Download:
|
by Huan Liu, Rudy Setiono
http://www.comp.nus.edu.sg/~liuh/ds98.ps
Add To MetaCart
Abstract:
Abstract. Univariate decision trees (UDT's) have inherent problems of replication, repetition, and fragmentation. Multivariate decision trees (MDT's) have been proposed to overcome some of the problems. Close examination of the conventional ways of building MDT's, however, reveals that the fragmentation problem still persists. A novel approach is suggested to minimize the fragmentation problem by separating hyperplane search from decision tree building. This is achieved by feature transformation. Let the initial feature vector be x, the new feature vector after feature transformation T is y, i.e., y = T (x). We can obtain an MDT by (1) building a UDT on y; and (2) replacing new features y at each node with the combinations of initial features x. We elaborate on the advantages of this approach, the details of T, and why it is expected to perform well. Experiments are conducted in order to confirm the analysis, and results are compared to those of C4.5, OC1, and CART. 1
Citations
|
3243
|
C4.5: Programs for Machine Learning
– Quinlan
- 1992
|
|
2511
|
Induction of decision trees
– Quinlan
- 1986
|
|
2466
|
Classification and Regression Trees
– Breiman, Friedman, et al.
- 1984
|
|
2157
|
Uci repository of machine learning databases
– Merz, Murphy
- 1996
|
|
424
|
Multi-interval discretization of continuous-valued attributes for classification learning
– Fayyad, Irani
- 1993
|
|
191
|
Boolean feature discovery in empirical learning
– Pagallo, Haussler
- 1990
|
|
172
|
The Feature Selection Problem: Traditional Methods and a New Algorithm
– Kira, Rendell
- 1992
|
|
170
|
Extracting refined rules from knowledge-based neural networks
– Towell, Shavlik
- 1993
|
|
135
|
An Empirical Comparison of Selection Measures for Decision Tree Induction”, Machine learning
– Mingers
- 1989
|
|
105
|
Hypothesis-driven Constructive Induction in AQ17-HCI: A method and experiments
– Wnek, Michalski
- 1994
|
|
104
|
Utgo , \Multivariate decision trees
– Brodley, E
- 1995
|
|
97
|
Symbolic and neural learning algorithms: an experimental comparison
– Shavlik, Mooney, et al.
- 1991
|
|
82
|
Constructive Induction on Decision Trees
– Matheus, Rendell
- 1989
|
|
80
|
Learning Oblique Decision Trees
– Heath, Kasif, et al.
- 1993
|
|
74
|
Lazy Decision Trees
– Friedman, Yun, et al.
- 1996
|
|
55
|
OC1: Randomized induction of oblique decision trees
– Murthy, Kasif, et al.
- 1993
|
|
50
|
Chi2: Feature selection and discretization of numeric attributes
– Liu, Setiono
- 1995
|
|
34
|
Neural Network Training via Linear Programming
– Bennett, Mangasarian
- 1992
|
|
26
|
An incremental method for finding multivariate splits for decision trees
– Utgoff
- 1990
|
|
25
|
Understanding neural networks via rule extraction
– Setiono, Liu
- 1995
|
|
15
|
Feature selection methods for classifications
– Dash, Liu
- 1997
|
|
14
|
A Penalty-function Approach for Pruning Feedforward Neural Networks
– Setiono
- 1997
|
|
14
|
Global data analysis and the fragmentation problem in decision tree induction
– Vilalta, Blix, et al.
- 1997
|
|
7
|
order derivatives for network pruning: Optimal brain surgeon
– Second
- 1993
|
|
5
|
Neural implementation of tree classifiers
– Sethi
- 1995
|
|
4
|
Analysis of hidden representations by greedy clustering, Connection Science (10)1
– Setiono, Liu
- 1998
|
