Ankur Taly

Artificial Intelligence · 2016–2019

A researcher in the Science corpus: 8 papers; trusts 366 researchers and is trusted by 242 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 132 citations into it; #1,338 of 35,345 by trust here, #1,878 by citations
• Safety, Robustness & Interpretability — 98 citations into it; #2,086 of 2,251 by trust here, #1,148 by citations
• Computer Vision and Pattern Recognition — 63 citations into it; #19,200 of 21,575 by trust here, #11,721 by citations
• Natural Language Processing — 33 citations into it; #423 of 5,688 by trust here, #496 by citations
• Safety Research — 19 citations into it; #5,042 of 5,829 by trust here, #827 by citations
• Evaluation & Benchmarks — 11 citations into it
• Management Science and Operations Research — 10 citations into it
• Model Architectures — 10 citations into it

Whom Ankur Taly trusts overall

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

1. Karen Simonyan
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alex Krizhevsky
5. Avanti Shrikumar
6. Ilya Sutskever
7. Yann LeCun
8. Christian Szegedy
9. Diederik P. Kingma
10. Mukund Sundararajan

Who trusts Ankur Taly overall

1. Umang Bhatt
2. Mukund Sundararajan
3. Wojciech Samek
4. Frederick Liu
5. Laura Rieger
6. Marco Ancona
7. Been Kim
8. Scott M. Lundberg
9. Mengnan Du
10. Xisen Jin

Papers from Ankur Taly's perspective

Ordered by how strongly the researchers Ankur Taly 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. Long Short-Term Memory
5. Gradient-based learning applied to document recognition
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. ImageNet Large Scale Visual Recognition Challenge
9. Going deeper with convolutions
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Axiomatic Attribution for Deep Networks (2017) — 8,293 citations
• Counterfactual Fairness in Text Classification through Robustness (2018) — 294 citations
• Explainable machine learning in deployment (2019) — 701 citations
• Did the Model Understand the Question? (2018) — 206 citations
• Using a Deep Learning Algorithm and Integrated Gradients Explanation to Assist Grading for Diabetic Retinopathy. (2019) — 379 citations
• The Explanation Game: Explaining Machine Learning Models with Cooperative Game Theory (2019) — 34 citations
• A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values (2018) — 22 citations
• Gradients of Counterfactuals (2016) — 115 citations