OC1: randomized induction of oblique decision trees

Authors:
Sreerama Murthy;Simon Kasif;Steven Salzberg;Richard Beigel
Affiliations:
Dept. of Computer Science, Johns Hopkins University, Baltimore, MD;Dept. of Computer Science, Johns Hopkins University, Baltimore, MD;Dept. of Computer Science, Johns Hopkins University, Baltimore, MD;Dept. of Computer Science, Yale University, New Haven, CT
Venue:
AAAI'93 Proceedings of the eleventh national conference on Artificial intelligence
Year:
1993

Citing 8
Cited 4

Inferring decision trees using the minimum description length principle

Information and Computation
C4.5: programs for machine learning

C4.5: programs for machine learning
A geometric framework for machine learning

A geometric framework for machine learning
An Empirical Comparison of Pruning Methods for Decision Tree Induction

Machine Learning
Induction of Decision Trees

Machine Learning
Distance Metrics for Instance-Bsed Learning

ISMIS '91 Proceedings of the 6th International Symposium on Methodologies for Intelligent Systems
Linear Machine Decision Trees

Linear Machine Decision Trees
An empirical comparison of pattern recognition, neural nets, and machine learning classification methods

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1

Towards the automatic design of decision tree induction algorithms

Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Model trees for classification of hybrid data types

IDEAL'05 Proceedings of the 6th international conference on Intelligent Data Engineering and Automated Learning
Automatic creation of links: an approach based on decision tree

FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part II
From Optimal Hyperplanes to Optimal Decision Trees

Fundamenta Informaticae

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces OC1, a new algorithm for generating multivariate decision trees. Multivariate trees classify examples by testing linear combinations of the features at each non-leaf node of the tree. Each test is equivalent to a hyperplane at an oblique orientation to the axes. Because of the computational intractability of finding an optimal orientation for these hyperplanes, heurist.ic methods must be used to produce good trees. This paper explores a new method that combines deterministic and randomized procedures to search for a good tree. Experiments on several different real-world data sets demonstrate that the method consistently finds much smaller trees than comparable methods using univariate tests. In addition, the accuracy of the trees found with our method matches or exceeds the best results of other machine learning methods.