Michael P. Kim

Artificial Intelligence · 2017–2018

A researcher in the Science corpus: 5 papers; trusts 50 researchers and is trusted by 30 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 70 citations into it; #10,873 of 35,345 by trust here, #11,327 by citations
• Safety, Robustness & Interpretability — 47 citations into it
• Statistical Learning Theory — 22 citations into it
• Safety Research — 22 citations into it; #3,279 of 5,829 by trust here, #2,279 by citations
• AI Ethics, Fairness & Society — 16 citations into it; #37 of 494 by trust here, #57 by citations
• Computer Vision and Pattern Recognition — 15 citations into it
• Optimization & Training — 15 citations into it; #2,175 of 2,601 by trust here, #1,766 by citations
• Sociology and Political Science — 15 citations into it

Whom Michael P. Kim trusts overall

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

1. Moritz Hardt
2. Cynthia Dwork
3. Michael Kearns
4. Vitaly Feldman
5. Alexandra Chouldechova
6. Jerome H. Friedman
7. Guy N. Rothblum
8. Adam Tauman Kalai
9. Avrim Blum
10. Leslie G. Valiant

Who trusts Michael P. Kim overall

1. Luca Oneto
2. Elliot Creager
3. Michael Kearns
4. Silvia Chiappa
5. Aaron Roth
6. Alexandra Chouldechova
7. Jörn-Henrik Jacobsen
8. Guy N. Rothblum
9. Amanda Coston
10. Cynthia Dwork

Papers from Michael P. Kim's perspective

Ordered by how strongly the researchers Michael P. Kim 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. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. ImageNet: A large-scale hierarchical image database
6. Learning Multiple Layers of Features from Tiny Images
7. Attention is All you Need (Neural Information Processing Systems)
8. Long Short-Term Memory
9. Going deeper with convolutions
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Multiaccuracy: Black-Box Post-Processing for Fairness in Classification (2018) — 404 citations
• Fairness Through Computationally-Bounded Awareness (2018) — 154 citations
• Calibration for the (Computationally-Identifiable) Masses (2017) — 92 citations
• Multicalibration: Calibration for the (Computationally-Identifiable) Masses (2018) — 504 citations
• Multiaccuracy : Black-Box Post-Processing for Fairness in Classi cation (2018)