Alhussein Fawzi
Artificial Intelligence · 2015–2023
A researcher in the Science corpus: 19 papers; trusts 932 researchers and is trusted by 1,935 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 258 citations into it; #1,035 of 36,961 by trust here, #1,068 by citations
- Computer Vision and Pattern Recognition — 144 citations into it; #1,399 of 21,973 by trust here, #1,044 by citations
- Safety, Robustness & Interpretability — 131 citations into it; #21 of 2,259 by trust here, #40 by citations
- Model Architectures — 33 citations into it
- Signal Processing — 33 citations into it
- Optimization & Training — 30 citations into it
- Computational Theory and Mathematics — 28 citations into it
- Representation & Self-Supervised Learning — 27 citations into it
Whom Alhussein Fawzi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yann LeCun
- Yoshua Bengio
- Karen Simonyan
- Christian Szegedy
- Diederik P. Kingma
- Ian J. Goodfellow
- Ilya Sutskever
- Kaiming He
Who trusts Alhussein Fawzi overall
- Seyed-Mohsen Moosavi-Dezfooli
- Nicholas Carlini
- Dimitris Tsipras
- Elvis Dohmatob
- Naveed Akhtar
- Florian Tramèr
- Matthias Hein
- Moustapha Cissé
- Logan Engstrom
- Nina Narodytska
Papers from Alhussein Fawzi's perspective
Ordered by how strongly the researchers Alhussein Fawzi trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks (2015) — 5,469 citations
- Universal Adversarial Perturbations (2016) — 2,828 citations
- Analysis of classifiers’ robustness to adversarial perturbations (2015) — 386 citations
- Robustness of classifiers: from adversarial to random noise (2016) — 405 citations
- Are Labels Required for Improving Adversarial Robustness? (2019) — 361 citations
- Adversarial Robustness through Local Linearization (2019) — 333 citations
- Adversarial vulnerability for any classifier (2018) — 273 citations
- Manitest: Are classifiers really invariant? (2015) — 120 citations
- Analysis of universal adversarial perturbations (2017) — 122 citations
- Empirical Study of the Topology and Geometry of Deep Networks (2018) — 157 citations
- Robustness via Curvature Regularization, and Vice Versa (2018) — 345 citations
- Mathematical discoveries from program search with large language models (2023) — 1,101 citations
- Fundamental limits on adversarial robustness (2015) — 58 citations
- Analysis of classifiers’ robustness to adversarial perturbations (2017)
- Discovering faster matrix multiplication algorithms with reinforcement learning (2022) — 714 citations
- Learning dynamic polynomial proofs (2019) — 18 citations
- Robustness of classifiers to uniform 𝓁p and Gaussian noise (2018) — 31 citations
- Robustness of classifiers to uniform $\ell_p$ and Gaussian noise (2018) — 21 citations
- Image inpainting through neural networks hallucinations (2016) — 31 citations