Natural Ideal Operators in Inductive Logic Programming
Abstract
We present in this paper the original notion of natural relation , a quasi order that extends the idea of generality order: it allows the sound and dynamic pruning of hypotheses that do not satisfy a property, be it completeness or correctness with respect to the training examples, or hypothesis language restriction. Natural relations for conjunctions of such properties are characterized. Learning operators that satisfy these complex natural relations allow pruning with respect to this set of properties to take place before inappropriate hypotheses are generated. Once the natural relation is defined that optimally prunes the search space with respect to a set of properties, we discuss the existence of ideal operators for the search space ordered by this natural relation. We have adapted the results from [vdLNC94a] on the non-existence of ideal operators to those complex natural relations. We prove those nonexistence conditions do not apply to some of those natural relations, thus overcoming the previous negative results about ideal operators for space ordered by θ -subsumption only.
Cite
Text
Torre and Rouveirol. "Natural Ideal Operators in Inductive Logic Programming." European Conference on Machine Learning, 1997. doi:10.1007/3-540-62858-4_92Markdown
[Torre and Rouveirol. "Natural Ideal Operators in Inductive Logic Programming." European Conference on Machine Learning, 1997.](https://mlanthology.org/ecmlpkdd/1997/torre1997ecml-natural/) doi:10.1007/3-540-62858-4_92BibTeX
@inproceedings{torre1997ecml-natural,
title = {{Natural Ideal Operators in Inductive Logic Programming}},
author = {Torre, Fabien and Rouveirol, Céline},
booktitle = {European Conference on Machine Learning},
year = {1997},
pages = {274-289},
doi = {10.1007/3-540-62858-4_92},
url = {https://mlanthology.org/ecmlpkdd/1997/torre1997ecml-natural/}
}