Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
A Closer Look at Codistillation for Distributed Training

Oct 06, 2020
Shagun Sodhani, Olivier Delalleau, Mahmoud Assran, Koustuv Sinha, Nicolas Ballas, Michael Rabbat

* Under review 

  Access Paper or Ask Questions

Revisiting Loss Modelling for Unstructured Pruning

Jun 22, 2020
CĂ©sar Laurent, Camille Ballas, Thomas George, Nicolas Ballas, Pascal Vincent


  Access Paper or Ask Questions

Recovering Petaflops in Contrastive Semi-Supervised Learning of Visual Representations

Jun 18, 2020
Mahmoud Assran, Nicolas Ballas, Lluis Castrejon, Michael Rabbat


  Access Paper or Ask Questions

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

Oct 01, 2019
Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Michael Rabbat


  Access Paper or Ask Questions

Needles in Haystacks: On Classifying Tiny Objects in Large Images

Aug 16, 2019
Nick Pawlowski, Suvrat Bhooshan, Nicolas Ballas, Francesco Ciompi, Ben Glocker, Michal Drozdzal


  Access Paper or Ask Questions

Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

Jun 09, 2019
Mahmoud Assran, Joshua Romoff, Nicolas Ballas, Joelle Pineau, Mike Rabbat


  Access Paper or Ask Questions

Improved Conditional VRNNs for Video Prediction

Apr 27, 2019
Lluis Castrejon, Nicolas Ballas, Aaron Courville

* Project page: https://sites.google.com/view/videovrnn 

  Access Paper or Ask Questions

Stochastic Gradient Push for Distributed Deep Learning

Nov 27, 2018
Mahmoud Assran, Nicolas Loizou, Nicolas Ballas, Michael Rabbat


  Access Paper or Ask Questions

Three Factors Influencing Minima in SGD

Sep 13, 2018
Stanisław Jastrzębski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

* First two authors contributed equally. Short version accepted into ICLR workshop. Accepted to Artificial Neural Networks and Machine Learning, ICANN 2018 

  Access Paper or Ask Questions

DNN's Sharpest Directions Along the SGD Trajectory

Jul 13, 2018
Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

* Short version accepted into Modern Trends in Nonconvex Optimization for Machine Learning workshop at International Conference on Machine Learning 2018 

  Access Paper or Ask Questions

A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning

Jun 25, 2018
Amy Zhang, Nicolas Ballas, Joelle Pineau

* 20 pages, 16 figures 

  Access Paper or Ask Questions

Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis

Jun 11, 2018
Thomas George, CĂ©sar Laurent, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent


  Access Paper or Ask Questions

Residual Connections Encourage Iterative Inference

Mar 08, 2018
Stanisław Jastrzębski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio

* First two authors contributed equally. Published in ICLR 2018 

  Access Paper or Ask Questions

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

Sep 22, 2017
David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Aaron Courville, Chris Pal

* David Krueger and Tegan Maharaj contributed equally to this work 

  Access Paper or Ask Questions

A Closer Look at Memorization in Deep Networks

Jul 01, 2017
Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, Simon Lacoste-Julien

* Appears in Proceedings of the 34th International Conference on Machine Learning (ICML 2017), Devansh Arpit, Stanis{\l}aw Jastrz\k{e}bski, Nicolas Ballas, and David Krueger contributed equally to this work 

  Access Paper or Ask Questions

Recurrent Batch Normalization

Feb 28, 2017
Tim Cooijmans, Nicolas Ballas, César Laurent, Çağlar Gülçehre, Aaron Courville


  Access Paper or Ask Questions

A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering

Feb 05, 2017
Tegan Maharaj, Nicolas Ballas, Anna Rohrbach, Aaron Courville, Christopher Pal


  Access Paper or Ask Questions

Oracle performance for visual captioning

Sep 14, 2016
Li Yao, Nicolas Ballas, Kyunghyun Cho, John R. Smith, Yoshua Bengio

* BMVC2016 (Oral paper) 

  Access Paper or Ask Questions

Dynamic Capacity Networks

May 22, 2016
Amjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, Aaron Courville

* ICML 2016 

  Access Paper or Ask Questions

Theano: A Python framework for fast computation of mathematical expressions

May 09, 2016
The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre-Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Mélanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian Goodfellow, Matt Graham, Caglar Gulcehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrancois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert T. McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang

* 19 pages, 5 figures 

  Access Paper or Ask Questions

Delving Deeper into Convolutional Networks for Learning Video Representations

Mar 01, 2016
Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville

* ICLR 2016 

  Access Paper or Ask Questions

Describing Videos by Exploiting Temporal Structure

Oct 01, 2015
Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, Aaron Courville

* Accepted to ICCV15. This version comes with code release and supplementary material 

  Access Paper or Ask Questions

FitNets: Hints for Thin Deep Nets

Mar 27, 2015
Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, Yoshua Bengio


  Access Paper or Ask Questions