Machine Learning

2016

International Conference on Intelligent Systems for Molecular Biology (ISMB)
(CVPR) Conference on Computer Vision and Pattern Recognition
  • Wenjie Luo, Alex Schwing and Raquel Urtasun.  Efficient Deep Learning for Stereo Matching.  In Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, US, June 2016.  (Spotlight)
  • Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Raquel Urtasun and Sanja Fidler.  MovieQA: Understanding Stories in Movies through Question-Answering.  In Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, US, June 2016.  (Spotlight)
  • Gellert Mattyus, Shenlong Wang, Sanja Fidler and Raquel Urtasun.  HD Maps: Fine-grained Road Segmentation by Parsing Ground and Aerial Images.  In Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, US, June 2016.
  • Xiaozhi Chen, Kaustav Kundu, Ziyu Zhang, Huimin Ma, Sanja Fidler and Raquel Urtasun.  Monocular 3D Object Detection for Autonomous Driving.  In Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, US, June 2016.
  • Ziyu Zhang, Sanja Fidler and Raquel Urtasun.  Instance-Level Segmentation with Deep Densely Connected MRFs.  In Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, US, June 2016.
(ICLR) International Conference on Learning Representations
(AISTATS) International Conference on Artificial Intelligence and Statistics
  • Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, Eric Xing.  Deep Kernel Learning.  In International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.
  • Yali Wang, Markus Brubaker and Raquel Urtasun.  Sequential Inference for Deep Gaussian Process.  In International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.
Critical Reviews in Biochemistry and Molecular Biology
Proceedings of the IEEE

2015

(NIPS) Neural Information Processing Systems
  • Lei Jimmy Ba, Roger Grosse, Ruslan Salakhutdinov, Brendan Frey.  Learning Wake-Sleep Recurrent Attention Models.  In Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015.
  • Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard S. Zemel, Antonio Torralba, Raquel Urtasun, Sanja Fidler.  Skip-Thought Vectors.  In Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015.
  • Behnam Neyshabur, Ruslan Salakhutdinov, Nathan Srebro.  Path-SGD: Path-Normalized Optimization in Deep Neural Networks.  In Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015.
  • Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Andrew Berneshawi, Huimin Ma, Sanja Fidler and Raquel Urtasun.  3D Object Proposals for Accurate Object Class Detection.  In Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015.
  • Ofer Meshi, Mehrdad Mahdavi, and Alexander G. Schwing.  Smooth and Strong: MAP Inference with Linear Convergence.  In Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015.
  • Mengye Ren, Ryan Kiros, Richard Zemel.  Exploring Models and Data for Image Question Answering.  In Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015.
  • Alireza Makhzani, Brendan Frey.  Winner-Take-All Autoencoders.  In Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015.
(ICCV)  International Conference on Computer Vision
  • Yukun Zhu, Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler.  Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books.  In International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.  (Oral)
  • Shenlong Wang, Sanja Fidler and Raquel Urtasun.  Lost Shopping! Monocular Localization in Large Indoor Spaces.  In International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.  (Oral)
  • Jimmy Ba, Kevin Swersky, Sanja Fidler, Ruslan Salakhutdinov.  Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions.  In International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.
  • Gellert Matthyus, Shenlong Wang, Sanja Fidler and Raquel Urtasun.  Enhancing World Maps by Parsing Aerial Images.  In International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.
  • Philip Lenz, Andreas Geiger and Raquel Urtasun.  FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation.  In International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.
  • Ziyu Zhang, Alex Schwing, Sanja Fidler and Raquel Urtasun.  Monocular Object Instance Segmentation and Depth Ordering with CNNs.  In International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.
ACM Transactions on Interactive and Intelligent Systems
  • Axel J. Soto, Ryan Kiros, Vlado Keselj, Evangelos Milios.  Exploratory Visual Analysis and Interactive Pattern Extraction from Semi-Structured Data.  In ACM Transactions on Interactive and Intelligent Systems, 2015.
(UAI) Conference on Uncertainty in Artificial Intelligence
Nature
  • Yann LeCun, Yoshua Bengio and Geoffrey Hinton.  Deep Learning.  Nature, Vol. 521, pp 436-444. 2015
(RecSys) ACM Conference on Recommender Systems
(BMVC) British Machine Vision Conference
  • Dahua Lin, Chen Kong, Sanja Fidler and Raquel Urtasun.  Generating Multi-Sentence Lingual Descriptions of Indoor Scenes (Oral).  In British Machine Vision Conference (BMVC), Swansea, Wales, September 2015
(ICML) International Conference on Machine Learning
  • Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard Zemel, Yoshua Bengio.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.  In International Conference on Machine Learning (ICML), Lille, France, July 2015.
  • Nitish Srivastava, Elman Mansimov, Ruslan Salakhutdinov.   Unsupervised Learning of Video Representations using LSTMs.   In International Conference on Machine Learning (ICML), Lille, France, July 2015.
  • Liang-Chieh Chen, Alexander Schwing, Alan Yuille and Raquel Urtasun.  Learning Deep Structured Models.  In International Conference on Machine Learning (ICML), Lille, France, July 2015.
  • Yujia Li, Kevin Swersky and Richard Zemel.  Generative Moment Matching Networks.  In International Conference on Machine Learning (ICML), Lille, France, July 2015.
  • James Martens and Roger Grosse.  Optimizing Neural Networks with Kronecker-factored Approximate Curvature.  In International Conference on Machine Learning (ICML), Lille, France, July 2015.
  • Roger Grosse and Ruslan Salakhutdinov.  Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix.  In International Conference on Machine Learning (ICML), Lille, France, July 2015.
  • Jasper Snoek, Oren Rippel, Kevin Swersky, Ryan Kiros, Nadathur Satish, Narayanan Sundaram, Md. Mostofa Ali Patwary, Prabhat, Ryan P. Adams.  Scalable Bayesian Optimization Using Deep Neural Networks.  In International Conference on Machine Learning (ICML), Lille, France, July 2015.
(ICLR) International Conference on Learning Representations
(PAMI) Transactions on Pattern Recognition and Machine Intelligence
  • Roozbeh Mottaghi, Sanja Fidler, Alan Yuille, Raquel Urtasun and Devi Parikh.  Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding.  In Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015
  • Alexander Schwing, Tamir Hazan, Marc Pollefeys and Raquel Urtasun.  Distributed Algorithms for Large Scale Learning and Inference in Graphical Models.  In Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015
  • Marcus Brubaker, Andreas Geiger and Raquel Urtasun.  Map-Based Probabilistic Visual Self-Localization.  In Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015
Annual Review of Statistics and Its Application
Journal of Chemical Information and Modeling
(CVPR) Conference on Computer Vision and Pattern Recognition
(WACV) Winter Conference on Applications of Computer Vision
(TACL) Transactions of the Association for Computational Linguistics
Science
(ICASSP) International Conference on Acoustics, Speech and Signal Processing
(AISTATS) International Conference on Artificial Intelligence and Statistics

2014

(NIPS) Neural Information Processing Systems
(KDD) ACM Conference on Knowledge Discovery and Data Mining
(JMLR) Journal of Machine Learning Research
  • Nitish Srivastava and Ruslan Salakhutdinov.  Multimodal Learning with Deep Boltzmann Machines.  In Journal of Machine Learning Research, 2014.
  • Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan R. Salakhutdinov.  Dropout: A simple way to prevent neural networks from overfitting.  In Journal of Machine Learning Research, 2014.
(ACCV) Asian Conference on Computer Vision
  • Edgar Simo, Sanja Fidler, Francesc Moreno-Noguer and Raquel Urtasun. A High Performance CRF Model for Clothes Parsing. In Asian Conference on Computer Vision (ACCV), Singapore, November 2014.
(ECCV) European Conference on Computer Vision
(UAI) Conference on Uncertainty in Artificial Intelligence
(ICML) International Conference on Machine Learning
(CVPR) Conference on Computer Vision and Pattern Recognition
Frontiers in Neuroscience
NeuralImage
Bioinformatics
  • Michael K. K. Leung, Hui Yuan Xiong, Leo J. Lee, Brendan J. Frey.  Deep learning of the tissue-regulated splicing code.  Proceedings of the 22nd Annual International Conference on Intelligent Systems for Molecular Biology (ISMB), June 2014.  Bioinformatics, Vol 30, No. 12.
(ICLR) International Conference on Learning Representations
  • Alireza Makhzani, Brendan Frey. k-Sparse AutoencodersInternational Conference on Learning Representations (ICLR), 2014.
(ICCP) International Conference on Computational Photography
Nature Methods

