Horn Query Learning with Multiple Refinement

  1. Sierra, J. 1
  2. Santibáñez, J. 2
  1. 1 Universitat Politècnica de Catalunya
    info

    Universitat Politècnica de Catalunya

    Barcelona, España

    ROR https://ror.org/03mb6wj31

  2. 2 Universidad de La Rioja
    info

    Universidad de La Rioja

    Logroño, España

    ROR https://ror.org/0553yr311

Book:
Simulated Evolution and Learning :]7th International Conference, SEAL 2008, Melbourne, Australia, December 7-10, 2008. Proceedings

Publisher: Springer

ISBN: 978-3-540-89694-4

Year of publication: 2008

Volume: 5361 LNAI

Pages: 503-513

Type: Book chapter

DOI: 10.1007/978-3-540-89694-4_51 SCOPUS: 2-s2.0-58349083556 WoS: WOS:000263961300051 GOOGLE SCHOLAR

Abstract

In this paper we try to understand the heuristics that underlie the decisions made by the Horn query learning algorithm proposed in [1]. We take advantage of our explicit representation of such heuristics in order to present an alternative termination proof for the algorithm, as well as to justify its decisions by showing that they always guarantee that the negative examples in the sequence maintained by the algorithm violate different clauses in the target formula. Finally, we propose a new algorithm that allows multiple refinement when we can prove that such a refinement does not affect the independence of the negative examples in the sequence maintained by the algorithm. © 2008 Springer Berlin Heidelberg.