Geoffrey E. Hinton

Department of Computer Science
  email: geoffrey [dot] hinton [at] gmail [dot] com
University of Toronto   voice: send email
6 King's College Rd.   fax: scan and send email
Toronto, Ontario  

Information for prospective students, postdocs and visitors:
I will not be taking any more students, postdocs or visitors.

Results of the 2012 competition to recognize 1000 different types of object
How George Dahl won the competition to predict the activity of potential drugs
How Vlad Mnih won the competition to predict job salaries from job advertisements
How Laurens van der Maaten won the competition to visualize a dataset of potential drugs

Using big data to make people vote against their own interests
A possible motive for making people vote against their own interests

Basic papers on deep learning

LeCun, Y., Bengio, Y. and Hinton, G. E. (2015)
Deep Learning
Nature, Vol. 521, pp 436-444. [pdf]

Hinton, G. E., Osindero, S. and Teh, Y. (2006)
A fast learning algorithm for deep belief nets.
Neural Computation, 18, pp 1527-1554. [pdf]
Movies of the neural network generating and recognizing digits

Hinton, G. E. and Salakhutdinov, R. R. (2006)
Reducing the dimensionality of data with neural networks.
Science, Vol. 313. no. 5786, pp. 504 - 507, 28 July 2006.
[ full paper ] [ supporting online material (pdf) ] [ Matlab code ]
Papers on deep learning without much math

Hinton, G. E. (2007)
To recognize shapes, first learn to generate images
In P. Cisek, T. Drew and J. Kalaska (Eds.)
Computational Neuroscience: Theoretical Insights into Brain Function. Elsevier. [pdf of final draft]

Hinton, G. E. (2007)
Learning Multiple Layers of Representation.
Trends in Cognitive Sciences, Vol. 11, pp 428-434. [pdf]

Hinton, G. E. (2014)
Where do features come from?.
Cognitive Science, Vol. 38(6), pp 1078-1101. [pdf]

Recent Papers

Qin, Y., Frosst, N., Sabour, S., Raffel, C., Cottrell, C. and Hinton, G.
Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
ICLR-2020 [pdf]

Kosiorek, A. R., Sabour, S., Teh, Y. W. and Hinton, G. E.
Stacked Capsule Autoencoders
Advances in Neural Information Processing Systems 32 [pdf]

Zhang, M., Lucas, J., Ba, J., and Hinton, G. E.
Lookahead Optimizer: k steps forward, 1 step back
Advances in Neural Information Processing Systems 32 [pdf]

Muller, R., Kornblith, S. and Hinton G. (2019)
When Does Label Smoothing Help?
Advances in Neural Information Processing Systems 32 [pdf]

Deng, B., Kornblith, S. and Hinton, G. (2019)
Cerberus: A multi-headed derenderer.
3D Scene Understanding Workshop, CVPR 2019 [pdf]

Deng, B., Genova, K., Yazdani, S., Bouaziz, S., Hinton, G. and Tagliasacchi, A. (2019)
Cvxnet: Learnable convex decomposition.
Perception as Generative Reasoning Workshop, NeurIPS 2019 [pdf]

Kornblith, S., Norouzi, M., Lee, H. and Hinton, G. (2019)
Similarity of neural network representations revisited
ICML-2019 [pdf]

Hinton, G. E., Sabour, S. and Frosst, N.
Matrix Capsules with EM Routing
ICLR-2018 [pdf]

Kiros, J. R., Chan, W. and Hinton, G. E.
Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search
ACL-2018 [pdf]

Anil, R., Pereyra, G., Passos, A., Ormandi, R., Dahl, G. and Hinton, G. E.
Large scale distributed neural network training through online distillation
ICLR-2018 [pdf]

Guan, M. Y., Gulshan, V., Dai, A. M. and Hinton, G. E.
Who Said What: Modeling Individual Labelers Improves Classification
AAAI-2018 [pdf]

Sabour, S., Frosst, N. and Hinton, G. E.
Dynamic Routing between Capsules
NIPS-2017, [pdf]

Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., & Dean, J. (2017)
Outrageously large neural networks: The sparsely-gated mixture-of-experts layer
arXiv preprint arXiv:1701.06538 [pdf]

Ba, J. L., Hinton, G. E., Mnih, V., Leibo, J. Z. and Ionescu, C. (2016)
Using Fast Weights to Attend to the Recent Past
NIPS-2016, arXiv preprint arXiv:1610.06258v2 [pdf]

Ba, J. L., Kiros, J. R. and Hinton, G. E. (2016)
Layer normalization
Deep Learning Symposium, NIPS-2016, arXiv preprint arXiv:1607.06450 [pdf]

2021 commencement address at IIT Mumbai    

Joseph Turian's map of 2500 English words produced by using t-SNE on the word feature vectors learned by Collobert & Weston, ICML 2008    

Doing analogies by using vector algebra on word embeddings    

My favorite Gary Marcus quote    

A new concept of healing from the people who design unimprovised explosive devices