124 citations · 344 across the 42 of their papers we have counts for
3 papers · 2 filters
Explainable Machine Learning in Deployment
Umang Bhatt, Alice Xiang, Shubham Sharma +7
Explainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactu…
Towards Aggregating Weighted Feature Attributions
Umang Bhatt, Pradeep Ravikumar, Jose M. F. Moura
Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances…
On Network Science and Mutual Information for Explaining Deep Neural Networks
Brian Davis, Umang Bhatt, Kartikeya Bhardwaj +2
In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforwar…