Yoshua Bengio
Computer scientist
Université de Montréal and Mila
Canada
Yoshua Bengio is a researcher affiliated with Université de Montréal and Mila. This profile connects verified scholarly identity information and publication records from OpenAlex and DOI sources. Research areas include Neural Networks and Applications, Topic Modeling, Generative Adversarial Networks and Image Synthesis, Domain Adaptation and Few-Shot Learning, Natural Language Processing Techniques.
Read biography ↓Biography, research & contributions
Research profile
Yoshua Bengio is a computer scientist known for research in deep learning. He shared the 2018 ACM A. M. Turing Award with Geoffrey Hinton and Yann LeCun. The award recognised conceptual and engineering contributions that made deep neural networks central to many computing applications.
Source: ACM: the 2018 Turing Award ↗
Why learned representations matter
In a language model, many possible word sequences never occur in the training examples. Bengio and colleagues investigated learning a numerical representation for each word together with a model of word-sequence probabilities. Similar representations allow information from observed examples to help the model handle other combinations. This illustrates why learning features can be as important as fitting a predictor.
Source: Bengio and colleagues: A Neural Probabilistic Language Model ↗
Selected publication
A Neural Probabilistic Language Model appeared in the Journal of Machine Learning Research in 2003, coauthored with Réjean Ducharme, Pascal Vincent and Christian Jauvin. The paper describes its model, the computational challenge of training it, and comparisons with n-gram methods. It is a useful primary reading for understanding an early neural approach to language modelling.
Source: JMLR 3, 1137–1155 (2003) ↗
Related work and reading route
Bengio also coauthored the 1998 paper on gradient-based document recognition with Yann LeCun, Léon Bottou and Patrick Haffner. Reading these two works side by side shows neural learning applied to different kinds of data: sequences of words and images of written characters. They provide a more precise introduction to his research than a list of citation totals alone.
At a glance
- Full name
- Yoshua Bengio
- Fields
- Artificial Intelligence, Computer Science
- ORCID
- https://orcid.org/0000-0002-9322-3515
- OpenAlex ID
- A5086198262
Research interests
- Deep learning
- Representation learning
- Neural language models
Research topics
Education
Not yet documented in this profile.
Selected research & further reading
A curated reading list, not a ranking by citation count. References use DOI metadata, matching public scholarly records or authoritative lecture sources.
- Deep learning ↗2015 · NatureDOI: 10.1038/nature14539
Citation & publication trends
Annual counts are not yet available from a verified author record. Explore the research guide above for the work itself; publication and citation totals depend on database coverage.
Most-cited linked publications
- A Recurrent Latent Variable Model for Sequential Data2026-05-02 · arXiv (Cornell University)145record citations
- Identifying indicators of consciousness in AI systems2025-11-10 · Trends in Cognitive Sciences24record citations
- Deep-learning-based virtual screening of antibacterial compounds2025-10-24 · Nature Biotechnology12record citations
- International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management2025-11-25 · arXiv (Cornell University)1record citations
- International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management2025-12-07 · SuperIntelligence - Robotics - Safety & Alignment1record citations
Recent linked publications
- A Recurrent Latent Variable Model for Sequential Data2026-05-02 · arXiv (Cornell University)
- Sliding Window Recurrences for Sequence Models2025-12-15 · arXiv (Cornell University)
- International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management2025-12-07 · SuperIntelligence - Robotics - Safety & Alignment
- Adsorption energies are necessary but not sufficient to identify good catalysts2025-12-05 · arXiv (Cornell University)
Journals published in
Related publishers
Institutions
Current verified institution
No verified record links added yet.
Previous institutions
No verified record links added yet.
Awards & honors
- 2018 — ACM A. M. Turing Award, shared with Geoffrey Hinton and Yann LeCun
Career timeline
- 2018 — ACM A. M. Turing Award, shared with Geoffrey Hinton and Yann LeCun
Co-authors
Education & career institution links
No verified record links added yet.
Claim & manage this profile
Are you this researcher? Sign in, provide identity evidence, and request administrator approval. Editing becomes available only after approval.
Sign in to claim this profileSources & data information
Editorial review: 2026-10-03 · Last data update: 2026-10-03
- https://openalex.org/A5086198262
- https://awards.acm.org/binaries/content/assets/press-releases/2019/march/turing-award-2018.pdf
- https://www.jmlr.org/papers/v3/bengio03a.html
- https://leon.bottou.org/papers/lecun-98h
Unknown values are left blank. Linked publications may be a subset of total works. Identity verification, data retrieval and profile ownership are separate checks.
Portrait reuse license · Image resized for display.
Portrait: Xuthoria · CC BY-SA 4.0