activity
20152026
most citedTowards A Rigorous Science of Interpretable Machine Learning

3.2k citations · 4.3k across the 100 of their papers we have counts for

collaborators
Showing 2017Show all

14 papers · 1 filter

cs.LG2017★ 5 cited

Prediction-Constrained Topic Models for Antidepressant Recommendation

Michael C. Hughes, Gabriel Hope, Leah Weiner +4

Supervisory signals can help topic models discover low-dimensional data representations that are more interpretable for clinical tasks. We propose a framework for training supervis…

cs.LG2017★ 280 cited

Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients

Andrew Slavin Ross, Finale Doshi-Velez

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their…

stat.ML2017★ 104 cited

Beyond Sparsity: Tree Regularization of Deep Models for Interpretability

Mike Wu, Michael C. Hughes, Sonali Parbhoo +3

The lack of interpretability remains a key barrier to the adoption of deep models in many applications. In this work, we explicitly regularize deep models so human users might step…

cs.AI2017

Accountability of AI Under the Law: The Role of Explanation

Finale Doshi-Velez, Mason Kortz, Ryan Budish +9

The ubiquity of systems using artificial intelligence or "AI" has brought increasing attention to how those systems should be regulated. The choice of how to regulate AI systems wi…

stat.ML2017

Weighted Tensor Decomposition for Learning Latent Variables with Partial Data

Omer Gottesman, Weiwei Pan, Finale Doshi-Velez

Tensor decomposition methods are popular tools for learning latent variables given only lower-order moments of the data. However, the standard assumption is that we have sufficient…

stat.ML2017

Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning

Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez +1

Bayesian neural networks with latent variables are scalable and flexible probabilistic models: They account for uncertainty in the estimation of the network weights and, by making…