Dropout Training as Adaptive Regularization
NIPS, pp. 351-359, 2013.
Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout regularizer is first-order equivalent to an L2 regularizer applied after scaling the features by an ...More
PPT (Upload PPT)