This is PaperWhy. Our sisyphean endeavour not to drown in the immense Machine Learning literature.

With thousands of papers every month, keeping up with and making sense of recent research in machine learning has become almost impossible. By routinely reviewing and reporting papers we help ourselves and hopefully someone else.

Paperwhy

22 Dec 18
Recurrent models of visual attention (2014)

Mnih Hees Graves Kavukcuoglu
21 Oct 17
Extrapolation and learning equations (2016)

Martius Lamport
06 Jul 17
Deep Residual Learning for image recognition (2016)

he Zhang Ren Sun
26 Jun 17
Batch normalization: accelerating deep network training by reducing internal... (2015)

Ioffe Szegedy
20 Jun 17
On the number of linear regions of deep neural networks (2014)

Montufar Pascanu Cho Bengio
12 Jun 17
Training with noise is equivalent to Tikhonov regularization (1995)

Bishop
07 Jun 17
Identity matters in Deep Learning (2016)

Hardt Ma
04 Jun 17
On gradient-based optimization: accelerated, stochastic, asynchronous,... (2017)

Jordan
31 May 17
Dropout training as adaptive regularization (2013)

Wager Wang Liang
29 May 17
Why and when can deep – but not shallow – networks avoid the curse of... (2016)

Poggio Mhaskar Rosasco Miranda Liao
23 May 17
Maxout Networks (2013)

Goodfellow Warde-Farley Mirza Courville Bengio
18 May 17
Deep sparse rectifier neural networks (2011)

Glorot Bordes Bengio
15 May 17
Deep Learning using linear Support Vector Machines (2013)

Tang
13 May 17
Why does deep and cheap learning work so well? (2016)

Lin Tegmark
10 May 17
Greedy layer-wise training of Deep Networks (2007)

Bengio Lamblin Popovici Larochelle

Newer Older