Y
Yoshua Bengio
Researcher at Université de Montréal
Publications - 1146
Citations - 534376
Yoshua Bengio is an academic researcher from Université de Montréal. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 202, co-authored 1033 publications receiving 420313 citations. Previous affiliations of Yoshua Bengio include McGill University & Centre de Recherches Mathématiques.
Papers
More filters
Posted Content
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
TL;DR: GraphMix is presented, a regularization method for Graph Neural Network based semi-supervised object classification, whereby it is proposed to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization.
Posted Content
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
TL;DR: Nguyen et al. as mentioned in this paper proposed a Plug and Play Generative Network (PPGN) to generate high-resolution, photo-realistic images with an additional prior on the latent code.
Posted Content
Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks
TL;DR: Experiments show that the proposed improved self-supervised method can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues.
Posted Content
Pointing the Unknown Words
TL;DR: A novel way to deal with the rare and unseen words for the neural network models using attention is proposed using attention, which uses two softmax layers in order to predict the next word in conditional language models.
Posted Content
End-to-End Attention-based Large Vocabulary Speech Recognition
TL;DR: In this article, the HMM is replaced with a Recurrent Neural Network (RNN) that performs sequence prediction directly at the character level, where alignment between the input features and the desired character sequence is learned automatically by an attention mechanism built into the RNN.