Kurtosis-Based CRTRL Algorithms for Fully Connected Recurrent Neural Networks

Basit Öğe Kaydı
dc.contributor.authorMenguc E.C.
dc.contributor.authorAcir N.
dc.date.accessioned2019-08-01T13:38:39Z
dc.date.available2019-08-01T13:38:39Z
dc.date.issued2018
dc.departmentNiğde ÖHÜ
dc.description.abstractIn this paper, kurtosis-based complex-valued real-time recurrent learning (KCRTRL) and kurtosis-based augmented CRTRL (KACRTRL) algorithms are proposed for training fully connected recurrent neural networks (FCRNNs) in the complex domain. These algorithms are designed by minimizing the cost functions based on the kurtosis of a complex-valued error signal. The KCRTRL algorithm exploits the circularity properties of the complex-valued signals, and this algorithm not only provides a faster convergence rate but also results in a lower steady-state error. However, the KCRTRL algorithm is suboptimal in the processing of noncircular (NC) complex-valued signals. On the other hand, the KACRTRL algorithm contains a complete second-order information due to the augmented statistics, thus considerably improves the performance of the FCRNN in the processing of NC complex-valued signals. Simulation results on the one-step-ahead prediction problems show that the proposed KCRTRL algorithm significantly enhances the performance for only circular complex-valued signals, whereas the proposed KACRTRL algorithm provides more superior performance than existing algorithms for NC complex-valued signals in terms of the convergence rate and the steady-state error. © 2012 IEEE.
dc.identifier.doi10.1109/TNNLS.2018.2826442
dc.identifier.endpage6131
dc.identifier.issn2162237X
dc.identifier.issue12
dc.identifier.pmid29994052
dc.identifier.scopus2-s2.0-85046350453
dc.identifier.scopusqualityN/A
dc.identifier.startpage6123
dc.identifier.urihttps://dx.doi.org/10.1109/TNNLS.2018.2826442
dc.identifier.urihttps://hdl.handle.net/11480/1578
dc.identifier.volume29
dc.identifier.wosWOS:000451230100028
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.institutionauthor[0-Belirlenecek]
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofIEEE Transactions on Neural Networks and Learning Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectAugmented statistics
dc.subjectcircular and noncircular (NC) complex-valued signals
dc.subjectkurtosis
dc.subjectnonlinear complex-valued adaptive filter
dc.titleKurtosis-Based CRTRL Algorithms for Fully Connected Recurrent Neural Networks
dc.typeArticle

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu