Sciweavers

55 search results - page 1 / 11
» A new metric splitting criterion for decision trees
Sort
View
PAAPP
2006
85views more  PAAPP 2006»
13 years 5 months ago
A new metric splitting criterion for decision trees
Abstract: We examine a new approach to building decision tree by introducing a geometric splitting criterion, based on the properties of a family of metrics on the space of partiti...
Dan A. Simovici, Szymon Jaroszewicz
PAKDD
2004
ACM
108views Data Mining» more  PAKDD 2004»
13 years 10 months ago
A Metric Approach to Building Decision Trees Based on Goodman-Kruskal Association Index
We introduce a numerical measure on sets of partitions of finite sets that is linked to the Goodman-Kruskal association index commonly used in statistics. This measure allows us t...
Dan A. Simovici, Szymon Jaroszewicz
ICML
2002
IEEE
14 years 6 months ago
Learning Decision Trees Using the Area Under the ROC Curve
ROC analysis is increasingly being recognised as an important tool for evaluation and comparison of classifiers when the operating characteristics (i.e. class distribution and cos...
César Ferri, José Hernández-O...
FLAIRS
2006
13 years 6 months ago
Generalized Entropy for Splitting on Numerical Attributes in Decision Trees
Decision Trees are well known for their training efficiency and their interpretable knowledge representation. They apply a greedy search and a divide-and-conquer approach to learn...
Mingyu Zhong, Michael Georgiopoulos, Georgios C. A...
INTERSPEECH
2010
13 years 3 days ago
A discriminative splitting criterion for phonetic decision trees
Phonetic decision trees are a key concept in acoustic modeling for large vocabulary continuous speech recognition. Although discriminative training has become a major line of rese...
Simon Wiesler, Georg Heigold, Markus Nußbaum...