DMCA
On Mapping Decision Trees and Neural Networks (1999)
Cached
Download Links
- [www.iscs.nus.edu.sg]
- [ftp.comp.nus.edu.sg]
- [www.comp.nus.edu.sg]
- DBLP
Other Repositories/Bibliography
| Venue: | Knowledge Based Systems |
| Citations: | 5 - 0 self |
BibTeX
@ARTICLE{Setiono99onmapping,
author = {Rudy Setiono and Wee Kheng Leow},
title = {On Mapping Decision Trees and Neural Networks},
journal = {Knowledge Based Systems},
year = {1999},
volume = {13},
pages = {95--99}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
There exist several methods for transforming decision trees to neural networks. These methods typically construct the networks by directly mapping decision nodes or rules to the neural units. As a result, the networks constructed are often larger than necessary. This paper describes a pruning-based method for mapping decision trees to neural networks, which can compress the network by removing unimportant and redundant units and connections. In addition, equivalent decision trees extracted from the pruned networks are simpler than those induced by well-known algorithms such as ID3 and C4.5. Keywords: decision trees, neural networks, pruning. 1 Introduction Decision trees have been widely used for nonparametric pattern classification tasks which involve several pattern classes and a large number of features. Given an input pattern, the tree classifier performs the comparisons stipulated in each decision node of the tree, and then branches to either the left or the right subtree based on...
Keyphrases
neural network decision tree mapping decision tree decision node right subtree pruning-based method nonparametric pattern classification task well-known algorithm neural unit several pattern class introduction decision tree tree classifier redundant unit equivalent decision tree large number input pattern several method
