Samira Ebrahimi Kahou
Professor
Department of Software and IT Engineering
I am a postdoctoral researcher at McGill/Mila working with Professor Doina Precup. My current research interests are multimodal learning, reasoning across modalities, metalearning and in general efficient representation learning. I also work on deep learning methods for dialogue systems and humanitarian AI.
I was on maternity leave from May 2018 to February 2019.
Before my postdoc, I was a researcher at Microsoft Research Montréal.
I received my Ph.D. from Polytechnique Montréal/Mila in 2016 under the supervision of Professor Chris Pal. During my Ph.D. studies, I worked on computer vision and deep learning applied to emotion recognition, object tracking and knowledge distillation.
Feel free to reach out, if you’re interested in my research and would like to discuss.
+ Original articles in refereed journals and books chapters
«Keep Drawing It : Iterative language-based image generation and editing»El-nouby, Alaaeldin and Sharma, Shikhar and Schulz, Hannes and Hjelm, Devon and Asri, Layla El and Kahou, Samira Ebrahimi and Bengio, Yoshua and Taylor, Graham W.” NIPS 2018 Workshop on ViGIL 2018. |
«Do deep convolutional nets really need to be deep and convolutional?»Urban, Gregor and Geras, Krzysztof J. and Kahou, Samira Ebrahimi and Aslan, Ozlem and Wang, Shengjie and Mohamed, Abdelrahman and Philipose, Matthai and Richardson, Matt and Caruana, Rich” 2017. |
«Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints, abs/1605.02688»Al-Rfou, Rami and Alain, Guillaume and Almahairi, Amjad and Angermueller, Christof and Bahdanau, Dzmitry and Ballas, N and Bastien, F and Bayer, J and Belikov, A and Belopolsky, A and Others” URL http://arxiv. org/abs/1605.02688 2016. |
«ARTICLE 3: RATM: RECURRENT ATTENTIVE TRACKING MODEL»Kahou, S E and Michalski, V and …” łdots WITH DEEP NEURAL łdots 2016. |
«Image compression: Comparative analysis of basic algorithms»Sulema, Yevgeniya and Kahou, Samira Ebrahimi” Proceedings of IEEE East-West Design and Test Symposium, EWDTS\’10 2010. |
Read More >
+ Papers in refereed conference proceedings
«Dead-ends and secure exploration in reinforcement learning»Fatemi, Mehdi and Sharma, Shikhar and van Seijen, Harm and Kahou, Samira Ebrahimi” 36th International Conference on Machine Learning, ICML 2019 2019. |
«Deep-hurricane-tracker: Tracking and forecasting extreme climate events»Kim, Sookyung and Kim, Hyojin and Lee, Joonseok and Yoon, Sangwoong and Kahou, Samira E. and Kashinath, Karthik and Prabhat” Proceedings – 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019 2019. |
«Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction»El-Nouby, Alaaeldin and Sharma, Shikhar and Schulz, Hannes and Hjelm, Devon and Asri, Layla El and Kahou, Samira Ebrahimi and Bengio, Yoshua and Taylor, Graham W.” arXiv 2018. |
«RATM: Recurrent Attentive Tracking Model»Kahou, Samira Ebrahimi and Michalski, Vincent and Memisevic, Roland and Pal, Christopher and Vincent, Pascal” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2017. |
«FitNets: Hints for thin deep nets»Romero, Adriana and Ballas, Nicolas and Kahou, Samira Ebrahimi and Chassang, Antoine and Gatta, Carlo and Bengio, Yoshua” 3rd Internatiohttps://liviamtl.ca/wp-admin/post.php?post=26361&action=edit&classic-editor=1#savenal Conference on Learning Representations, ICLR 2015 – Conference Track Proceedings 2015. |
Samira
Ebrahimi Kahou
Research & Innovation
Contact Us
Pavillon Principal (A)
1100, rue Notre-Dame Ouest
Montréal, QC, H3C 1K3
Room A-3600
Tel.: +1 (514) 396-8650
E-Mail: eric.granger@etsmtl.ca