Been Kim (Google Brain) gave us a talk on her work on interpretability of machine learning

In our second seminar of this term Professor Been Kim from Google Brain shared her work and insights in this talk: "Interpretability, the past, present and future".

Speaker bio:

Been 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 at conferences including NeurIPS, ICML, ICLR, and AISTATS. She received her PhD. from MIT.

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.