Sarah Tan

Artificial Intelligence · with Caruana · 2016–2018

A researcher in the Science corpus: 7 papers; trusts 109 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 155 citations into it; #15,181 of 35,345 by trust here, #13,760 by citations
• Safety, Robustness & Interpretability — 88 citations into it; #1,125 of 2,251 by trust here, #1,265 by citations
• Statistics and Probability — 54 citations into it
• Computer Vision and Pattern Recognition — 26 citations into it
• Safety Research — 25 citations into it; #3,289 of 5,829 by trust here, #2,344 by citations
• AI Ethics, Fairness & Society — 24 citations into it
• Statistical Learning Theory — 15 citations into it
• Optimization & Training — 14 citations into it

Whom Sarah Tan trusts overall

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

1. R. Caruana
2. Geoffrey E. Hinton
3. Yin Lou
4. Robert Tibshirani
5. Yann LeCun
6. Giles Hooker
7. Jerome H. Friedman
8. Trevor J. Hastie
9. Alex Krizhevsky
10. Jimmy Ba

Who trusts Sarah Tan overall

1. Giles Hooker
2. Amina Adadi
3. Yujia Zhang
4. Lucas K. Mentch
5. Riccardo Guidotti
6. Mohammed Berrada
7. Kuangyan Song
8. Dino Pedreschi
9. Cynthia Rudin
10. Seonguk Park

Papers from Sarah Tan's perspective

Ordered by how strongly the researchers Sarah Tan 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. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation (2017) — 212 citations
• Learning Global Additive Explanations for Neural Nets Using Model Distillation (2018) — 112 citations
• Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models (2018) — 3 citations
• Interpretable Approaches to Detect Bias in Black-Box Models (2018) — 6 citations
• Transparent Model Distillation (2018) — 38 citations
• Auditing Black-Box Models Using Transparent Model Distillation With Side Information (2017) — 18 citations
• Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable (2016) — 79 citations