Sara Hooker
Artificial Intelligence · 2017–2023
A researcher in the Science corpus: 17 papers; trusts 1,766 researchers and is trusted by 104 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 654 citations into it; #4,397 of 36,961 by trust here, #3,146 by citations
- Computer Vision and Pattern Recognition — 343 citations into it; #4,731 of 21,973 by trust here, #2,896 by citations
- Safety, Robustness & Interpretability — 266 citations into it; #709 of 2,259 by trust here, #308 by citations
- Efficiency & Compression — 140 citations into it; #216 of 1,273 by trust here, #396 by citations
- Natural Language Processing — 124 citations into it
- Evaluation & Benchmarks — 74 citations into it; #2,048 of 3,155 by trust here, #1,486 by citations
- Safety Research — 62 citations into it; #3,015 of 5,835 by trust here, #1,666 by citations
- Model Architectures — 60 citations into it
Whom Sara Hooker trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Yann LeCun
- Diederik P. Kingma
- Karen Simonyan
- Yoshua Bengio
- Ilya Sutskever
- Christian Szegedy
- Ross B. Girshick
Who trusts Sara Hooker overall
- N. Ahmed
- Mostafa Dehghani
- Tri Dao
- Laura Rieger
- Charlie Blake
- Harini Suresh
- Suraj Srinivas
- Josh Cowls
- Beidi Chen
- Yi Tay
Papers from Sara Hooker's perspective
Ordered by how strongly the researchers Sara Hooker 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)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- The State of Sparsity in Deep Neural Networks (2019) — 891 citations
- Evaluating the Social Impact of Generative AI Systems in Systems and Society (2023) — 177 citations
- The (Un)reliability of saliency methods (2017) — 806 citations
- On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research (2023) — 59 citations
- A Benchmark for Interpretability Methods in Deep Neural Networks (2018) — 879 citations
- Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020) — 480 citations
- Moving beyond “algorithmic bias is a data problem” (2021) — 193 citations
- Randomness In Neural Network Training: Characterizing The Impact of Tooling (2021) — 97 citations
- Selective Brain Damage: Measuring the Disparate Impact of Model Pruning (2019) — 38 citations
- Evaluating Feature Importance Estimates (2018) — 104 citations
- Characterising Bias in Compressed Models (2020) — 211 citations
- What Do Compressed Deep Neural Networks Forget (2019) — 221 citations
- The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation (2021) — 64 citations
- The hardware lottery (2020) — 287 citations
- FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling (2023) — 16 citations
- Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics (2022) — 36 citations
- Intriguing Properties of Compression on Multilingual Models (2022) — 16 citations