Communication Dans Un Congrès Année : 2006

Version Space Learning for Possibilistic Hypotheses

Résumé

In this paper, we are interested in learning stratified hypotheses from examples and counter-examples associated with weights that express their prototypical importance. It leads to an extension of the well-known version space learning framework. In order to do that, we emphasize that the treatment of positive and negative examples in version space learning is reminding of a bipolar revision process recently studied in the setting of possibilistic information representation. Bipolarity appears when the positive and negative sides of information are specified in a distinct way. Then, we use the possibilistic bipolar representation setting, which distinguishes between what is guaranteed to be possible, and what is simply not impossible, as a basis for extending version space learning to examples associated with possibility degrees. It allows us to define a formal framework for learning layered hypotheses.

Fichier principal
Vignette du fichier
Prade_Serrurier_2006.pdf (112.42 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-03361589 , version 1 (01-10-2021)

Licence

Identifiants

  • HAL Id : hal-03361589 , version 1

Citer

Henri Prade, Mathieu Serrurier. Version Space Learning for Possibilistic Hypotheses. 17th European Conference on Artificial Intelligence (ECAI 2006), European Coordinating Committee for Artificial Intelligence (ECCAI); Italian Association of Artificial Intelligence, Aug 2006, Riva del Garda, Italy. pp.801-802. ⟨hal-03361589⟩
80 Consultations
104 Téléchargements

Partager

  • More