Information
----Curriculum Vitae
----Contact Details
 
Research
----Publications
----Talks
 
My Home Page
http://web.mit.edu/~rsalakhu/www/
  
[Image]

 

Ruslan Salakhutdinov
Postdoctoral Fellow
Department of Brain and Cognitive Sciences and CSAIL
Massachusetts Institute of Technology
MIT Building 46-4053
77 Massachusetts Avenue, Cambridge, MA 02139

Email: rsalakhu (at) mit (dot) edu
Office: 46-4053H


NIPS 2009 Workshop on Approximate Learning of Large Scale Graphical Models: Theory and Applications here
(that I am organizing together with Amir Globerson and David Sontag).

ICML09 Workshop on Learning Feature Hierarchies here

Learning Deep Generative Models.
Ruslan Salakhutdinov
PhD Thesis, Sep 2009
Dept. of Computer Science, University of Toronto
[bibtex] [ps.gz][ pdf]

Several Representative Papers:

Reducing the Dimensionality of Data with Neural Networks.
Geoffrey E. Hinton and Ruslan R. Salakhutdinov
Science, 28 July 2006:
Vol. 313. no. 5786, pp. 504 - 507
[bibtex] [pdf][ Science Online]
Supporting Online Material [pdf, Science Online]
Matlab Code is available here

Deep Boltzmann Machines.
Ruslan Salakhutdinov and Geoffrey Hinton
12th International Conference on Artificial Intelligence and Statistics (2009).
[bibtex] [ps.gz][ pdf]

Learning and Evaluating Boltzmann Machines.
Ruslan Salakhutdinov
Technical Report UTML TR 2008-002, Dept. of Computer Science, University of Toronto
[bibtex] [ps.gz][ pdf]
This paper introduces a new Boltzmann machine learning algorithm that combines variational techniques and MCMC.



Recent Papers

Ruslan Salakhutdinov.
Learning in Markov Random Fields using Tempered Transitions.
To appear in Neural Information Processing Systems 22.
[bibtex] [ps.gz][ pdf]

Ruslan Salakhutdinov and Geoffrey Hinton.
Replicated Softmax: an Undirected Topic Model.
To appear in Neural Information Processing Systems 22.
[bibtex] [ps.gz][ pdf]

Ilya Sutskever, Ruslan Salakhutdinov, and Josh Tenenbaum.
Modelling Relational Data using Bayesian Clustered Tensor Factorization.
To appear in Neural Information Processing Systems 22.
[bibtex] [pdf]

John Langford, Ruslan Salakhutdinov and Tong Zhang.
Learning Nonlinear Dynamic Models.
Proceedings of the 26th International Conference on Machine Learning (ICML), 2009.
[bibtex] [ps.gz][ pdf]

Hanna M. Wallach, Iain Murray, Ruslan Salakhutdinov and David Mimno.
Evaluation Methods for Topic Models.
Proceedings of the 26th International Conference on Machine Learning (ICML), 2009.
[bibtex] [ pdf]

Iain Murray and Ruslan Salakhutdinov.
Evaluating probabilities under high-dimensional latent variable models.
Neural Information Processing Systems 21 (NIPS 2009)
[bibtex] [ pdf], Jan 2009


Recent Talks

  • Deep Boltzmann Machines (ps.gz, pdf).
    Snowbird workshop, April 2009.

  • I was co-organizing Deep Learning Workshop: Foundations and Future Directions, NIPS 2007.

  • Deep Belief Nets (ps.gz, pdf).
    Snowbird workshop, March 2007.
    Demo and explanation of Digits and Faces.

    [ Home | Information | Research | ]

    Ruslan Salakhutdinov, Department of Brain and Cognitive Sciences and CSAIL, MIT || http://web.mit.edu/~rsalakhu/www/