Combining Top-Down and Bottom-up Techniques in Inductive Logic Programming
Abstract
This paper describes a new method for inducing logic programs from examples which attempts to integrate the best aspects of existing ILP methods into a single coherent framework. In particular, it combines a bottom-up method similar to GOLEM with a top-down method similar to FOIL. It also includes a method for predicate invention similar to CHAMP and an elegant solution to the “noisy oracle” problem which allows the system to learn recursive programs without requiring a complete set of positive examples. Systematic experimental comparisons to both GOLEM and FOIL on a range of problems are used to clearly demonstrate the advantages of the approach.
Cite
Text
Zelle et al. "Combining Top-Down and Bottom-up Techniques in Inductive Logic Programming." International Conference on Machine Learning, 1994. doi:10.1016/B978-1-55860-335-6.50049-0Markdown
[Zelle et al. "Combining Top-Down and Bottom-up Techniques in Inductive Logic Programming." International Conference on Machine Learning, 1994.](https://mlanthology.org/icml/1994/zelle1994icml-combining/) doi:10.1016/B978-1-55860-335-6.50049-0BibTeX
@inproceedings{zelle1994icml-combining,
title = {{Combining Top-Down and Bottom-up Techniques in Inductive Logic Programming}},
author = {Zelle, John M. and Mooney, Raymond J. and Konvisser, Joshua B.},
booktitle = {International Conference on Machine Learning},
year = {1994},
pages = {343-351},
doi = {10.1016/B978-1-55860-335-6.50049-0},
url = {https://mlanthology.org/icml/1994/zelle1994icml-combining/}
}