Yoshua Bengio

447.2k total citations · 48 hit papers
412 papers, 192.7k citations indexed

About

Yoshua Bengio is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Signal Processing. According to data from OpenAlex, Yoshua Bengio has authored 412 papers receiving a total of 192.7k indexed citations (citations by other indexed papers that have themselves been cited), including 299 papers in Artificial Intelligence, 160 papers in Computer Vision and Pattern Recognition and 57 papers in Signal Processing. Recurrent topics in Yoshua Bengio's work include Neural Networks and Applications (103 papers), Generative Adversarial Networks and Image Synthesis (62 papers) and Topic Modeling (57 papers). Yoshua Bengio is often cited by papers focused on Neural Networks and Applications (103 papers), Generative Adversarial Networks and Image Synthesis (62 papers) and Topic Modeling (57 papers). Yoshua Bengio collaborates with scholars based in Canada, United States and United Kingdom. Yoshua Bengio's co-authors include Yann LeCun, Geoffrey E. Hinton, Léon Bottou, Patrick Haffner, Aaron Courville, Xavier Glorot, Ian Goodfellow, Pascal Vincent, James Bergstra and Hugo Larochelle and has published in prestigious journals such as Nature, Science and The Journal of Chemical Physics.

In The Last Decade

Yoshua Bengio

398 papers receiving 184.5k citations

Hit Papers

Deep learning 1994 2026 2004 2015 2015 1998 2020 2010 2013 10.0k 20.0k 30.0k 40.0k 50.0k
What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

  1. Deep learning
    2015 53.7k citations Yoshua Bengio et al. profile →
  2. Gradient-based learning applied to document recognition
    1998 34.5k citations Yoshua Bengio et al. profile →
  3. Generative adversarial networks
    2020 8.1k citations Ian Goodfellow, Aaron Courville et al. profile →
  4. Understanding the difficulty of training deep feedforward neural networks
    2010 7.8k citations Xavier Glorot, Yoshua Bengio profile →
  5. Representation Learning: A Review and New Perspectives
    2013 7.7k citations Yoshua Bengio, Aaron Courville et al. profile →
  6. Deep Learning
    2016 5.8k citations Ian Goodfellow, Yoshua Bengio et al. MIT Press eBooks profile →
  7. Random search for hyper-parameter optimization
    2012 5.5k citations James Bergstra, Yoshua Bengio profile →
  8. Learning long-term dependencies with gradient descent is difficult
    1994 5.5k citations Yoshua Bengio et al. profile →
  9. Learning Deep Architectures for AI
    2009 4.8k citations Yoshua Bengio profile →
  10. Extracting and composing robust features with denoising autoencoders
    2008 4.4k citations Pascal Vincent, Yoshua Bengio et al. profile →
  11. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
    2015 4.2k citations Kyunghyun Cho, Aaron Courville et al. arXiv (Cornell University) profile →
  12. Proceedings of the 21st International Conference on Neural Information Processing Systems
    2008 3.6k citations Yoshua Bengio et al. profile →
  13. Learning Deep Architectures for AI
    2009 3.4k citations Yoshua Bengio profile →
  14. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
    2010 3.3k citations Pascal Vincent, Yoshua Bengio et al. profile →
  15. Curriculum learning
    2009 2.6k citations Yoshua Bengio et al. profile →
  16. How transferable are features in deep neural networks?
    2014 2.3k citations Yoshua Bengio et al. arXiv (Cornell University) profile →
  17. Brain tumor segmentation with Deep Neural Networks
    2016 2.1k citations Aaron Courville, Yoshua Bengio et al. profile →
  18. Why Does Unsupervised Pre-training Help Deep Learning?
    2010 1.4k citations Aaron Courville, Yoshua Bengio et al. profile →
  19. Word Representations: A Simple and General Method for Semi-Supervised Learning
    2010 1.2k citations Yoshua Bengio et al. profile →
