Univariate margin tree
Yükleniyor...
Dosyalar
Tarih
2010
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In many pattern recognition applications, first decision trees are used due to their simplicity and easily interpretable nature. In this paper, we propose a new decision tree learning algorithm called univariate margin tree, where for each continuous attribute, the best split is found using convex optimization. Our simulation results on 47 datasets show that the novel margin tree classifier performs at least as good as C4.5 and LDT with a similar time complexity. For two class datasets it generates smaller trees than C4.5 and LDT without sacrificing from accuracy, and generates significantly more accurate trees than C4.5 and LDT for multiclass datasets with one-vs-rest methodology.
Açıklama
Anahtar Kelimeler
Continuous attribute, Convex optimization, Data sets, Decision trees, Decision tree learning algorithm, Information science, Learning algorithms, Multi-class, Neural networks, Pattern recognition, Simulation result, Support vector machines, Time complexity, Tree classifiers, Univariate
Kaynak
Lecture Notes in Electrical Engineering
WoS Q Değeri
Scopus Q Değeri
Q4
Cilt
62
Sayı
Künye
Yıldız, O. T. (2010). Univariate margin tree. Paper presented at the Lecture Notes in Electrical Engineering, 62, 11-16. doi:10.1007/978-90-481-9794-1_3
