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
Visit my new webpage at Toronto.
Quick link to my research papers and invited talks.
In July 2011, I will be joining the faculty of
Department of Statistics and
Department of Computer Science
(by courtesy) at the
University of Toronto.
I will serve
as an Area Chair for the
NIPS 2011
program committee.
Upcoming Visits:
-
- June 5-6: Invited talk at the Workshop on Infusing Statistics and Engineering, Harvard University
- July 2: Invited talk at the ICML 2011 Workshop on Unsupervised and Transfer Learning, Bellevue, Washington.
- July 6-16: Guest lecture at the IPAM Graduate Summer School: Probabilistic Models of Cognition, UCLA
- Aug 2-6: Tutorial on Learning Rich Generative Models at the CIFAR summer school 2011, University of Toronto
- June 5-6: Invited talk at the Workshop on Infusing Statistics and Engineering, Harvard University
Several Representative Papers:
-
Reducing the Dimensionality of Data with Neural Networks.
Geoffrey Hinton and Ruslan Salakhutdinov
Science, 28 July 2006, [pdf]Bayesian Probabilistic Matrix Factorization using MCMC.
Ruslan Salakhutdinov and Andriy Mnih
In 25th International Conference on Machine Learning (ICML-2008), [ pdf]
Matlab code, also check out this implementation by GraphLab at Carnegie Mellon University.Learning and Evaluating Boltzmann Machines.
Ruslan Salakhutdinov
Technical Report UTML TR 2008-002, Dept. of Computer Science, University of Toronto, [ pdf]
Deep Boltzmann Machines.
Ruslan Salakhutdinov and Geoffrey Hinton
12th International Conference on Artificial Intelligence and Statistics (2009), [ pdf] Matlab code
Learning Deep Generative Models.
Ruslan Salakhutdinov
PhD Thesis, Sep 2009
Dept. of Computer Science, University of Toronto, [ pdf]
Recent Papers:
Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions
Rina Foygel,
Ohad Shamir,
Nathan Srebro, and
Ruslan Salakhutdinov
ArXiv Report, 2011
Domain Adaptation: Overfitting and Small Sample Statistics
Dean Foster,
Sham Kakade, and
Ruslan Salakhutdinov
ArXiv Report
[ pdf], 2011
One-shot learning of simple visual concepts
Brenden Lake ,
Ruslan Salakhutdinov, Jason Gross, and
Josh Tenenbaum.
To appear in
Proceedings of the 33rd Annual
Conference of the Cognitive Science Society, 2011
[ pdf],
videos
Learning to Share Visual Appearance for Multiclass Object Detection
Ruslan Salakhutdinov,
Antonio Torralba , and
Josh Tenenbaum.
To appear in Computer Vision and Pattern Recognition (CVPR) 2011
[ pdf]
Collaborative Filtering in a Non-Uniform World: Learning
with the Weighted Trace Norm.
Ruslan Salakhutdinov and
Nathan Srebro.
Neural Information Processing Systems 24, 2011
[ pdf]
Practical Large-Scale Optimization for Max-Norm Regularization.
Jason Lee,
Benjamin Recht,
Ruslan Salakhutdinov,
Nathan Srebro, and
Joel A. Tropp.
Neural Information Processing Systems 24, 2011
[ pdf]
Discovering Binary Codes for Documents by Learning
Deep Generative Models.
Geoffrey Hinton and Ruslan Salakhutdinov.
Topics in Cognitive Science, 2010,
[ pdf]
One-Shot Learning with a Hierarchical
Nonparametric Bayesian Model.
Ruslan Salakhutdinov,
Josh Tenenbaum, and
Antonio Torralba.
MIT Technical Report MIT-CSAIL-TR-2010-052, 2010,
[ pdf]
An Efficient Learning Procedure for
Deep Boltzmann Machines.
Ruslan Salakhutdinov and
Geoffrey Hinton .
MIT Technical Report MIT-CSAIL-TR-2010-037, 2010,
[ pdf]
[ Code]
Learning in Deep Boltzmann Machines using Adaptive MCMC.
Ruslan Salakhutdinov.
In 27th International
Conference on Machine Learning (ICML-2010),
[ pdf]
Efficient Learning of Deep Boltzmann Machines.
Ruslan Salakhutdinov and
Hugo Larochelle.
AI and Statistics, 2010,
[ pdf]