DC FieldValueLanguage
dc.contributor.authorTodorović, Branimiren
dc.contributor.authorStanković, Miomiren
dc.contributor.authorMoraga, Claudioen
dc.date.accessioned2020-12-11T13:04:29Z-
dc.date.available2020-12-11T13:04:29Z-
dc.date.issued2016-01-01en
dc.identifier.issn1860949Xen
dc.identifier.urihttp://researchrepository.mi.sanu.ac.rs/handle/123456789/4322-
dc.description.abstract© Springer International Publishing Switzerland 2016. We have implemented the recurrent neural networks training algorithms as joint estimation of synaptic weights and neuron outputs using approximate nonlinear recursive Bayesian estimators. We have considered two nonlinear derivative free estimators: Divided Difference Filter and Unscented Kalman filter and compared there computational efficiency and performances to the Extended Kalman Filter as training algorithms for different recurrent neural network architectures. Algorithms and architectures were tested on problems of long term, chaotic time series prediction.en
dc.relation.ispartofStudies in Computational Intelligenceen
dc.titleRecurrent neural networks training using derivative free nonlinear Bayesian filtersen
dc.typeBook Chapteren
dc.identifier.doi10.1007/978-3-319-26393-9_23en
dc.identifier.scopus2-s2.0-84949907787en
dc.identifier.urlhttps://api.elsevier.com/content/abstract/scopus_id/84949907787en
dc.relation.firstpage383en
dc.relation.lastpage410en
dc.contributor.orcid#NODATA#en
dc.contributor.orcid#NODATA#en
dc.contributor.orcid#NODATA#en
dc.relation.volume620en
item.cerifentitytypePublications-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.openairetypeBook Chapter-
item.grantfulltextnone-
Show simple item record

SCOPUSTM   
Citations

2
checked on Jul 21, 2024

Page view(s)

29
checked on May 9, 2024

Google ScholarTM

Check

Altmetric

Altmetric


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