« Extinction de neurone » : différence entre les versions
Aucun résumé des modifications |
Aucun résumé des modifications |
||
| Ligne 17 : | Ligne 17 : | ||
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 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 22 mars 2018 à 21:20
Domaine
Vocabulary Apprentissage profond
Définition
Termes privilégiés
Point mort
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
