Translations:Dropout A Simple Way to Prevent Overfitting/5/en

Dropout provides an efficient approximation to model combination. During each training step, each neuron (including input units) is retained with a probability $ p $ and dropped (set to zero) with probability $ 1 - p $. This means that on each training case, a different "thinned" sub-network is sampled. At test time, all neurons are used but their outputs are scaled by $ p $ to approximate the expected output of the ensemble.