Extinction de neurone

Domaine

Intelligence artificielle
Apprentissage automatique
Apprentissage profond

Définition

Technique de régularisation dont le principe est de désactiver aléatoirement à chaque itération un certain pourcentage des neurones d’une couche afin d'éviter le surajustement.

Français

extinction de neurone

Anglais

dropout

Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks. Dropout layers first gained popularity through their use in CNNs, but have since been applied to other layers, including input embeddings or recurrent networks.