handle/123456789/4381-
dc.description.abstractWe consider the problem of recurrent neural network training as a Bayesian state estimation. The proposed algorithm uses Gaussian sum filter for nonlinear, non-Gaussian estimation of network outputs and synaptic weights. The performances of the proposed algorithm and other Bayesian filters are compared in noisy chaotic time series long-term prediction.en
dc.publisherIEEE-
dc.relation.ispartof8th Seminar on Neural Network Applications in Electrical Engineering, Neurel-2006 Proceedingsen
dc.subjectDivided difference filter | Extended Kalman filter | Gaussian sum filter | Recurrent neural networks | Sequential Bayesian estimation | Unscented kalman filteren
dc.titleGaussian sum filters for recurrent neural networks trainingen
dc.typeConference Paperen
dc.identifier.doi10.1109/NEUREL.2006.341175en
dc.identifier.scopus2-s2.0-46749152690en
dc.relation.firstpage53en
dc.relation.lastpage57en
item.cerifentitytypePublications-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.openairetypeConference Paper-
item.grantfulltextnone-
Show simple item record

SCOPUSTM   
Citations

1
checked on Jul 21, 2024

Page view(s)

38
checked on May 9, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.