Ethan Fetaya

I'm a postdoctoral fellow in the machine learning group at the University of Toronto, working with Rich Zemel and Max Welling. I am interested in deep learning, reasoning using knowledge graphs and modeling complex dynamical behaviour.

Previously, I did my PhD at the Weizmann Inst. under the supervision of Shimon Ullman in computer vision.

I did my M.Sc in mathematics at the Hebrew University under the supervision of Alex Lubotzky on Homological Error Correcting Codes and Systolic Geometry.

Email: ethanf [AT] cs [DOT] toronto [DOT] edu

Publications


Learning Discrete Weights Using the Local Reparameterization Trick.

Preprint.

Oran Shayer, Dan Levi, Ethan Fetaya. [Arxiv]


Real-time category-based and general obstacle detection for autonomous driving.

ICCV workshop, 2017.

Noa Garnett, Shai Silberstein, Shaul Oron, Ethan Fetaya, Uri Verner, Ariel Ayash, Vlad Goldner, Rafi Cohen, Kobi Horn, Dan Levi. [Paper]


Human Pose Estimation using Deep Consensus Voting.

European Conference on Computer Vision (ECCV), 2016.

Ita Lifshitz*, Ethan Fetaya*, Shimon Ullman. [Paper, Arxiv, Code , Poster ]
*equal contribution


Atoms of recognition in human and computer vision.

Proceedings of the National Academy of Sciences (PNAS), 2016.

Shimon Ullman, Liav Assif, Ethan Fetaya, and Daniel Harari. [Paper]


Unsupervised Ensemble Learning with Dependent Classifiers.

International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.

Ariel Jaffe, Ethan Fetaya, Boaz Nadler, Tingting Jiang, and Yuval Kluger.[Paper, Supplementary]


StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation.

British Machine Vision Conference (BMVC), 2015.

Dan Levi, Noa Garnett and Ethan Fetaya. [Paper]


Learning Local Invariant Mahalanobis Distances.

International Conference on Machine Learning (ICML), 2015.

Ethan Fetaya and Shimon Ullman. [Paper]


Graph Approximation and Clustering on a Budget.

International Conference on Artificial Intelligence and Statistics (AISTATS), 2015.

Ethan Fetaya, Ohad Shamir and Shimon Ullman. [Paper, Supplementary ]


Bounding the distance of quantum surface codes.

Journal of Mathematical Physics, 2012.

Ethan Fetaya. [Paper]


Homological Error Correcting Codes and Systolic Geometry.

M.Sc Thesis.

Ethan Fetaya. [Arxiv]


Teaching

  • CSC411: Machine Learning and Data Mining, University of Toronto, Fall 2017

  • Introduction to Statistical Learning Theory, Weizmann Institute, Spring 2016

  • Introduction to Statistical Learning Theory, Weizmann Institute, Spring 2015