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
Unitary Evolution Recurrent Neural Networks
TL;DR: In this article, the authors propose a new architecture that learns a unitary weight matrix, with eigenvalues of absolute value exactly 1, which does not require expensive computations after each weight update.
Posted Content
Invariant Representations for Noisy Speech Recognition.
Dmitriy Serdyuk,Kartik Audhkhasi,Philemon Brakel,Bhuvana Ramabhadran,Samuel Thomas,Yoshua Bengio +5 more
TL;DR: This work focuses on investigating neural architectures which produce representations invariant to noise conditions for ASR, and evaluates the proposed architecture on the Aurora-4 task, a popular benchmark for noise robust ASR.
Posted Content
Recurrent Neural Networks With Limited Numerical Precision
TL;DR: This paper addresses the question of how to best reduce weight precision during training in the case of RNNs by presenting results from the use of different stochastic and deterministic reduced precision training methods applied to three major RNN types which are then tested on several datasets.
Journal ArticleDOI
A connectionist approach to speech recognition
TL;DR: Different architectures for sequence and speech recognition are reviewed, including recurrent networks as well as hybrid systems involving hidden Markov models, sometimes combined with statistical techniques for recognition of sequences of patterns.
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Iulian Vlad Serban,Alessandro Sordoni,Ryan Lowe,Laurent Charlin,Joelle Pineau,Aaron Courville,Yoshua Bengio +6 more
TL;DR: This paper proposed a neural network-based generative architecture with stochastic latent variables that span a variable number of time steps to generate meaningful, long and diverse responses and maintain dialogue state.