ML Anthology

Feature Construction in Structural Decision Trees

Larry Watanabe, Larry A. Rendell
ICML 1991 pp. 218-222
doi:10.1016/B978-1-55860-200-7.50047-7 /icml/1991/watanabe1991icml-feature/

Abstract

STRUCT is a system that learns structural decision trees from positive and negative examples. The algorithm uses a modification of Pagallo and Haussler's FRINGE algorithm to construct new features in a first-order representation. Experiments compare the different feature construction strategies. The results show that a modified FRINGE algorithm improves accuracy, but that it is sensitive to the distribution of the examples.

ICML Semantic Scholar

Cite

Text

Watanabe and Rendell. "Feature Construction in Structural Decision Trees." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50047-7

Markdown

[Watanabe and Rendell. "Feature Construction in Structural Decision Trees." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/watanabe1991icml-feature/) doi:10.1016/B978-1-55860-200-7.50047-7

BibTeX

@inproceedings{watanabe1991icml-feature,
  title     = {{Feature Construction in Structural Decision Trees}},
  author    = {Watanabe, Larry and Rendell, Larry A.},
  booktitle = {International Conference on Machine Learning},
  year      = {1991},
  pages     = {218-222},
  doi       = {10.1016/B978-1-55860-200-7.50047-7},
  url       = {https://mlanthology.org/icml/1991/watanabe1991icml-feature/}
}