Geoffrey E. Hinton
| Department of Computer Science | email: hinton [at] cs [dot] toronto [dot] edu | |||
| University of Toronto | voice: 416-978-7564 | |||
| 6 King's College Rd. | fax: 416-978-1455 | |||
| Toronto, Ontario | office: Pratt 290G | |||
| M5S 3G4, CANADA | Directions for Visitors | |||
Check out the new web page for
Machine Learning at Toronto
Information for prospective students:
I will not be taking any more postdocs until 2011.
I will take at most one new graduate student in sept 2010.
Basic papers on deep learning
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)
Learning Multiple Layers of Representation.
Trends in Cognitive Sciences, Vol. 11, pp 428-434.
[pdf]
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]
Recent Papers
Salakhutdinov, R. and Hinton, G.~E. (2009)
Deep Boltzmann Machines.
To appear in Artificial Intelligence and Statistics.
[pdf]
Mnih, A. and Hinton, G.~E.
A Scalable Hierarchical Distributed Language Model. (2009)
Advances in Neural Information Processing Systems 21,
MIT Press, Cambridge, MA
[pdf]
Nair, V. and Hinton, G.~E.
Implicit Mixtures of Restricted Boltzmann Machines (2009)
Advances in Neural Information Processing Systems 21,
MIT Press, Cambridge, MA
[pdf]
Sutskever, I. and Hinton, G.~E.
Using matrices to model symbolic relationships. (2009)
Advances in Neural Information Processing Systems 21,
MIT Press, Cambridge, MA
[pdf]
Sutskever, I., Hinton, G.~E. and Taylor, G. W. (2009)
The Recurrent Temporal Restricted Boltzmann Machine.
Advances in Neural Information Processing Systems 21,
MIT Press, Cambridge, MA
[pdf]
van der Maaten, L. J. P. and Hinton, G. E. (2008)
Visualizing Data using t-SNE.
Journal of Machine Learning Research, Vol 9, (Nov) pp 2579-2605.
[pdf]
[supplementary material in pdf
(25MB)]
Nair, V., Susskind, J., and Hinton, G.E. (2008)
Analysis-by-Synthesis by Learning to Invert Generative Black Boxes.
ICANN-08: International conference on Artificial Neural
Networks, Prague.
[pdf]
Sutskever, I. and Hinton, G. E. (2008)
Deep Narrow Sigmoid Belief Networks are Universal Approximators.
Neural Computation, Vol 20, pp 2629-2636.
[pdf]
Osindero, S. and Hinton, G. E. (2008)
Modeling image patches with a directed hierarchy of Markov random fields.
Advances in Neural Information Processing Systems 20
[pdf]
Salakhutdinov, R. R. and Hinton, G. E. (2008)
Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes.
Advances in Neural Information Processing Systems 20
[pdf]
Salakhutdinov R. R. and Hinton, G. E.
Semantic Hashing.
Proceedings of the SIGIR Workshop on Information Retrieval and
Applications of Graphical Models, Amsterdam.
[
pdf ]
Salakhutdinov, R. R., Mnih, A. and Hinton, G. E.
Restricted Boltzmann Machines for Collaborative Filtering.
ICML 2007
[
pdf ] (applied to Netflix)
Memisevic, R. F. and Hinton, G. E.
Unsupervised Learning of Image Transformations.
CVPR-07 [pdf] Technical Report UTML TR 2006-005.
[pdf]
