Regularizing soft decision trees

Yükleniyor...
Küçük Resim

Tarih

2013

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

Springer

Erişim Hakkı

info:eu-repo/semantics/closedAccess

Araştırma projeleri

Organizasyon Birimleri

Dergi sayısı

Özet

Recently, we have proposed a new decision tree family called soft decision trees where a node chooses both its left and right children with different probabilities as given by a gating function, different from a hard decision node which chooses one of the two. In this paper, we extend the original algorithm by introducing local dimension reduction via L-1 and L-2 regularization for feature selection and smoother fitting. We compare our novel approach with the standard decision tree algorithms over 27 classification data sets. We see that both regularized versions have similar generalization ability with less complexity in terms of number of nodes, where L-2 seems to work slightly better than L-1.

Açıklama

Anahtar Kelimeler

Algorithms, Classification (of information), Data mining, Information science, Decision-tree algorithm, Dimension reduction, Gating functions, Generalization ability, Hard decisions, Original algorithms, Decision trees

Kaynak

Lecture Notes in Electrical Engineering

WoS Q Değeri

N/A

Scopus Q Değeri

Q4

Cilt

264

Sayı

Künye

Yıldız, O. T. & Alpaydın, A. İ. E. (2014). Regularizing soft decision trees. Paper presented at the Lecture Notes in Electrical Engineering, 264, 15-21. doi:10.1007/978-3-319-01604-7_2