Andrew Slavin Ross

Identifiers

No identifiers captured yet.

Papers (5)

1. Training Machine Learning Models by Regularizing their Explanations cs.LG · 2018 · author #1
2. Learning Qualitatively Diverse and Interpretable Rules for Classification cs.LG · 2018 · author #1
3. Human-in-the-Loop Interpretability Prior stat.ML · 2018 · author #2
4. Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients cs.LG · 2017 · author #1
5. Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations cs.LG · 2017 · author #1

Mentions

No mention provenance yet.

Frequent Coauthors

• Finale Doshi-Velez 4 shared papers
• Been Kim 1 shared papers
• Isaac Lage 1 shared papers
• Michael C. Hughes 1 shared papers
• Samuel J. Gershman 1 shared papers
• Weiwei Pan 1 shared papers