Tractable Induction and Classification in First Order Logic Via Stochastic Matching

  title={Tractable Induction and Classification in First Order Logic Via Stochastic Matching},
  author={Mich{\`e}le Sebag and C{\'e}line Rouveirol},
Learning in first-order logic (FOL) languages suffers from a specific difficulty: both induction and classification are potentially exponential in the size of hypotheses. This difficulty is usually dealt wi th by l imit ing the size of hypotheses, via either syntactic restrictions or search strategies. This paper is concerned with polynomial induction and use of FOL hypotheses with no size restrictions. This is done via stochastic matching: instead of exhaustively exploring the set of matchings… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.


Publications referenced by this paper.

Learning logical def ini t ion f rom relations

  • J. Quinlan
  • Machine Learning
  • 1990
Highly Influential
6 Excerpts

Compar ing the use of background knowledge by two I LP systems

  • A. Morgan Kaufmann. Srinivasan, S. Muggleton
  • 1995

Inverse entai lment and P R O G O L

  • S. A C M Press. Muggleton
  • 1995

Search intemsive concept induct ion

  • D. Haussler
  • Evolutionary Computation
  • 1994

Learning in FOL wi th a similari ty measure

  • Y. Kodratoff, R. Michalski, G. Bisson
  • 1992

Similar Papers

Loading similar papers…