scispace - formally typeset
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

Martin Arjovsky, +2 more
- 20 Nov 2015 - 
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, +5 more
- 27 Nov 2016 - 
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

Joachim Ott, +4 more
- 24 Aug 2016 - 
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

Yoshua Bengio
- 01 Aug 1993 - 
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, +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.