Yoshua Bengio

high confidence · 26 work(s) in this corpus · 476,665 citations across 1,232 works in OpenAlex · ORCID 0000-0002-9322-3515

24 of 82 collaborators, ranked by collaboration weight rather than by shared-paper count. Dashed lines are collaborations between the collaborators. See how the weight is computed.

Yoshua Bengio collaborator line weight = collaboration weight

Works in this corpus

Title	Position	Year	Cited
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation	last	2014	25,048
Neural Machine Translation by Jointly Learning to Align and Translate	last	2014	14,615
Understanding the difficulty of training deep feedforward neural networks	last	2010	12,673
Deep Learning	middle	2016	8,952
Learning long-term dependencies with gradient descent is difficult	first	1994	8,610
Graph Attention Networks	last	2017	8,400
Learning Deep Architectures for AI	first	2009	6,951
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches	last	2014	6,683
Deep Sparse Rectifier Neural Networks	last	2011	5,428
Curriculum learning	first	2009	5,154
Learning Deep Architectures for AI	first	2009	5,077
Proceedings of the 21st International Conference on Neural Information Processing Systems	middle	2008	4,492
On the difficulty of training Recurrent Neural Networks	last	2012	3,801
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation	last	2014	3,518
Algorithms for Hyper-Parameter Optimization	middle	2011	3,188
Why Does Unsupervised Pre-training Help Deep Learning?	middle	2010	2,114
Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation	first	2013	1,996
Practical Recommendations for Gradient-Based Training of Deep Architectures	first	2012	1,960
Word Representations: A Simple and General Method for Semi-Supervised Learning	last	2010	1,941
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering	middle	2018	1,743
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models	middle	2016	1,725
Challenges in Representation Learning: A Report on Three Machine Learning Contests	last	2013	1,588
Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach	last	2011	1,562
A Structured Self-attentive Sentence Embedding	last	2017	1,473
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations	last	2016	1,420
Learning deep representations by mutual information estimation and maximization	last	2018	1,393

Is this one person?

This record carries a person-claimed ORCID and no signal that it mixes two people.

supportsAn ORCID is claimed by a person, not inferred, so it is the only identity assertion here that a human made.
supports2 distinct name form(s) across this row's works, counting a spelled-out given name and its initial as one form.
supportsAt most 5 distinct institution(s) inside any five-year window, which is a normal career.
supports93% of this row's works sit in its single largest field.
neutralConfidence is judged on the 26 work(s) this corpus holds, not on the author's whole output. A single-work row carries little evidence either way.

Affiliations

Université de Montréal (1994–2016), Polytechnique Montréal (2014–2014), Constructor University (2014–2014), Alcatel Lucent (Germany) (2014–2014), Canadian Institute for Advanced Research (2014–2014), Queen's University (1994–1994), AT&T (United States) (1994–1994)

In this corpus

h-index 26 over the works held here, which is a number about this corpus and not about a career.

OpenAlex record