CMU Artificial Intelligence Seminar Series sponsored by Fortive
Tuesday, Mar 30, 2021
Time: 02:00 - 03:00 PM ET
Been Kim -- Interpretability, the Past, Present and Future
Relevant Paper(s):
- Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
- Sanity Checks for Saliency Maps
- Towards Automatic Concept-based Explanations
- Explaining Classifiers with Causal Concept Effect (CaCE)
- Concept Bottleneck Models
- On Completeness-aware Concept-Based Explanations in Deep Neural Networks
Abstract: Interpretable machine learning has been a popular topic of study in the past many years. But are we making progress? In this talk, I will talk about my reflections on the progress by taking a critical look at some of the existing methods, and discussing series of user-centric methods that can "speak" the user's language, rather than the computer's language.
Bio: Been Kim is a staff research scientist at Google Brain. Her research focuses on improving interpretability in machine learning by building interpretability methods for already-trained models or building inherently interpretable models. She gave a talk at the G20 meeting in Argentina in 2019. Her work TCAV received UNESCO Netexplo award, was featured at Google I/O 19' and in Brian Christian's book on "The Alignment Problem". Been has given keynote at ECML 2020, tutorials on interpretability at ICML, University of Toronto, CVPR and at Lawrence Berkeley National Laboratory. She was a co-workshop Chair ICLR 2019, and has been an area chair/senior area chair at conferences including NeurIPS, ICML, ICLR, and AISTATS. She received her Ph.D. from MIT.