2013

(NIPS) Conference on Neural Information Processing Systems
(ICML) International Conference on Machine Learning
  • Ilya Sutskever, James Martens, George Dahl and Geoffrey Hinton. On the importance of initialization and momentum in deep learning. 2013. in Proceedings of the 30th International Conference on Machine Learning (ICML).
  • Daniel Tarlow,  Ilya Sutskever  and Richard S. Zemel. Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning. 2013. in Proceedings of the 30th International Conference on Machine Learning (ICML).
  • Yichuan Tang, Ruslan Salakhutdinov and Geoffrey Hinton. Tensor Analyzers. 2013. in Proceedings of the 30th International Conference on Machine Learning (ICML).
  • Richard Zemel, Yu Ledell Wu, Kevin Swersky, Toniann Pitassi and Cynthia Dwork. Learning Fair Representations. 2013. in Proceedings of the 30th International Conference on Machine Learning (ICML).
(UAI) Conference on Uncertainty in Artificial Intelligence
  • Nitish Srivastava, Ruslan Salakhutdinov and Geoffrey Hinton. Modeling Documents with Deep Boltzmann Machines. 2013. in Conference on Uncertainty in Artificial Intelligence (UAI).
(CVPR) IEEE Conference on Computer Vision and Pattern Recognition
(ICASSP) International Conference on Acoustics, Speech and Signal Processing
(TPAMI) IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Marc’Aurelio Ranzato, Volodymyr Mnih, Joshua M. Susskind and Geoffrey E. Hinton. Modeling Natural Images Using Gated MRFs. 2013. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  • Ruslan Salakhutdinov, Joshua B. Tenenbaum and Antonio Torralba. Learning with Hierarchical-Deep Models. 2013.IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
Journal of Machine Learning Research
  • Maksims N. Volkovs and Richard S. Zemel. New Learning Methods for Supervised and Unsupervised Preference Aggregation. 2013. Journal of Machine Learning Research.

2012

(NIPS) Conference on Neural Information Processing Systems
(ICML) International Conference on Machine Learning
(UAI) Conference on Uncertainty in Artificial Intelligence
(CVPR) IEEE Conference on Computer Vision and Pattern Recognition
(ICASSP) International Conference on Acoustics, Speech and Signal Processing
(AISTATS) International Conference on Artificial Intelligence and Statistics
(CIKM) International Conference on Information and Knowledge Management
(CogSci) Annual Conference of the Cognitive Science Society
  • Brenden M. Lake, Ruslan Salakhutdinov and Joshua B. Tenenbaum.Concept learning as motor program induction: A large-scale empirical study. 2012. in Proceedings of the 34rd Annual Conference of the Cognitive Science Society.
(ITCS) Innovations in Theoretical Computer Science
  • Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. Fairness through awareness. 2012. in Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pages 214–226. ACM.
(TASLP) IEEE Transactions on Audio, Speech, and Language Processing
(WWW) International World Wide Web Conference
Machine Learning
  • Laurens van der Maaten and Geoffrey Hinton. Visualizing non-metric similarities in multiple maps. 2012.Machine learning, 87(1):33–55.
Neural Computation
Science

2011

(NIPS) Conference on Neural Information Processing Systems
(ICML) International Conference on Machine Learning
(UAI) Conference on Uncertainty in Artificial Intelligence
(CVPR) IEEE Conference on Computer Vision and Pattern Recognition
(ICASSP) International Conference on Acoustics, Speech and Signal Processing
Journal of Machine Learning Research
  • Graham W. Taylor, Geoffrey E. Hinton and Sam T. Roweis. Two distributed-state models for generating high-dimensional time series. 2011. Journal of Machine Learning Research, 12:1025–1068.
(AISTATS) International Conference on Artificial Intelligence and Statistics
(ICANN) International Conference on Artificial Neural Networks
  • Geoffrey E. Hinton, Alex Krizhevsky and Sida D.Wang. Transforming auto-encoders. 2011. in Artificial Neural Networks and Machine Learning (ICANN), pages 44–51. Springer.
(KDD) International Conference on Knowledge Discovery and Data Mining

