Sophie Hilgard

Safety, Robustness & Interpretability · 2019

A researcher in the Science corpus: 2 papers; trusts 7 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Safety, Robustness & Interpretability — 27 citations into it
• Artificial Intelligence — 25 citations into it

Whom Sophie Hilgard trusts overall

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

1. Marco Tulio Ribeiro
2. Scott M. Lundberg
3. Been Kim
4. Cynthia Rudin
5. Zachary Chase Lipton
6. Sameer Singh

Who trusts Sophie Hilgard overall

1. Cynthia Rudin
2. Sarah Wiegreffe
3. Guy Van den Broeck

Papers from Sophie Hilgard's perspective

Ordered by how strongly the researchers Sophie Hilgard trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. ImageNet Large Scale Visual Recognition Challenge
6. The mythos of model interpretability
7. Attention is All you Need (Neural Information Processing Systems)
8. Association for Computational Linguistics " Why Should I Trust You? " Explaining the Predictions of Any Classifier
9. Going deeper with convolutions
10. Long Short-Term Memory

Their papers

• Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods (2019) — 1,143 citations
• How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods (2019) — 70 citations