  20. The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
    2017 1.1k citations Yoshua Bengio et al. profile →
  21. Exploring Strategies for Training Deep Neural Networks
    2009 758 citations Yoshua Bengio et al. profile →
  22. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
    2018 732 citations Zhilin Yang, Peng Qi et al. profile →
  23. Machine learning for combinatorial optimization: A methodological tour d'horizon
    2021 719 citations Yoshua Bengio, Andrea Lodi et al. profile →
  24. Theano: A CPU and GPU Math Compiler in Python
    2010 686 citations James Bergstra, Guillaume Desjardins et al. profile →
  25. A Neural Probabilistic Language Model
    2000 678 citations Yoshua Bengio, Pascal Vincent et al. profile →
  26. Contractive Auto-Encoders: Explicit Invariance During Feature Extraction
    2011 675 citations Salah Rifai, Pascal Vincent et al. International Conference on Machine Learning profile →
  27. An empirical evaluation of deep architectures on problems with many factors of variation
    2007 665 citations Aaron Courville, James Bergstra et al. profile →
  28. Scaling learning algorithms towards AI
    2007 617 citations Yoshua Bengio et al. profile →
  29. Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering
    2003 599 citations Yoshua Bengio, Pascal Vincent et al. profile →
  30. Semi-supervised Learning by Entropy Minimization
    2004 527 citations Yoshua Bengio et al. Neural Information Processing Systems profile →
  31. Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
    2008 527 citations Yoshua Bengio et al. profile →
  32. Toward Causal Representation Learning
    2021 519 citations Bernhard Schölkopf, Anirudh Goyal et al. profile →
  33. Deep Learning of Representations for Unsupervised and Transfer Learning.
    2011 517 citations Yoshua Bengio International Conference on Machine Learning profile →
  34. No Unbiased Estimator of the Variance of K-Fold Cross-Validation
    2003 513 citations Yoshua Bengio et al. profile →
  35. On Using Very Large Target Vocabulary for Neural Machine Translation
    2015 465 citations Sébastien Jean, Kyunghyun Cho et al. profile →
  36. Hierarchical Probabilistic Neural Network Language Model.
    2005 450 citations Yoshua Bengio et al. profile →
  37. Classification using discriminative restricted Boltzmann machines
    2008 449 citations Yoshua Bengio et al. profile →
  38. A semantic matching energy function for learning with multi-relational data
    2013 416 citations Xavier Glorot, Yoshua Bengio et al. profile →
  39. How to Construct Deep Recurrent Neural Networks
    2014 400 citations Yoshua Bengio et al. International Conference on Learning Representations profile →
  40. Maxout Networks
    2013 380 citations Ian Goodfellow, Aaron Courville et al. profile →
  41. Deep learning for AI
    2021 355 citations Yoshua Bengio et al. profile →
  42. A closer look at memorization in deep networks
    2017 344 citations Tegan Maharaj, Aaron Courville et al. profile →
  43. An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
    2014 341 citations Ian Goodfellow, Aaron Courville et al. arXiv (Cornell University) profile →
  44. BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
    2016 318 citations Yoshua Bengio et al. arXiv (Cornell University) profile →
  45. Mutual Information Neural Estimation.
    2018 302 citations Yoshua Bengio, Aaron Courville et al. International Conference on Machine Learning profile →
  46. A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion
    2015 270 citations Yoshua Bengio et al. profile →
  47. Light Gated Recurrent Units for Speech Recognition
    2018 267 citations Yoshua Bengio et al. profile →
  48. Inductive biases for deep learning of higher-level cognition
    2022 129 citations Anirudh Goyal, Yoshua Bengio profile →

