« Apprentissage d'Occam » : différence entre les versions
(Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == ''' Occam learning''' In computational learning theory, Occam learning... ») |
(Aucune différence)
|
Version du 17 décembre 2020 à 22:22
en construction
Définition
XXXXXXXXX
Français
XXXXXXXXX
Anglais
Occam learning
In computational learning theory, Occam learning is a model of algorithmic learning where the objective of the learner is to output a succinct representation of received training data. This is closely related to probably approximately correct (PAC) learning, where the learner is evaluated on its predictive power of a test set.
Occam learnability implies PAC learning, and for a wide variety of concept classes, the converse is also true: PAC learnability implies Occam learnability.
Contributeurs: Imane Meziani, wiki