150 citations · 832 across the 25 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2015★ 96 cited
Dropout as data augmentation
Xavier Bouthillier, Kishore Konda, Pascal Vincent +1
Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentat…
stat.ML2014★ 37 cited
Zero-bias autoencoders and the benefits of co-adapting features
Kishore Konda, Roland Memisevic, David Krueger
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidd…