1.6k citations · 2.2k across the 16 of their papers we have counts for
5 papers · 1 filter
On the exact relationship between the denoising function and the data distribution
Heikki Arponen, Matti Herranen, Harri Valpola
We prove an exact relationship between the optimal denoising function and the data distribution in the case of additive Gaussian noise, showing that denoising implicitly models the…
Recurrent Ladder Networks
Isabeau Prémont-Schwarz, Alexander Ilin, Tele Hotloo Hao +3
We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models. We demonstrate that the recur…
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
Antti Tarvainen, Harri Valpola
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label…
Semi-Supervised Learning with Ladder Networks
Antti Rasmus, Harri Valpola, Mikko Honkala +2
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised c…
Denoising autoencoder with modulated lateral connections learns invariant representations of natural images
Antti Rasmus, Tapani Raiko, Harri Valpola
Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoenc…