---
title: "Geoffrey E. Hinton — all works — Elamur Research"
description: "All 66 works of Geoffrey E. Hinton in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/geoffrey-e-hinton/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/geoffrey-e-hinton/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Geoffrey E. Hinton](https://md.research.elamur.ai/free/en/authors/geoffrey-e-hinton/) / all works

# Geoffrey E. Hinton — all works

66 works · [← Geoffrey E. Hinton](https://md.research.elamur.ai/free/en/authors/geoffrey-e-hinton/)

1. **[Dropout: A Simple Way to Prevent Neural Networks from Overfitting ↗](https://jmlr.org/papers/v15/srivastava14a.html) JMLR 15(56):1929–1958 · no summary yet**Nitish Srivastava et al.*2014 · 34,422 citations*
2. **[Reducing the Dimensionality of Data with Neural Networks ↗](https://doi.org/10.1126/science.1127647) Science · no summary yet**Geoffrey E. Hinton, Ruslan Salakhutdinov*2006 · 21,029 citations*
3. [**Distilling the Knowledge in a Neural Network arXiv:1503.02531**Geoffrey Hinton, Oriol Vinyals, Jeff Dean*2015 · 15,229 citations*](https://md.research.elamur.ai/free/en/papers/hinton-2015-distilling-knowledge-neural-network/)
4. **[Speech recognition with deep recurrent neural networks ↗](https://doi.org/10.1109/icassp.2013.6638947) IEEE International Conference on Acoustics Speech and Signal Processing · no summary yet**Alex Graves, Abdelrahman Mohamed, Geoffrey E. Hinton*2013 · 8,998 citations*
5. [**A Simple Framework for Contrastive Learning of Visual Representations arXiv:2002.05709**Ting Chen, Simon Kornblith, Mohammad Norouzi, et al.*2020 · 8,000 citations*](https://md.research.elamur.ai/free/en/papers/chen-2020-simple-framework-contrastive-learning-visual/)
6. **[Improving neural networks by preventing co-adaptation of feature detectors ↗](https://arxiv.org/abs/1207.0580) arXiv:1207.0580 · no summary yet**Geoffrey E. Hinton et al.*2012 · 6,645 citations*
7. [**ImageNet Classification with Deep Convolutional Neural Networks NeurIPS 2012**Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton*2012 · 2,801 citations*](https://md.research.elamur.ai/free/en/papers/krizhevsky-2012-imagenet-classification-deep-convolutional/)
8. **[Restricted Boltzmann machines for collaborative filtering ↗](https://doi.org/10.1145/1273496.1273596) International Conference on Machine Learning · no summary yet**Ruslan Salakhutdinov, Andriy Mnih, Geoffrey E. Hinton*2007 · 1,865 citations*
9. [**Layer Normalization arXiv:1607.06450**Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton*2016 · 1,819 citations*](https://md.research.elamur.ai/free/en/papers/ba-2016-layer-normalization/)
10. **[Deep Boltzmann machines ↗](https://openalex.org/W189596042) no summary yet**Ruslan Salakhutdinov, Geoffrey E. Hinton*2009 · 1,728 citations*
11. **[Neighbourhood Components Analysis ↗](https://openalex.org/W2144935315) no summary yet**Jacob Goldberger et al.*2004 · 1,676 citations*
12. **[The Helmholtz Machine ↗](https://doi.org/10.1162/neco.1995.7.5.889) Neural Computation · no summary yet**Peter Dayan et al.*1995 · 1,202 citations*
13. **[Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer ↗](https://arxiv.org/abs/1701.06538) arXiv:1701.06538 · no summary yet**Noam Shazeer et al.*2017 · 1,111 citations*
14. **[Autoencoders, Minimum Description Length and Helmholtz Free Energy ↗](https://openalex.org/W2102409316) no summary yet**Geoffrey E. Hinton, Richard S. Zemel*1993 · 1,073 citations*
15. **[Grammar as a Foreign Language ↗](https://arxiv.org/abs/1412.7449) arXiv:1412.7449 · no summary yet**Oriol Vinyals et al.*2014 · 687 citations*
16. [**Similarity of Neural Network Representations Revisited arXiv:1905.00414**Simon Kornblith, Mohammad Norouzi, Honglak Lee, et al.*2019 · 679 citations*](https://md.research.elamur.ai/free/en/papers/kornblith-2019-similarity-neural-network-representations-revisited/)
17. **[A Simple Way to Initialize Recurrent Networks of Rectified Linear Units ↗](https://arxiv.org/abs/1504.00941) arXiv (Cornell University) · no summary yet**Quoc Viet Le, Navdeep Jaitly, Geoffrey E. Hinton*2015 · 571 citations*
18. [**Regularizing Neural Networks by Penalizing Confident Output Distributions arXiv:1701.06548**Gabriel Pereyra, George Tucker, Jan Chorowski, et al.*2017 · 496 citations*](https://md.research.elamur.ai/free/en/papers/pereyra-2017-regularizing-neural-networks-penalizing-confident/)
19. **[An Efficient Learning Procedure for Deep Boltzmann Machines ↗](https://doi.org/10.1162/neco_a_00311) Neural Computation · no summary yet**Ruslan Salakhutdinov, Geoffrey E. Hinton*2012 · 485 citations*
