|
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.
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 ]
Recent Papers
Hinton, G. E. (2022)
The Forward-Forward Algorithm: Some Preliminary
Investigations
arXiv:2212.13345
[pdf of final version]
[ffcode.zip matlab code for the supervised version of FF
with the first 10 pixels being the labels]
[load mnistdata.mat in matlab to create the data]
[README.txt explains what to do to run
FF}
Sindy Loewe's translation to python code is available at
https://github.com/loeweX/Forward-Forward
Chen, T., Zhang, R., & Hinton, G. (2022)
Analog bits: Generating discrete data using diffusion models with
self-conditioning
arXiv preprint arXiv:2208.04202
[pdf]
Ren, M., Kornblith, S., Liao, R., & Hinton, G. (2022)
Scaling Forward Gradient With Local Losses
arXiv preprint arXiv:2210.03310
[pdf]
Chen, T., Saxena, S., Li, L., Lin, T. Y., Fleet, D. J., & Hinton, G. (2022)
A unified sequence interface for vision tasks
arXiv preprint arXiv:2206.07669
[pdf]
Chen, T., Li, L., Saxena, S., Hinton, G., & Fleet, D. J.(2022)
A generalist framework for panoptic segmentation of images and
videos
arXiv preprint arXiv:2210.06366
[pdf]
Liao, R., Kornblith, S., Ren, M., Fleet, D. J., & Hinton, G. (2022)
Gaussian-Bernoulli RBMs Without Tears
arXiv preprint arXiv:2210.10318
[pdf]
Culp, L., Sabour, S., & Hinton, G. E. (2022)
Testing GLOM's ability to infer wholes from ambiguous parts
arXiv preprint arXiv: 2211.16564
[pdf]
Agarwal, R., Melnick, L., Frosst, N., Zhang, X., Lengerich, B.,
Caruana, R., & Hinton, G. E. (2021)
Neural additive models:Interpretable machine learning with neural nets
Advances in Neural Information Processing Systems, 34, 4699-4711.
[pdf]
Bengio, Y., Lecun, Y., & Hinton, G. (2021)
Deep learning for AI
Communications of the ACM, 64(7), 58-65.
[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 (in 2008)    
My old favorite Gary Marcus quote    
GPT-4 corrects Gary Marcus    
My new favorite Gary Marcus quote
"It gloms on to different clusters of text. That is all."
A new concept of healing from the people who design unimprovised
explosive devices    
|