Budding trees
Yükleniyor...
Dosyalar
Tarih
2014-08-24
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
IEEE Computer Soc
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
We 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.
Açıklama
Anahtar Kelimeler
Accuracy, Educational institutions, Equations, Mathematical model, Regression tree analysis, Training, Decision trees, Gradient methods, Binary classification, Budding trees, Decision tree model, Gradient-descent, Internal decision node, Leaf node, Multiclass classification data sets, Pruning phase, Regression, Soft tree architecture, Tree construction algorithm
Kaynak
22nd International Conference on Pattern Recognition
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
Cilt
Sayı
Künye
İrsoy, 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.2014.616