A training trick that randomly turns off some neurons to reduce overfitting.
Dropout is like a coach benching random players at practice. Now everyone must learn the play.
In neural-network training, it turns off some neurons for a moment. This helps the model avoid overfitting and plain old memorizing.
Regularization
Dropout is a Regularization method. It randomly turns neurons off to fight overfitting.
Neural-network
Dropout turns off some neurons during Neural-network training.
Weight Decay
Both fight overfitting: Dropout turns neurons off, Weight Decay keeps weights small.
AlexNet
AlexNet used Dropout to reduce overfitting and made it famous.