DC Field | Value | Language |
---|---|---|
dc.contributor.author | Todorović, Branimir | en |
dc.contributor.author | Stanković, Miomir | en |
dc.contributor.author | Moraga, Claudio | en |
dc.date.accessioned | 2020-12-11T13:04:29Z | - |
dc.date.available | 2020-12-11T13:04:29Z | - |
dc.date.issued | 2016-01-01 | en |
dc.identifier.issn | 1860949X | en |
dc.identifier.uri | http://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.ispartof | Studies in Computational Intelligence | en |
dc.title | Recurrent neural networks training using derivative free nonlinear Bayesian filters | en |
dc.type | Book Chapter | en |
dc.identifier.doi | 10.1007/978-3-319-26393-9_23 | en |
dc.identifier.scopus | 2-s2.0-84949907787 | en |
dc.identifier.url | https://api.elsevier.com/content/abstract/scopus_id/84949907787 | en |
dc.relation.firstpage | 383 | en |
dc.relation.lastpage | 410 | en |
dc.contributor.orcid | #NODATA# | en |
dc.contributor.orcid | #NODATA# | en |
dc.contributor.orcid | #NODATA# | en |
dc.relation.volume | 620 | en |
item.grantfulltext | none | - |
item.cerifentitytype | Publications | - |
item.fulltext | No Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.openairetype | Book Chapter | - |
SCOPUSTM
Citations
2
checked on Sep 8, 2024
Page view(s)
1
checked on Sep 7, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.