2010

(NIPS) Conference on Neural Information Processing Systems
(ICML) International Conference on Machine Learning
(UAI) Conference on Uncertainty in Artificial Intelligence
(ICASSP) International Conference on Acoustics, Speech and Signal Processing
(AISTATS) International Conference on Artificial Intelligence and Statistics
(ECCV) European Conference on Computer Vision
(IJCV) International Journal of Computer Vision
(Interspeech) Annual Conference of the International Speech Communication Association
Nature
  • Yoseph Barash, John A. Calarco, Weijun Gao, Qun Pan, Xinchen Wang, Ofer Shai, Benjamin J. Blencowe and Brendan J. Frey. Deciphering the splicing code. 2010. Nature, 465(7294):53–59. (The coding capacity of the vertebrate genome is greatly expanded by alternative splicing, which enables a single gene to produce more than one distinct protein.The Frey and Blencowe labs at the University of Toronto have combined forces to develop a ‘splicing code’ that accurately predicts how hundreds of RNA features work together to regulate tissue-dependent alternative splicing for thousands of exons. It has been used to predict how alternative splicing may play important roles in development and neurological processes, and has provided insights into mechanisms of splicing regulation. The code has also been incorporated into a web tool.)
Neural Networks

2009

(NIPS) Conference on Neural Information Processing Systems
(ICML) International Conference on Machine Learning
(AISTATS) International Conference on Artificial Intelligence and Statistics
Neural Computation
(ICCV) International Conference on Computer Vision
Neural Processing
  • Rama Natarajan, Iain Murray, Ladan Shams and Richard Zemel. Characterizing response behavior in multisensory perception with conflicting cues. 2009. in Advances in Neural Information Processing Systems 21,pages 1153–1160.
Protein Sequence Classification and Motif Discovery
Cumulative Distribution Networks
  • Jim C. Huang and Brendan J. Frey. Structured ranking learning using cumulative distribution networks. 2009. inAdvances in Neural Information Processing Systems 21.
Restricted Boltzmann Machines and Deep Belief Networks

The group does a significant amount of work on the unsupervised discovery of data representations using Restricted Boltzmann Machines and Deep Belief Networks.

  • Iain Murray and Ruslan Salakhutdinov. Evaluating probabilities under high-dimensional latent variable models.2009. in Advances in Neural Information Processing Systems 21, pages 1137–1144.
  • Tanya Schmah, Geoffrey E Hinton, Richard Zemel, Steven L. Small and Stephen Strother. Generative versus discriminative training of RBMs for classification of fMRI images. 2009. in Advances in Neural Information Processing Systems 21, pages 1409–1416.
  • Ilya Sutskever, Geoffrey Hinton, and Graham Taylor. The Recurrent Temporal Restricted Boltzmann Machine. 2009. inAdvances in Neural Information Processing Systems 21, pages 1137–1144.

2008

(NIPS) Conference on Neural Information Processing Systems
(ICML) International Conference on Machine Learning
(UAI) Conference on Uncertainty in Artificial Intelligence
Neural Computation
(ICANN) International Conference on Artificial Neural Networks
(ECCV) European Conference on Computer Vision
Cumulative Distribution Networks
  • Jim C. Huang and Brendan J. Frey. Cumulative distribution networks and the derivative-sum-product algorithm.2008.
Inverting Generative Black Boxes
Language Modeling
Dimensionality Reduction, Embedding, and Data Visualization
Restricted Boltzmann Machines and Deep Belief Networks

