A principled approach to fuzzy rule base interpolation using similarity relations
Résumé
In this work we consider a very general principle for fuzzy rule interpolation methods based on an interpretation of the generalized modus ponens rule in terms of closeness relations. Then we present two particular instances of the general principle when the closeness relations are defined from parametric families of similarity fuzzy relations on the input and output spaces. The case of multiple input variables is also considered.
Domaines
Intelligence artificielle [cs.AI]
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...