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
Matthieu Courbariaux

DIRO

BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization

Feb 08, 2020
Miloš Nikolić, Ghouthi Boukli Hacene, Ciaran Bannon, Alberto Delmas Lascorz, Matthieu Courbariaux, Yoshua Bengio, Vincent Gripon, Andreas Moshovos


  Access Paper or Ask Questions

Attention Based Pruning for Shift Networks

May 29, 2019
Ghouthi Boukli Hacene, Carlos Lassance, Vincent Gripon, Matthieu Courbariaux, Yoshua Bengio


  Access Paper or Ask Questions

BNN+: Improved Binary Network Training

Dec 31, 2018
Sajad Darabi, Mouloud Belbahri, Matthieu Courbariaux, Vahid Partovi Nia


  Access Paper or Ask Questions

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

Sep 22, 2016
Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio

* arXiv admin note: text overlap with arXiv:1602.02830 

  Access Paper or Ask Questions

BinaryConnect: Training Deep Neural Networks with binary weights during propagations

Apr 18, 2016
Matthieu Courbariaux, Yoshua Bengio, Jean-Pierre David

* Accepted at NIPS 2015, 9 pages, 3 figures 

  Access Paper or Ask Questions

Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Mar 17, 2016
Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio

* 11 pages and 3 figures 

  Access Paper or Ask Questions

Neural Networks with Few Multiplications

Feb 26, 2016
Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic, Yoshua Bengio

* Published as a conference paper at ICLR 2016. 9 pages, 3 figures 

  Access Paper or Ask Questions

Training deep neural networks with low precision multiplications

Sep 23, 2015
Matthieu Courbariaux, Yoshua Bengio, Jean-Pierre David

* 10 pages, 5 figures, Accepted as a workshop contribution at ICLR 2015 

  Access Paper or Ask Questions