A Generalization Model Based on OI-implication for Ideal Theory Refinement

• Autorzy: Esposito, F. , Fanizzi, N. , Ferilli, S. , Semeraro, G.
• Języki publikacji: EN

Abstrakty

EN

A framework for theory refinement is presented pursuing the efficiency and effectiveness of learning regarded as a search process. A refinement operator satisfying these requirements is formally defined as ideal. Past results have demonstrated the impossibility of specifying ideal operators in search spaces where standard generalization models, like logical implication or q-subsumption, are adopted. By assuming the object identity bias over a space defined by a clausal language ordered by logical implication, a novel generalization model, named OI-implication, is derived and we prove that ideal operators can be defined for the resulting search space.

Słowa kluczowe

EN

incremental learning; theory refinement; refinement operators; generalization models; implication

• Czasopismo: Fundamenta Informaticae
• Rocznik: 2001
• Tom: Vol. 47, nr 1,2
• Strony: 15-33
• Opis fizyczny: bibliogr. 26 poz.

Twórcy

autor

Esposito, F.

autor

Fanizzi, N.

autor

Ferilli, S.

autor

Semeraro, G.

• Dipartimento di Informatica, Universita degli Studi di Bari, Via E. Orabona, 4 I-70125 Bari, Italy,