deep learning papers

Papers

Dropout

Journal of Machine Learning Research 2014

[jmlr-dropout] Dropout: A Simple Way to Prevent Neural Networks from Overfitting [PDF] [notes]

Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov

Batchnorm

Journal of Machine Learning Research 2014

[jmlr-batchnorm] Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift [PDF] [notes]

Sergey Ioffe, Christian Szegedy

Autoencoders

Science 2006

science-autoencoder Reducing the Dimensionality of Data with Neural Networks [PDF] [notes]

Geoffrey Hinton, Ruslan Salakhutdinov

Notes

Convolutions

Dilated convolutions

about dilated convolutions and transposed convolutions

Loss functions

about loss functions

about l2 minimization and blurring