Matthieu Courbariaux

Artificial Intelligence · 2014–2016

A researcher in the Science corpus: 9 papers; trusts 383 researchers and is trusted by 936 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 125 citations into it; #1,133 of 35,345 by trust here, #1,301 by citations
• Computer Vision and Pattern Recognition — 123 citations into it; #1,521 of 21,575 by trust here, #1,005 by citations
• Model Architectures — 69 citations into it; #1,212 of 2,278 by trust here, #1,104 by citations
• Optimization & Training — 52 citations into it; #386 of 2,601 by trust here, #843 by citations
• ML Systems & Hardware — 49 citations into it
• Efficiency & Compression — 48 citations into it; #11 of 1,264 by trust here, #17 by citations
• Electrical and Electronic Engineering — 27 citations into it
• Hardware and Architecture — 24 citations into it

Whom Matthieu Courbariaux trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Yann LeCun
5. Alex Graves
6. Diederik P. Kingma
7. Ilya Sutskever
8. Xavier Glorot
9. Ian J. Goodfellow
10. Nitish Srivastava

Who trusts Matthieu Courbariaux overall

1. Tim Dettmers
2. Itay Hubara
3. Xundong Wu
4. Asit K. Mishra
5. Yoshua Bengio
6. Yu Cheng
7. Lu Hou
8. Arun Mallya
9. Philipp Gysel
10. Mohammad Rastegari

Papers from Matthieu Courbariaux's perspective

Ordered by how strongly the researchers Matthieu Courbariaux trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• BinaryConnect: Training Deep Neural Networks with binary weights during propagations (2015) — 3,245 citations
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations (2016) — 2,112 citations
• Binarized Neural Networks (2016) — 1,334 citations
• Low precision storage for deep learning (2014) — 51 citations
• BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 (2016) — 704 citations
• Binarized Neural Networks (2016) — 2,178 citations
• Neural Networks with Few Multiplications (2015) — 347 citations
• Training deep neural networks with low precision multiplications (2014) — 607 citations
• Low precision arithmetic for deep learning (2014) — 175 citations