Share This Author
Domain-Adversarial Training of Neural Networks
A new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions, which can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer.
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
- Pascal Vincent, H. Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol
- Computer ScienceJ. Mach. Learn. Res.
- 1 March 2010
This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.
Extracting and composing robust features with denoising autoencoders
- Pascal Vincent, H. Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol
- Computer ScienceICML '08
- 5 July 2008
This work introduces and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern.
Practical Bayesian Optimization of Machine Learning Algorithms
This work describes new algorithms that take into account the variable cost of learning algorithm experiments and that can leverage the presence of multiple cores for parallel experimentation and shows that these proposed algorithms improve on previous automatic procedures and can reach or surpass human expert-level optimization for many algorithms.
Optimization as a Model for Few-Shot Learning
Greedy Layer-Wise Training of Deep Networks
These experiments confirm the hypothesis that the greedy layer-wise unsupervised training strategy mostly helps the optimization, by initializing weights in a region near a good local minimum, giving rise to internal distributed representations that are high-level abstractions of the input, bringing better generalization.
Autoencoding beyond pixels using a learned similarity metric
- Anders Boesen Lindbo Larsen, Søren Kaae Sønderby, H. Larochelle, O. Winther
- Computer ScienceICML
- 31 December 2015
An autoencoder that leverages learned representations to better measure similarities in data space is presented and it is shown that the method learns an embedding in which high-level abstract visual features (e.g. wearing glasses) can be modified using simple arithmetic.
Describing Videos by Exploiting Temporal Structure
- L. Yao, Atousa Torabi, Aaron C. Courville
- Computer ScienceIEEE International Conference on Computer Vision…
- 27 February 2015
This work proposes an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions and proposes a temporal attention mechanism that allows to go beyond local temporal modeling and learns to automatically select the most relevant temporal segments given the text-generating RNN.
Meta-Learning for Semi-Supervised Few-Shot Classification
This work proposes novel extensions of Prototypical Networks that are augmented with the ability to use unlabeled examples when producing prototypes, and confirms that these models can learn to improve their predictions due to unlabeling examples, much like a semi-supervised algorithm would.
An empirical evaluation of deep architectures on problems with many factors of variation
- H. Larochelle, D. Erhan, Aaron C. Courville, J. Bergstra, Yoshua Bengio
- Computer ScienceICML '07
- 20 June 2007
A series of experiments indicate that these models with deep architectures show promise in solving harder learning problems that exhibit many factors of variation.