Extracting and composing robust features with denoising autoencoders
- Pascal Vincent, H. Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol
- Computer ScienceInternational Conference on Machine Learning
- 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.
A Neural Probabilistic Language Model
- Yoshua Bengio, Réjean Ducharme, Pascal Vincent, Christian Janvin
- Computer ScienceJournal of machine learning research
- 1 March 2003
This work proposes to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences.
Theano: A Python framework for fast computation of mathematical expressions
- Rami Al-Rfou, Guillaume Alain, Ying Zhang
- Computer ScienceArXiv
- 9 May 2016
The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.
Why Does Unsupervised Pre-training Help Deep Learning?
- D. Erhan, Aaron C. Courville, Yoshua Bengio, Pascal Vincent
- Computer ScienceInternational Conference on Artificial…
- 1 March 2010
The results suggest that unsupervised pre-training guides the learning towards basins of attraction of minima that support better generalization from the training data set; the evidence from these results supports a regularization explanation for the effect of pre- training.
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
- Nicolas Boulanger-Lewandowski, Yoshua Bengio, Pascal Vincent
- Computer ScienceInternational Conference on Machine Learning
- 26 June 2012
A probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences that outperforms many traditional models of polyphonic music on a variety of realistic datasets is introduced.
A Variational Inequality Perspective on Generative Adversarial Nets
- Gauthier Gidel, Hugo Berard, Pascal Vincent, S. Lacoste-Julien
- Computer ScienceInternational Conference on Learning…
- 28 February 2018
This work applies averaging, extrapolation and a computationally cheaper variant that is called extrapolation from the past to the stochastic gradient method (SGD) and Adam and proposes to extend techniques designed for variational inequalities to the training of GANs.
Combining modality specific deep neural networks for emotion recognition in video
- S. Kahou, C. Pal, Zhenzhou Wu
- Computer ScienceInternational Conference on Multimodal…
- 9 December 2013
In this paper we present the techniques used for the University of Montréal's team submissions to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the emotions…
Audio Chord Recognition with Recurrent Neural Networks
- Nicolas Boulanger-Lewandowski, Yoshua Bengio, Pascal Vincent
- Computer ScienceInternational Society for Music Information…
- 2013
An efficient algorithm to search for the global mode of the output distribution while taking long-term dependencies into account is devised and the resulting method is competitive with state-of-the-art approaches on the MIREX dataset in the major/minor prediction task.
Masked Siamese Networks for Label-Efficient Learning
- Mahmoud Assran, Mathilde Caron, Nicolas Ballas
- Computer ScienceEuropean Conference on Computer Vision
- 14 April 2022
This work proposes Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations that improves the scalability of joint-embedding architectures, while producing representations of a high semantic level that perform competitively on low-shot image classification.
EmoNets: Multimodal deep learning approaches for emotion recognition in video
- S. Kahou, Xavier Bouthillier, Yoshua Bengio
- Computer ScienceJournal on Multimodal User Interfaces
- 5 March 2015
This paper explores multiple methods for the combination of cues from these modalities into one common classifier, which achieves a considerably greater accuracy than predictions from the strongest single-modality classifier.
...
...