AUTHOR=Anirudh Rushil , Thiagarajan Jayaraman J. , Sridhar Rahul , Bremer Peer-Timo TITLE=MARGIN: Uncovering Deep Neural Networks Using Graph Signal Analysis JOURNAL=Frontiers in Big Data VOLUME=4 YEAR=2021 URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2021.589417 DOI=10.3389/fdata.2021.589417 ISSN=2624-909X ABSTRACT=
Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are otherwise opaque to a user. There are a plethora of existing solutions addressing various aspects of interpretability ranging from identifying prototypical samples in a dataset to explaining image predictions or explaining mis-classifications. While all of these diverse techniques address seemingly different aspects of interpretability, we hypothesize that a large family of interepretability tasks are variants of the same central problem which is identifying