35 citations · 151 across the 21 of their papers we have counts for
Showing stat.MLShow 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.ML2015★ 13 cited
Why Regularized Auto-Encoders learn Sparse Representation?
Devansh Arpit, Yingbo Zhou, Hung Ngo +1
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solutio…