2007

(AISTATS) International Conference on Artificial Intelligence and Statistics
Language Modeling
Identification of microRNA Targets
  • Jim C. Huang, Tomas Babak, Timothy W. Corson, Gordon Chua, Sophia Khan, Brenda L. Gallie, Timothy R. Hughes, Benjamin J. Blencowe, Brendan J. Frey and Quaid D. Morris. Using expression profiling data to identify human microRNA targets. 2007. Nature Methods, 4:1045–1049.
Dimensionality Reduction, Embedding, and Data Visualization
  • James Cook, Ilya Sutskever, Andriy Mnih and Geoffrey Hinton. Visualizing similarity data with a mixture of maps. 2007.
  • R. R. Salakhutdinov and G. E. Hinton. Learning a non-linear embedding by preserving class neighbourhood structure. 2007. in AI and Statistics.
Restricted Boltzmann Machines and Deep Belief Networks

2006

(UAI) Conference on Uncertainty in Artificial Intelligence
  • Inmar Givoni, Vincent Cheung, Brendan J. Frey. Matrix tile analysis. 2006. in Conference on Uncertainty in Artificial Intelligence.
Cell
Identification of microRNA Targets
  • Jim C. Huang, Quaid D. Morris and Brendan J. Frey. Detecting microRNA targets by linking sequence, microRNA and gene expression data. 2006.
Modeling Human Motion
  • Graham W. Taylor, Geoffrey E. Hinton and Sam T. Roweis. Modeling Human Motion Using Binary Latent Variables. 2006. in Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 4-7, 2006, pages 1345-1352.
Dimensionality Reduction, Embedding, and Data Visualization
  • Amir Globerson and Sam Roweis. Metric Learning by Collapsing Classes. 2006. in Advances in Neural Information Processing Systems 19 (NIPS’05), pages 451–458.
  • Geoffrey E. Hinton and Ruslan Salakhutdinov. Reducing the Dimensionality of Data with Neural Networks . 2006.Science, 313(5786):504-507.
Restricted Boltzmann Machines and Deep Belief Networks

2005

Inferring Motor Programs from Images of Handwritten Digit
Dimensionality Reduction, Embedding, and Data Visualization
Restricted Boltzmann Machines and Deep Belief Networks
  • Geoffrey E. Hinton. What kind of graphical model is the brain?. 2005. in IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, July 30-August 5, 2005, pages 1765-.

2004

Dimensionality Reduction, Embedding, and Data Visualization
  • Jacob Goldberger, Sam T. Roweis, Geoffrey E. Hinton and Ruslan Salakhutdinov. Neighbourhood Components Analysis. 2004. in Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, NIPS 2004, December 13-18, 2004, Vancouver, British Columbia, Canada].
  • Roland Memisevic and Geoffrey E. Hinton. Multiple Relational Embedding. 2004. in Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, NIPS 2004, December 13-18, 2004, Vancouver, British Columbia, Canada].

2003

Dimensionality Reduction, Embedding, and Data Visualization
  • Geoffrey Hinton and Sam Roweis. Stochastic Neighbor Embedding. 2003. in Advances in Neural Information Processing Systems 15 (NIPS’02), pages 857–864.
Restricted Boltzmann Machines and Deep Belief Networks
  • Geoffrey E. Hinton, Max Welling and Andriy Mnih. Wormholes Improve Contrastive Divergence. 2003. inAdvances in Neural Information Processing Systems 16 [Neural Information Processing Systems, NIPS 2003, December 8-13, 2003, Vancouver and Whistler, British Columbia, Canada].

2000

Dimensionality Reduction, Embedding, and Data Visualization
  • Sam T. Roweis and Lawrence K. Saul. Nonlinear Dimensionality Reduction by Locally Linear Embedding. 2000.Science, 290(5500):2323-2326. [PDF]

1995

Helmholtz Machines:

Unsupervised learning using bottom-up recognition models.

  • Richard S. Zemel and Geoffrey E. Hinton. Learning Population Codes by Minimizing Description Length. 1995. Neural Computation, 7:549-564. [PDF]

1994

Helmholtz Machines
  •  Geoffrey E. Hinton and Richard S. Zemel. Autoencoders, Minimum Description Length, and Helmholtz Free Energy. 1994. inAdvances in Neural Information Processing Systems 6[PDF]

Combining Discriminative Features To Infer Complex Trajectories

A conditional model for time-series regression.

Multiple-Cause Vector Quantization

Learning parts-based models of data.

Glove-Talk

A neural network that converts gestures into real-time speech.

Elastic Models

Using deformable models to recognize hand-written digits.