Soufiane Hayou

Artificial Intelligence · 2018–2024

A researcher in the Science corpus: 3 papers; trusts 84 researchers and is trusted by 4 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 62 citations into it; #21,852 of 35,345 by trust here, #22,463 by citations
• Model Architectures — 25 citations into it; #1,519 of 2,278 by trust here, #1,927 by citations
• Computer Vision and Pattern Recognition — 24 citations into it; #13,679 of 21,575 by trust here, #15,955 by citations
• Scaling & Learning Theory — 20 citations into it
• Optimization & Training — 19 citations into it; #1,851 of 2,601 by trust here, #2,052 by citations
• Statistical and Nonlinear Physics — 17 citations into it
• Large Language Models — 9 citations into it
• Statistical Learning Theory — 7 citations into it

Whom Soufiane Hayou trusts overall

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

1. Greg Yang
2. Kaiming He
3. Yann LeCun
4. Geoffrey E. Hinton
5. Yoshua Bengio
6. Sam Schoenholz
7. Dan Hendrycks
8. Diederik P. Kingma
9. Alex Krizhevsky
10. Radford M. Neal

Who trusts Soufiane Hayou overall

1. Greg Yang
2. Lechao Xiao
3. Jeffrey Pennington
4. Sam Schoenholz
5. Yasaman Bahri

Papers from Soufiane Hayou's perspective

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

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

Their papers

• On the Selection of Initialization and Activation Function for Deep Neural Networks (2018) — 77 citations
• LoRA+: Efficient Low Rank Adaptation of Large Models (2024) — 442 citations
• Mean-field Behaviour of Neural Tangent Kernel for Deep Neural Networks (2019) — 35 citations