🧑‍🔬 Geoffrey E. Hinton

🏛️ Affiliations

🎓University of TorontoToronto · Canada1987–2026 · 194 paperscurrent🏢MicrosoftRedmond · United States2026 · 2 paperscurrent🏢GoogleMountain View · United States2014–2023 · 33 papers🎓University College LondonLondon · United Kingdom1999–2013 · 23 papers🔬Gatsby Computational Neuroscience UnitLondon · United Kingdom1999–2013 · 20 papers🎓Carnegie Mellon UniversityPittsburgh · United States1983–1988 · 19 papers🔬Canadian Institute for Advanced ResearchToronto · Canada1989–2005 · 7 papers🔬Vector InstituteToronto · Canada2019–2024 · 6 papers🏢Google DeepMindLondon · United Kingdom2016–2023 · 3 papers🎓University of California San DiegoSan Diego · United States1979–1980 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Distilling the Knowledge in a Neural Network (2015 · 15,229 citations)
   Averaging many models or training one huge, heavily regularized net gives strong accuracy, but such systems are too slow and expensive to serve to many users.
2. A Simple Framework for Contrastive Learning of Visual Representations (2020 · 8,000 citations)
   The paper asks how far a deliberately plain recipe can take self-supervised image representation learning.
3. ImageNet Classification with Deep Convolutional Neural Networks (2012 · 2,801 citations)
   The authors worked on image classification from the ImageNet LSVRC-2010 contest. The training set contained about 1.2 million photographs in 1000 classes. They built a deep convolutional network (CNN) with five convolutional and three fully connected layers. The network has approximately 60 million parameters. To…
4. Layer Normalization (2016 · 1,819 citations)
   Batch normalization speeds up training of deep networks, but it estimates its statistics from the mini-batch.
5. Similarity of Neural Network Representations Revisited (2019 · 679 citations)
   The paper asks how to tell whether two neural network layers, inside one model or across separately trained models, encode the same information.
6. Regularizing Neural Networks by Penalizing Confident Output Distributions (2017 · 496 citations)
   Most regularizers for deep networks work on weights or hidden activations. This paper regularizes the output distribution instead. The authors add a confidence penalty to the training loss: the negative log-likelihood minus β times the entropy of the softmax prediction, which discourages overly peaked outputs. They…

All works

66 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. Dropout: A Simple Way to Prevent Neural Networks from Overfitting ↗JMLR 15(56):1929–1958 · no summary yetNitish Srivastava et al.2014 · 34,422 citations
2. Reducing the Dimensionality of Data with Neural Networks ↗Science · no summary yetGeoffrey E. Hinton, Ruslan Salakhutdinov2006 · 21,029 citations
3. Distilling the Knowledge in a Neural NetworkarXiv:1503.02531Geoffrey Hinton, Oriol Vinyals, Jeff Dean2015 · 15,229 citations
4. Speech recognition with deep recurrent neural networks ↗IEEE International Conference on Acoustics Speech and Signal Processing · no summary yetAlex Graves, Abdelrahman Mohamed, Geoffrey E. Hinton2013 · 8,998 citations
5. A Simple Framework for Contrastive Learning of Visual RepresentationsarXiv:2002.05709Ting Chen, Simon Kornblith, Mohammad Norouzi, et al.2020 · 8,000 citations
6. Improving neural networks by preventing co-adaptation of feature detectors ↗arXiv:1207.0580 · no summary yetGeoffrey E. Hinton et al.2012 · 6,645 citations
7. ImageNet Classification with Deep Convolutional Neural NetworksNeurIPS 2012Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton2012 · 2,801 citations
8. Restricted Boltzmann machines for collaborative filtering ↗International Conference on Machine Learning · no summary yetRuslan Salakhutdinov, Andriy Mnih, Geoffrey E. Hinton2007 · 1,865 citations
9. Layer NormalizationarXiv:1607.06450Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton2016 · 1,819 citations
10. Deep Boltzmann machines ↗no summary yetRuslan Salakhutdinov, Geoffrey E. Hinton2009 · 1,728 citations
11. Neighbourhood Components Analysis ↗no summary yetJacob Goldberger et al.2004 · 1,676 citations
12. The Helmholtz Machine ↗Neural Computation · no summary yetPeter Dayan et al.1995 · 1,202 citations
13. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer ↗arXiv:1701.06538 · no summary yetNoam Shazeer et al.2017 · 1,111 citations
14. Autoencoders, Minimum Description Length and Helmholtz Free Energy ↗no summary yetGeoffrey E. Hinton, Richard S. Zemel1993 · 1,073 citations
15. Grammar as a Foreign Language ↗arXiv:1412.7449 · no summary yetOriol Vinyals et al.2014 · 687 citations
16. Similarity of Neural Network Representations RevisitedarXiv:1905.00414Simon Kornblith, Mohammad Norouzi, Honglak Lee, et al.2019 · 679 citations
17. A Simple Way to Initialize Recurrent Networks of Rectified Linear Units ↗arXiv (Cornell University) · no summary yetQuoc Viet Le, Navdeep Jaitly, Geoffrey E. Hinton2015 · 571 citations
18. Regularizing Neural Networks by Penalizing Confident Output DistributionsarXiv:1701.06548Gabriel Pereyra, George Tucker, Jan Chorowski, et al.2017 · 496 citations
19. An Efficient Learning Procedure for Deep Boltzmann Machines ↗Neural Computation · no summary yetRuslan Salakhutdinov, Geoffrey E. Hinton2012 · 485 citations
20. Replicated Softmax: an Undirected Topic Model ↗neural information processing systems · no summary yetGeoffrey E. Hinton, Ruslan Salakhutdinov2009 · 443 citations
21. On rectified linear units for speech processing ↗IEEE International Conference on Acoustics Speech and Signal Processing · no summary yetMatthew D. Zeiler et al.2013 · 440 citations
22. Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure ↗no summary yetRuslan Salakhutdinov, Geoffrey E. Hinton2007 · 434 citations
23. Exponential Family Harmoniums with an Application to Information Retrieval ↗no summary yetMax Welling, Michal Rosen‐Zvi, Geoffrey E. Hinton2004 · 413 citations
24. Managing extreme AI risks amid rapid progress ↗Science · no summary yetYoshua Bengio et al.2024 · 382 citations
25. Lookahead Optimizer: k steps forward, 1 step back ↗arXiv (Cornell University) · no summary yetMichael R. Zhang et al.2019 · 380 citations

See all 66 works by Geoffrey E. Hinton →

🤝 Co-authors here

11 co-authors with a page, the most papers together first.

• Mohammad Norouzi ×2
• Simon Kornblith ×2
• Honglak Lee
• Ilya Sutskever
• Jamie Kiros
• Jan Chorowski
• Jeff Dean
• Jimmy Lei Ba
• Łukasz Kaiser
• Oriol Vinyals
• Ting Chen

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Neural Computation ×5
• neural information processing systems ×4
• International Conference on Machine Learning ×3
• IEEE International Conference on Acoustics Speech and Signal Processing ×2
• Science ×2
• Cognitive Science
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
• IEEE Transactions on Neural Networks
• JMLR 15(56):1929–1958
• Lecture notes in computer science
• NeurIPS 2012
• The MIT Press eBooks

🔗 Cited by

Papers of our library cite their works 11,868 times (of the 149,439 papers whose bibliographies we read); 1,026 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/geoffrey-e-hinton/