Constructive Induction on Symbolic Features

Abstract

This paper addresses the problem of constructing new comparative terms from symbolic attributes. Within a set-theoretic framework, experiments with a learning system, RL4, show a performance improvement, which indicates that the set-theoretic method is effective and efficient and that symbolic comparative terms do improve the adequacy of the concept description language.

Cite

Text

Leng and Buchanan. "Constructive Induction on Symbolic Features." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50036-2

Markdown

[Leng and Buchanan. "Constructive Induction on Symbolic Features." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/leng1991icml-constructive/) doi:10.1016/B978-1-55860-200-7.50036-2

BibTeX

@inproceedings{leng1991icml-constructive,
  title     = {{Constructive Induction on Symbolic Features}},
  author    = {Leng, Bing and Buchanan, Bruce G.},
  booktitle = {International Conference on Machine Learning},
  year      = {1991},
  pages     = {163-167},
  doi       = {10.1016/B978-1-55860-200-7.50036-2},
  url       = {https://mlanthology.org/icml/1991/leng1991icml-constructive/}
}