Dr. Sumedha Singla, University of Pittsburgh
Causal Analysis for Interpretability
Sumedha gave this talk for the course on October 2021, during the last year of her Ph.D. In the talk, she explains her latest work about explaining black-boxes such as Deep Neural Networks in a smooth way by using counterfactuals and causal analysis.
NO ASSIGNMENTS
References
1. Singla S, Pollack B, Chen J, Batmanghelich K. Explanation by Progressive Exaggeration. In International Conference on Learning Representations 2019 Sep 25
2. Singla S, Pollack B, Wallace S, Batmanghelich K. Explaining the black-box smoothly – A counterfactual approach. Under review.
Introduction to AI Interpretability 