Connexion saute-couche


Révision datée du 25 mars 2018 à 14:46 par Pitpitt (discussion | contributions) (Page créée avec « __NOTOC__ == Domaine == Category:VocabularyVocabulary<br /> Category:Intelligence artificielleIntelligence artificielle<br /> <br /> == Définition == <br />... »)
(diff) ← Version précédente | Voir la version actuelle (diff) | Version suivante → (diff)

Domaine

Vocabulary
Intelligence artificielle



Définition


Termes privilégiés


Anglais

residual connections


ResNet and its constituent residual blocks draw their names from the ‘residual’—the difference between the predicted and target values. The authors of ResNet used residual learning of the form H(x) = F(x) + x. Simply, this means that even in the case of no residual, F(x)=0, we would still preserve an identity mapping of the input, x. The resulting learned residual allows our network to theoretically do no worse (than without it).