« Extinction de neurone » : différence entre les versions
(Page créée avec « == Domaine == catégorie:Démo Catégorie Démo == Définition == == Termes privilégiés == == Anglais == ») |
Aucun résumé des modifications |
||
| Ligne 2 : | Ligne 2 : | ||
[[catégorie:Démo]] Catégorie Démo | [[catégorie:Démo]] Catégorie Démo | ||
[[Catégorie:Apprentissage profond]] Apprentissage profond | |||
== Définition == | == Définition == | ||
| Ligne 15 : | Ligne 15 : | ||
== Anglais == | == 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. | |||
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting | |||
• Recurrent Neural Network Regularization | |||
Version du 26 février 2018 à 19:30
Domaine
Catégorie Démo Apprentissage profond
Définition
Termes privilégiés
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. • Dropout: A Simple Way to Prevent Neural Networks from Overfitting • Recurrent Neural Network Regularization
Contributeurs: Claude Coulombe, Jacques Barolet, Julie Roy, Patrick Drouin, wiki
