Budding trees

Basit Öğe Kaydı
dc.authorid0000-0001-5838-4615
dc.authorid0000-0001-7506-0321
dc.contributor.authorİrsoy, Ozanen_US
dc.contributor.authorYıldız, Olcay Taneren_US
dc.contributor.authorAlpaydın, Ahmet İbrahim Ethemen_US
dc.date.accessioned2015-11-24T14:15:03Z
dc.date.available2015-11-24T14:15:03Z
dc.date.issued2014-08-24
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Computer Engineeringen_US
dc.description.abstractWe propose a new decision tree model, named the budding tree, where a node can be both a leaf and an internal decision node. Each bud node starts as a leaf node, can then grow children, but then later on, if necessary, its children can be pruned. This contrasts with traditional tree construction algorithms that only grows the tree during the training phase, and prunes it in a separate pruning phase. We use a soft tree architecture and show that the tree and its parameters can be trained using gradient-descent. Our experimental results on regression, binary classification, and multi-class classification data sets indicate that our newly proposed model has better performance than traditional trees in terms of accuracy while inducing trees of comparable size.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationİrsoy, O., Yıldız, O. T. & Alpaydın, A. İ. E. (2014). Budding trees. Paper presented at the 22nd International Conference on Pattern Recognition, 3582-3587. doi:10.1109/ICPR.2014.616en_US
dc.identifier.doi10.1109/ICPR.2014.616
dc.identifier.endpage3587
dc.identifier.isbn9781479952083
dc.identifier.issn1051-4651
dc.identifier.scopus2-s2.0-84919884115
dc.identifier.scopusqualityN/A
dc.identifier.startpage3582
dc.identifier.urihttps://hdl.handle.net/11729/721
dc.identifier.urihttp://dx.doi.org/10.1109/ICPR.2014.616
dc.identifier.wosWOS:000359818003120
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakConference Proceedings Citation Index – Science (CPCI-S)en_US
dc.institutionauthorYıldız, Olcay Taneren_US
dc.institutionauthorid0000-0001-5838-4615
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherIEEE Computer Socen_US
dc.relation.ispartof22nd International Conference on Pattern Recognitionen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAccuracyen_US
dc.subjectEducational institutionsen_US
dc.subjectEquationsen_US
dc.subjectMathematical modelen_US
dc.subjectRegression tree analysisen_US
dc.subjectTrainingen_US
dc.subjectDecision treesen_US
dc.subjectGradient methodsen_US
dc.subjectBinary classificationen_US
dc.subjectBudding treesen_US
dc.subjectDecision tree modelen_US
dc.subjectGradient-descenten_US
dc.subjectInternal decision nodeen_US
dc.subjectLeaf nodeen_US
dc.subjectMulticlass classification data setsen_US
dc.subjectPruning phaseen_US
dc.subjectRegressionen_US
dc.subjectSoft tree architectureen_US
dc.subjectTree construction algorithmen_US
dc.titleBudding treesen_US
dc.typeConference Objecten_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
721.pdf
Boyut:
220.87 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.71 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bildiri Koleksiyonu | Bilgisayar Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu