Dropout
Randomly zeroing activations during training to reduce overfitting.
Aperçu
Dropout randomly disables a fraction of activations on each training step, so no unit can rely on another being present. It solves the problem that a network large enough to fit the training data will memorise it rather than learn from it. It exists as one of the cheapest regularisers available, and it is switched off at inference where the full network is used.
Graphe des technologies
Comment Dropout se rattache au reste de la pile.
Appliqué à
- Deep Learning concept Algorithms Dropout used for Deep Learning High ✓ source
- Fine-tuning technique Techniques Dropout used for Fine-tuning High ✓ source
- Pretraining technique Techniques Dropout used for Pretraining High ✓ source
- Overfitting concept Algorithms Dropout solves Overfitting High ✓ source
Outils
Logiciels qui implémentent Dropout ou s'y intègrent.