Stéphane d'Ascoli

Artificial Intelligence · 2018–2022

A researcher in the Science corpus: 8 papers; trusts 76 researchers and is trusted by 7 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 184 citations into it; #35,194 of 35,345 by trust here, #6,848 by citations
• Scaling & Learning Theory — 117 citations into it; #240 of 428 by trust here, #181 by citations
• Optimization & Training — 95 citations into it
• Computer Vision and Pattern Recognition — 90 citations into it
• Model Architectures — 64 citations into it
• Statistical and Nonlinear Physics — 46 citations into it
• AI for Physical Sciences — 45 citations into it
• Materials Chemistry — 43 citations into it

Whom Stéphane d'Ascoli trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Yann LeCun
4. Diederik P. Kingma
5. Yoshua Bengio
6. Kaiming He
7. Ilya Sutskever
8. Jimmy Ba
9. Radford M. Neal
10. Alex Graves

Who trusts Stéphane d'Ascoli overall

1. Mario Geiger
2. Sachin Mehta
3. Yang He
4. Manoj Kumar
5. Da-Wei Zhou
6. Stefano Spigler
7. Pavan Kumar Anasosalu Vasu
8. Xiangxiang Chu
9. Yawei Li
10. Ali Hassani

Papers from Stéphane d'Ascoli's perspective

Ordered by how strongly the researchers Stéphane d'Ascoli 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. Gradient-based learning applied to document recognition
6. Long Short-Term Memory
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• ConViT: improving vision transformers with soft convolutional inductive biases (2021) — 1,066 citations
• Scaling description of generalization with number of parameters in deep learning (2019) — 214 citations
• Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias (2019) — 37 citations
• A jamming transition from under- to over-parametrization affects generalization in deep learning (2018) — 160 citations
• End-to-end symbolic regression with transformers (2022) — 295 citations
• Triple descent and the two kinds of overfitting: where and why do they appear? (2020) — 91 citations
• The jamming transition as a paradigm to understand the loss landscape of deep neural networks (2018) — 157 citations
• A jamming transition from under- to over-parametrization affects loss landscape and generalization (2018) — 59 citations