ML Anthology

Learning Conjunctions of Horn Clauses

Dana Angluin, Michael Frazier, Leonard Pitt
MLJ 1992 pp. 147-164
doi:10.1007/BF00992675 /mlj/1992/angluin1992mlj-learning/

Abstract

An algorithm is presented for learning the class of Boolean formulas that are expressible as conjunctions of Horn clauses. (A Horn clause is a disjunction of literals, all but at most one of which is a negated variable.) The algorithm uses equivalence queries and membership queries to produce a formula that is logically equivalent to the unknown formula to be learned. The amount of time used by the algorithm is polynomial in the number of variables and the number of clauses in the unknown formula.

PDF MLJ Semantic Scholar

Cite

Text

Angluin et al. "Learning Conjunctions of Horn Clauses." Machine Learning, 1992. doi:10.1007/BF00992675

Markdown

[Angluin et al. "Learning Conjunctions of Horn Clauses." Machine Learning, 1992.](https://mlanthology.org/mlj/1992/angluin1992mlj-learning/) doi:10.1007/BF00992675

BibTeX

@article{angluin1992mlj-learning,
  title     = {{Learning Conjunctions of Horn Clauses}},
  author    = {Angluin, Dana and Frazier, Michael and Pitt, Leonard},
  journal   = {Machine Learning},
  year      = {1992},
  pages     = {147-164},
  doi       = {10.1007/BF00992675},
  volume    = {9},
  url       = {https://mlanthology.org/mlj/1992/angluin1992mlj-learning/}
}