Peers

Yoshua Bengio
Comparison fields: 5 of 241
  • Artificial Intelligence 80.5k
  • Computer Vision and Pattern Recognition 61.3k
  • Electrical and Electronic Engineering 18.6k
  • Signal Processing 15.1k
  • Radiology, Nuclear Medicine and Imaging 13.3k
Replace Yann LeCun with:
Yann LeCun United States
Geoffrey E. Hinton Canada
Shaoqing Ren China
Xiangyu Zhang China
Vladimir Vapnik United States
Kaiming He China
Ilya Sutskever Canada
Jürgen Schmidhuber Switzerland
Andrew Zisserman United Kingdom
Yann LeCun United States View profile →
Citations per field, relative to Yoshua Bengio
Yoshua Bengio · 1×
Citations per year, relative to Yoshua Bengio
Yoshua Bengio · 1×

Countries citing papers authored by Yoshua Bengio

Since Specialization
Citations

This map shows the geographic impact of Yoshua Bengio's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Yoshua Bengio with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Yoshua Bengio more than expected).

Fields of papers citing papers by Yoshua Bengio

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Yoshua Bengio. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Yoshua Bengio. The network helps show where Yoshua Bengio may publish in the future.

Co-authorship network of co-authors of Yoshua Bengio

This figure shows the co-authorship network connecting the top 25 collaborators of Yoshua Bengio. A scholar is included among the top collaborators of Yoshua Bengio based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Yoshua Bengio. Yoshua Bengio is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
# Work Indexed citations
1
Government Interventions to Avert Future Catastrophic AI Risks
2024 ·SHILAP Revista de lepidopterología ·Yoshua Bengio
4
2
Sources of richness and ineffability for phenomenally conscious states
2024 ·Neuroscience of Consciousness ·(unknown), (unknown), George Deane, Axel Constant, Guillaume Dumas, Guillaume Lajoie, Jonathan Simon, Yoshua Bengio
5
3
Towards equilibrium molecular conformation generation with GFlowNets
2024 ·Digital Discovery ·(unknown), Michał Koziarski, Álex Hernández-García, Chenghao Liu, Santiago Miret, Pablo Lemos, (unknown), (unknown), Alán Aspuru‐Guzik, Yoshua Bengio
0
4
Proactive Contact Tracing
2023 ·SHILAP Revista de lepidopterología ·(unknown), Tegan Maharaj, (unknown), Nasim Rahaman, Hannah Alsdurf, Nanor Minoyan, (unknown), Joanna Merckx, (unknown), Victor Schmidt, Pierre-Luc St-Charles, (unknown), (unknown), David L. Buckeridge, Christopher Pal, Bernhard Schölkopf, Yoshua Bengio
7
5
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
2022 ·arXiv (Cornell University) ·Eric Larsen, (unknown), Yoshua Bengio, Emma Frejinger, Simon Lacoste-Julien, Andrea Lodi
21
6
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
2020 ·International Conference on Learning Representations ·Anirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio
2
7
Online continual learning with no task boundaries.
2019 ·arXiv (Cornell University) ·Rahaf Aljundi, Min Lin, (unknown), Yoshua Bengio
13
8
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering breakdown →
2018 ·Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, Christopher D. Manning
732
9
FigureQA: An Annotated Figure Dataset for Visual Reasoning
2017 ·International Conference on Learning Representations ·Samira Ebrahimi Kahou, (unknown), Vincent Michalski, Ákos Kádár, Adam Trischler, Yoshua Bengio
6
10
Deep Learning breakdown →
2016 ·MIT Press eBooks ·Ian Goodfellow, Yoshua Bengio, Aaron Courville
5794
11
Architectural Complexity Measures of Recurrent Neural Networks
2016 ·Neural Information Processing Systems ·Saizheng Zhang, Yuhuai Wu, Tong Che, Zhouhan Lin, Roland Memisevic, Russ R. Salakhutdinov, Yoshua Bengio
16
12
On Using Very Large Target Vocabulary for Neural Machine Translation breakdown →
2015 ·Sébastien Jean, Kyunghyun Cho, Roland Memisevic, Yoshua Bengio
465
13
Marginalized Denoising Auto-encoders for Nonlinear Representations
2014 ·International Conference on Machine Learning ·Minmin Chen, Kilian Q. Weinberger, Fei Sha, Yoshua Bengio
72
14
On Tracking The Partition Function
2011 ·Neural Information Processing Systems ·Guillaume Desjardins, Yoshua Bengio, Aaron Courville
11
15
Contractive Auto-Encoders: Explicit Invariance During Feature Extraction breakdown →
2011 ·International Conference on Machine Learning ·Salah Rifai, Pascal Vincent, Xavier Muller, Xavier Glorot, Yoshua Bengio
675
16
Unsupervised Models of Images by Spike-and-Slab RBMs
2011 ·International Conference on Machine Learning ·Yoshua Bengio, Aaron Courville, James Bergstra
38
17
Shallow vs. Deep Sum-Product Networks
2011 ·Neural Information Processing Systems ·Olivier Delalleau, Yoshua Bengio
122
18
Training Methods for Adaptive Boosting of Neural Networks
1997 ·Neural Information Processing Systems ·Holger Schwenk, Yoshua Bengio
28
19
On the generalization capability of multi-layered networks in the extraction of speech properties
1989 ·Renato De Mori, Yoshua Bengio, Piero Cosi
2
20
A Neural Network to Detect Homologies in Proteins
1989 ·Neural Information Processing Systems ·Yoshua Bengio, Samy Bengio, Yannick Pouliot, (unknown)
1

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Breakdown of academic impact, for papers by Yann LeCun Breakdown of academic impact, for papers by Geoffrey E. Hinton Breakdown of academic impact, for papers by Shaoqing Ren Breakdown of academic impact, for papers by Xiangyu Zhang Breakdown of academic impact, for papers by Vladimir Vapnik Breakdown of academic impact, for papers by Kaiming He Breakdown of academic impact, for papers by Ilya Sutskever Breakdown of academic impact, for papers by Jürgen Schmidhuber Breakdown of academic impact, for papers by Andrew Zisserman
Rankless by CCL
2026