At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. Nitish Srivastava, et al., "Dropout: A Simple Way to Prevent…

During training, dropout samples from an exponential number of different “thinned” networks. Nitish Srivastava, et al., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting" http://jmlr.org/papers/volume15/srivastava14a/sriva…

This prevents units from co-adapting too much. Nitish Srivastava, et al., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting" http://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf ノードをランダムに消去しながら学…

The key idea is to randomly drop units (along with their connections) from the neural network during training. Nitish Srivastava, et al., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting" http://jmlr.org/papers/volume15/s…