Iterative Hard Thresholding Based Extreme Learning Machine

Basit Öğe Kaydı
dc.authoridince, melih cevdet/0000-0002-8200-5571
dc.authoridALCIN, Omer/0000-0002-2917-3736
dc.authoridSengur, Abdulkadir/0000-0003-1614-2639
dc.authoridince, melih cevdet/0000-0002-8200-5571
dc.authorwosidince, melih cevdet/AAG-6556-2021
dc.authorwosidALCIN, Omer/AAH-3525-2020
dc.authorwosidSengur, Abdulkadir/Q-8023-2019
dc.authorwosidARI, ALİ/ABH-1602-2020
dc.authorwosidince, melih cevdet/V-9858-2018
dc.contributor.authorAlcin, Omer Faruk
dc.contributor.authorAri, Ali
dc.contributor.authorSengur, Abdulkadir
dc.contributor.authorInce, Melih Cevdet
dc.date.accessioned2024-08-04T20:41:07Z
dc.date.available2024-08-04T20:41:07Z
dc.date.issued2015
dc.departmentİnönü Üniversitesien_US
dc.description23nd Signal Processing and Communications Applications Conference (SIU) -- MAY 16-19, 2015 -- Inonu Univ, Malatya, TURKEYen_US
dc.description.abstractExtreme Learning Machines (ELM) is a new learning algorithm for Single hidden Layer Feed-forward Networks (SLFNs). The ELM has better generalization, rapid training and lower complexity, however, the method suffer from singularity problem and obtaining optimum number of neurons in the hidden layer. In this paper, we considered an IHT for sparse approximation of the output weights vector of the ELM network. The performance evaluation of the proposed method which is called IHT-ELM, was chosen out on four commonly used medical dataset for prediction purposes. The results showed that IHT-ELM has several advantages against the original ELM methods such as obtaining optimum number of neurons and low complexity.en_US
dc.description.sponsorshipDept Comp Engn & Elect & Elect Engn,Elect & Elect Engn,Bilkent Univen_US
dc.identifier.endpage370en_US
dc.identifier.isbn978-1-4673-7386-9
dc.identifier.issn2165-0608
dc.identifier.scopus2-s2.0-84939153105en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage367en_US
dc.identifier.urihttps://hdl.handle.net/11616/96909
dc.identifier.wosWOS:000380500900070en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isotren_US
dc.publisherIeeeen_US
dc.relation.ispartof2015 23rd Signal Processing and Communications Applications Conference (Siu)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectExtreme learning machineen_US
dc.subjectsingle-hidden-layer feed forward neural networksen_US
dc.subjectsparsityen_US
dc.subjectiterative hard thresholdingen_US
dc.titleIterative Hard Thresholding Based Extreme Learning Machineen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu