• Publications
  • Influence
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
TLDR
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks, but it becomes unwieldy when learning large datasets, so Mean Teacher, a method that averages model weights instead of label predictions, is proposed.
Semi-supervised Learning with Ladder Networks
TLDR
This work builds on top of the Ladder network proposed by Valpola which is extended by combining the model with supervision and shows that the resulting model reaches state-of-the-art performance in semi-supervised MNIST and CIFAR-10 classification in addition to permutation-invariant MNIST classification with all labels.
Denoising Source Separation
TLDR
In the experimental section, various DSS schemes are applied extensively to artificial data, to real magnetoencephalograms and to simulated CDMA mobile network signals, and DSS appears to have relevance to many existing models of neural information processing.
Semi-Supervised Learning with Ladder Network
TLDR
This work builds on top of the Ladder network proposed by Valpola (2015) which is extended by combining the model with supervision, and shows that the resulting model reaches state-of-the-art performance in various tasks.
An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models
TLDR
Experiments with chaotic data show that the new Bayesian ensemble learning method is able to blindly estimate the factors and the dynamic process that generated the data and clearly outperforms currently available nonlinear prediction techniques in this very difficult test problem.
Tagger: Deep Unsupervised Perceptual Grouping
TLDR
This work presents a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features and greatly improves on the semi-supervised result of a baseline Ladder network on the authors' dataset, indicating that segmentation can also improve sample efficiency.
Deep Learning Made Easier by Linear Transformations in Perceptrons
TLDR
The usefulness of the transformations are confirmed, which make basic stochastic gradient learning competitive with state-of-the-art learning algorithms in speed and that they seem also to help find solutions that generalize better.
On-line Variational Bayesian Learning
TLDR
This paper presents an on-line variant of variational Bayesian learning based on collecting likelihood information as the training samples are processed one at a time and decaying the old likelihood information.
On the Effect of the Form of the Posterior Approximation in Variational Learning of ICA Models
We show that the choice of posterior approximation affects the solution found in Bayesian variational learning of linear independent component analysis models. Assuming the sources to be independent
...
1
2
3
4
5
...