81 citations · 196 across the 8 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
cs.LG2016★ 4 cited
Mollifying Networks
Caglar Gulcehre, Marcin Moczulski, Francesco Visin +1
The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e.g. it can…
cs.LG2016★ 81 cited
Noisy Activation Functions
Caglar Gulcehre, Marcin Moczulski, Misha Denil +1
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies…