Spaces of Theories with Ideal Refinement Operators
Abstract
Refinement operators for theories avoid the problems related to the myopia of many relational learning algorithms based on the operators that refine single clauses. However, the non-existence of ideal refinement operators has been proven for the standard clausal search spaces based on theta-subsumption or logical implication, which scales up to the spaces of theories. By adopting different generalization models constrained by the \nassumption of object identity, we extend the theoretical results \non the existence of ideal refinement operators for spaces of clauses to the case of spaces of theories.
Cite
Text
Fanizzi et al. "Spaces of Theories with Ideal Refinement Operators." International Joint Conference on Artificial Intelligence, 2003.Markdown
[Fanizzi et al. "Spaces of Theories with Ideal Refinement Operators." International Joint Conference on Artificial Intelligence, 2003.](https://mlanthology.org/ijcai/2003/fanizzi2003ijcai-spaces/)BibTeX
@inproceedings{fanizzi2003ijcai-spaces,
title = {{Spaces of Theories with Ideal Refinement Operators}},
author = {Fanizzi, Nicola and Ferilli, Stefano and Di Mauro, Nicola and Basile, Teresa Maria Altomare},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2003},
pages = {527-532},
url = {https://mlanthology.org/ijcai/2003/fanizzi2003ijcai-spaces/}
}