Dropout regularization is the use of dropout during training to improve a neural network’s ability to generalize. It temporarily removes a random subset of units for a training step, effectively encouraging the network to behave like an ensemble of smaller models.
A form of regularization useful in training neural networks. Dropout regularization removes a random selection of a fixed number of the units in a network layer for a single gradient step. The more units dropped out, the stronger the regularization. This is analogous to training the network to emulate an exponentially large ensemble of smaller networks. For full details, see Dropout: A Simple Way to Prevent Neural Networks from Overfitting.