20. **[Replicated Softmax: an Undirected Topic Model ↗](https://openalex.org/W2100002341) neural information processing systems · no summary yet**Geoffrey E. Hinton, Ruslan Salakhutdinov*2009 · 443 citations*
21. **[On rectified linear units for speech processing ↗](https://doi.org/10.1109/icassp.2013.6638312) IEEE International Conference on Acoustics Speech and Signal Processing · no summary yet**Matthew D. Zeiler et al.*2013 · 440 citations*
22. **[Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure ↗](https://openalex.org/W205159212) no summary yet**Ruslan Salakhutdinov, Geoffrey E. Hinton*2007 · 434 citations*
23. **[Exponential Family Harmoniums with an Application to Information Retrieval ↗](https://openalex.org/W2124914669) no summary yet**Max Welling, Michal Rosen‐Zvi, Geoffrey E. Hinton*2004 · 413 citations*
24. **[Managing extreme AI risks amid rapid progress ↗](https://doi.org/10.1126/science.adn0117) Science · no summary yet**Yoshua Bengio et al.*2024 · 382 citations*
25. **[Lookahead Optimizer: k steps forward, 1 step back ↗](https://arxiv.org/abs/1907.08610) arXiv (Cornell University) · no summary yet**Michael R. Zhang et al.*2019 · 380 citations*
26. **[Factored conditional restricted Boltzmann Machines for modeling motion style ↗](https://doi.org/10.1145/1553374.1553505) International Conference on Machine Learning · no summary yet**Graham W. Taylor, Geoffrey E. Hinton*2009 · 370 citations*
27. **[Using fast weights to improve persistent contrastive divergence ↗](https://doi.org/10.1145/1553374.1553506) International Conference on Machine Learning · no summary yet**Tijmen Tieleman, Geoffrey E. Hinton*2009 · 281 citations*
28. **[Attend, Infer, Repeat: Fast Scene Understanding with Generative Models ↗](https://arxiv.org/abs/1603.08575) arXiv (Cornell University) · no summary yet**S. M. Ali Eslami et al.*2016 · 256 citations*
29. **[Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes ↗](https://openalex.org/W2162724919) neural information processing systems · no summary yet**Geoffrey E. Hinton, Ruslan Salakhutdinov*2007 · 178 citations*
30. **[Using Fast Weights to Attend to the Recent Past ↗](https://arxiv.org/abs/1610.06258) arXiv (Cornell University) · no summary yet**Jimmy Lei Ba et al.*2016 · 168 citations*
31. **[Robust Boltzmann Machines for recognition and denoising ↗](https://doi.org/10.1109/cvpr.2012.6247936) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton*2012 · 168 citations*
32. **[Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation ↗](https://doi.org/10.1207/s15516709cog0000_76) Cognitive Science · no summary yet**Geoffrey E. Hinton et al.*2006 · 135 citations*
33. **[Learning Sparse Topographic Representations with Products of Student-t Distributions ↗](https://openalex.org/W2138448681) neural information processing systems · no summary yet**Max Welling, Simon Osindero, Geoffrey E. Hinton*2002 · 132 citations*
34. **[Topographic Product Models Applied to Natural Scene Statistics ↗](https://doi.org/10.1162/089976606775093936) Neural Computation · no summary yet**Simon Osindero, Max Welling, Geoffrey E. Hinton*2005 · 108 citations*
35. **[A Better Way to Pretrain Deep Boltzmann Machines ↗](https://openalex.org/W2125113755) neural information processing systems · no summary yet**Geoffrey E. Hinton, Ruslan Salakhutdinov*2012 · 105 citations*
36. **[Discovering Binary Codes for Documents by Learning Deep Generative Models ↗](https://doi.org/10.1111/j.1756-8765.2010.01109.x) Topics in Cognitive Science · no summary yet**Geoffrey E. Hinton, Ruslan Salakhutdinov*2010 · 101 citations*
37. **[Modeling documents with a Deep Boltzmann Machine ↗](https://openalex.org/W1853745982) no summary yet**Nitish Srivastava, Ruslan Salakhutdinov, Geoffrey E. Hinton*2013 · 96 citations*
38. **[A New Learning Algorithm for Mean Field Boltzmann Machines ↗](https://doi.org/10.1007/3-540-46084-5_57) Lecture notes in computer science · no summary yet**Max Welling, Geoffrey E. Hinton*2002 · 70 citations*
39. **[Generative versus discriminative training of RBMs for classification of fMRI images ↗](https://openalex.org/W2162747531) no summary yet**Tanya Schmah et al.*2008 · 69 citations*
40. **[Deep Lambertian Networks ↗](https://arxiv.org/abs/1206.6445) arXiv (Cornell University) · no summary yet**Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton*2012 · 66 citations*
