Mohammad Norouzi

Research Scientist on the Brain team
at Google in Mountain View
mnorouzi[at]google[.]com

Currently, I am highlighting:

My research lies at the intersection of machine learning, computer vision, and natural language processing with an emphasis on neural networks and reinforcement learning. My current research focuses on 1) learning better neural network models of structured outputs and sequences. 2) developing better reinforcement learning algorithms.

I graduated with a PhD in computer science from the University of Toronto in Dec 2015. My advisor was David Fleet. My thesis concerns scalable and efficient algorithms for processing, indexing, and searching digital media, to facilitate the use of web-scale datasets in computer vision. My PhD research was supported by a Google PhD fellowship.

Google scholar profile
GitHub page

Publications

Reward Augmented Maximum Likelihood for Neural Structured Prediction
Mohammad Norouzi, Samy Bengio, Zhifeng Chen, Navdeep Jaitly, Mike Schuster, Yonghui Wu, Dale Schuurmans
Neural Information Processing Systems (NIPS), 2016. [pdf]

Compact Discrete Representations for Scalable Similarity Search
Mohammad Norouzi, PhD thesis, 2016. [pdf]

Efficient Non-greedy Optimization of Decision Trees
Mohammad Norouzi, Maxwell D. Collins, Matthew Johnson, David J. Fleet, Pushmeet Kohl,
Neural Information Processing Systems (NIPS), 2015. [pdf]

CO2 Forest: Improved Random Forest by Continuous Optimization of Oblique Splits
Mohammad Norouzi, Maxwell D. Collins, David J. Fleet, Pushmeet Kohli,
Preprint on ArXiv, 2015. [pdf]

Zero-Shot Learning by Convex Combination of Semantic Embeddings
Mohammad Norouzi, Tomas Mikolov, Samy Bengio, Yoram Singer, Jonathon Shlens, Andrea Frome, Greg S. Corrado, Jeffrey Dean,
International Conference on Learning Representations (ICLR) 2014. [pdf] [slides:pptx] [dataset: 2-hop, 3-hop]

Fast Exact Search in Hamming Space with Multi-Index Hashing,
Mohammad Norouzi, Ali Punjani, David J. Fleet,
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 36, no. 6, 2014. [pdf] [code]

Cartesian k-means,
Mohammad Norouzi, David J. Fleet,
IEEE Computer Vision and Pattern Recognition (CVPR), 2013. [pdf] [code] [slides:ppt/pptx]

Hamming Distance Metric Learning,
Mohammad Norouzi, David J. Fleet, Ruslan Salakhutdinov,
Neural Information Processing Systems (NIPS), 2012. [pdf] [code] [supplemental] [poster]

Fast Search in Hamming Space with Multi-Index Hashing,
Mohammad Norouzi, Ali Punjani, David J. Fleet,
IEEE Computer Vision and Pattern Recognition (CVPR), 2012. [pdf] [code] [poster]

Minimal Loss Hashing for Compact Binary Codes,
Mohammad Norouzi, David J. Fleet,
International Conference in Machine Learning (ICML), 2011. [pdf] [code] [slides:ppt]

Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning,
Mohammad Norouzi, Mani Ranjbar, Greg Mori,
IEEE Computer Vision and Pattern Recognition (CVPR), 2009. [pdf]
Extended version: Master's thesis at Simon Fraser University, 2009. [pdf] [slides:ppt]


Recorded talks

[18 mins] Zero-Shot Learning by Convex Combination of Semantic Embeddings at ICLR 2014

[13 mins] Cartesian k-means at CVPR 2013

[20 mins, lost!] Minimal Loss Hashing for Compact Binary Codes at ICML 2011

Previously

PhD student, Computer Science, University of Toronto
Advisor: David Fleet, Sep 2010 - Dec 2015 Teaching assistant for
CSC2503: Foundations of Computer Vision (Grad),
CSC411: Machine Learning and Data Mining,
CSC373: Algorithm Design, Analysis and Complexity,
CSC263: Data Structures and Analysis,
CSC236: Intro to Theory of Computation.

Research Intern, Google, Mountain View, CA USA.
Mentors: Samy Bengio, Yoram Singer - Summer 2013.

Research Intern, Microsoft Research, Cambridge UK.
Mentor: Pushmeet Kohli - Spring 2013.