activity
20172021
most citedImproving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients

280 citations · 387 across the 9 of their papers we have counts for

collaborators
Showing 2018Show all

3 papers · 1 filter

cs.LG2018

Training Machine Learning Models by Regularizing their Explanations

Andrew Slavin Ross

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when…

cs.LG2018★ 7 cited

Learning Qualitatively Diverse and Interpretable Rules for Classification

Andrew Slavin Ross, Weiwei Pan, Finale Doshi-Velez

There has been growing interest in developing accurate models that can also be explained to humans. Unfortunately, if there exist multiple distinct but accurate models for some dat…

stat.ML2018★ 44 cited

Human-in-the-Loop Interpretability Prior

Isaac Lage, Andrew Slavin Ross, Been Kim +2

We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability…