• Publications
  • Influence
Extracting and composing robust features with denoising autoencoders
TLDR
We introduce 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. Expand
  • 4,294
  • 395
  • PDF
A Neural Probabilistic Language Model
TLDR
A goal of statistical language modeling is to learn the joint probability function of sequences of words in a language. Expand
  • 4,682
  • 343
  • PDF
Theano: A Python framework for fast computation of mathematical expressions
TLDR
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Expand
  • 1,873
  • 140
  • PDF
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
TLDR
We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Expand
  • 524
  • 62
  • PDF
Why Does Unsupervised Pre-training Help Deep Learning?
TLDR
We show that unsupervised pre-training guides the learning towards basins of attraction of minima that support better generalization from the training data set. Expand
  • 1,272
  • 32
  • PDF
A Variational Inequality Perspective on Generative Adversarial Nets
TLDR
We apply averaging, extrapolation and a computationally cheaper variant that we call extrapolation from the past to the stochastic gradient method (SGD) and Adam. Expand
  • 121
  • 27
  • PDF
Combining modality specific deep neural networks for emotion recognition in video
TLDR
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. Expand
  • 265
  • 16
  • PDF
Audio Chord Recognition with Recurrent Neural Networks
TLDR
In this paper, we present an audio chord recognition system based on a recurrent neural network that combines acoustic and musicological models under a unified training objective. Expand
  • 114
  • 10
  • PDF
EmoNets: Multimodal deep learning approaches for emotion recognition in video
TLDR
The task of the Emotion Recognition in the Wild (EmotiW) Challenge is to assign one of seven emotions to short video clips extracted from Hollywood style movies. Expand
  • 246
  • 7
  • PDF
High-dimensional sequence transduction
TLDR
We introduce a probabilistic model based on a recurrent neural network that is able to learn realistic output distributions given the input and we devise an efficient algorithm to search for the global mode of that distribution. Expand
  • 53
  • 6
  • PDF