41. **[Modeling Documents with Deep Boltzmann Machines ↗](https://arxiv.org/abs/1309.6865) arXiv (Cornell University) · no summary yet**Nitish Srivastava, Ruslan Salakhutdinov, Geoffrey E. Hinton*2013 · 63 citations*
42. **[Energy-Based Models for Sparse Overcomplete Representations ↗](https://openalex.org/W6990768437) no summary yet**Yee Whye Teh et al.*2003 · 53 citations*
43. **[Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions ↗](https://arxiv.org/abs/1907.02957) arXiv (Cornell University) · no summary yet**Yao Qin et al.*2019 · 52 citations*
44. **[Learning Population Codes by Minimizing Description Length ↗](https://doi.org/10.1162/neco.1995.7.3.549) Neural Computation · no summary yet**Richard S. Zemel, Geoffrey E. Hinton*1995 · 48 citations*
45. **[Comparing Classification Methods for Longitudinal fMRI Studies ↗](https://doi.org/10.1162/neco_a_00024) Neural Computation · no summary yet**Tanya Schmah et al.*2010 · 40 citations*
46. **[Self Supervised Boosting ↗](https://openalex.org/W2103504567) no summary yet**Max Welling, Richard S. Zemel, Geoffrey E. Hinton*2002 · 35 citations*
47. **[Deep Mixtures of Factor Analysers ↗](https://arxiv.org/abs/1206.4635) arXiv (Cornell University) · no summary yet**Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton*2012 · 33 citations*
48. **[Discovering Viewpoint-Invariant Relationships That Characterize Objects ↗](https://openalex.org/W2142150270) no summary yet**Richard S. Zemel, Geoffrey E. Hinton*1990 · 30 citations*
49. **[A Mode-Hopping MCMC sampler ↗](https://openalex.org/W116703061) no summary yet**Cristian Sminchisescu, Max Welling, Geoffrey E. Hinton*2003 · 19 citations*
50. **[Learning population coes by minimizing description length ↗](https://openalex.org/W2290658005) no summary yet**Richard S. Zemel, Geoffrey E. Hinton*1999 · 17 citations*
51. **[Deflecting Adversarial Attacks ↗](https://arxiv.org/abs/2002.07405) arXiv (Cornell University) · no summary yet**Yao Qin et al.*2020 · 13 citations*
52. **[A New View of ICA ↗](https://openalex.org/W1654789990) no summary yet**Geoffrey E. Hinton et al.*2001 · 13 citations*
53. **[Wormholes Improve Contrastive Divergence ↗](https://openalex.org/W2148186262) no summary yet**Max Welling, Andriy Mnih, Geoffrey E. Hinton*2003 · 12 citations*
54. **[Probabilistic Sequential Independent Components Analysis ↗](https://doi.org/10.1109/tnn.2004.828765) IEEE Transactions on Neural Networks · no summary yet**Max Welling, Richard S. Zemel, Geoffrey E. Hinton*2004 · 10 citations*
55. **[Efficient Parametric Projection Pursuit Density Estimation ↗](https://arxiv.org/abs/1212.2513) arXiv (Cornell University) · no summary yet**Max Welling, Richard S. Zemel, Geoffrey E. Hinton*2012 · 5 citations*
56. **[Learning Population Codes by Minimizing Description Length ↗](https://doi.org/10.7551/mitpress/7011.003.0016) The MIT Press eBooks · no summary yet**Richard S. Zemel, Geoffrey E. Hinton*1999 · 3 citations*
57. **[Fast Inference and Learning for Modeling Documents with a Deep Boltzmann Machine ↗](https://openalex.org/W2184456254) no summary yet**Nitish Srivastava, Ruslan Salakhutdinov, Geoffrey E. Hinton*2013 · 1 citation*
58. **[Approximate Contrastive Free Energies for Learning in Undirected Graphical Models ↗](https://openalex.org/W4090083) no summary yet**Max Welling, Geoffrey E. Hinton*2001 · 1 citation*
59. **[Learning and Evaluaing Deep Bolztmann Machines ↗](https://openalex.org/W7100594301) no summary yet**Ruslan Salakhutdinov, Geoffrey E. Hinton*2012*
60. **[This PDF file includes: Materials and Methods ↗](https://openalex.org/W7098040679) no summary yet**Geoffrey E. Hinton et al.*2009*
61. **[Generative versus discriminative training of RBMs for classification ↗](https://openalex.org/W7098424451) no summary yet**Tanya Schmah et al.*2009*
62. **[A New View of ICA ↗](https://openalex.org/W7099327536) no summary yet**Geoffrey E. Hinton et al.*2008*
63. **[DRAFT. A revised version will appear in NIPS 2007. Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes ↗](https://openalex.org/W7100182073) no summary yet**Ruslan Salakhutdinov, Geoffrey E. Hinton*2008*
64. **[Exponential family harmoniums with an . . . ↗](https://openalex.org/W7100727976) no summary yet**Max Welling, Michal Rosen‐Zvi, Geoffrey E. Hinton*2008*
65. **[Learning Sparse Topographic . . . ↗](https://openalex.org/W7100069272) no summary yet**Max Welling, Geoffrey E. Hinton, Simon Osindero*2008*
66. **[Developing Population Codes For ↗](https://openalex.org/W2186159355) no summary yet**Richard S. Zemel, Geoffrey E. Hinton*1993*