353 citations · 1.2k across the 32 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
stat.ML2016★ 1 cited
On Optimality Conditions for Auto-Encoder Signal Recovery
Devansh Arpit, Yingbo Zhou, Hung Q. Ngo +2
Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sp…
stat.ML2016★ 85 cited
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
Devansh Arpit, Yingbo Zhou, Bhargava U. Kota +1
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has cer…