MARGIN: Uncovering Deep Neural Networks Using Graph Signal Analysis

MARGIN: Uncovering Deep Neural Networks Using Graph Signal Analysis

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 rangi...

Full description

Bibliographic Details
Main Authors: Rushil Anirudh, Jayaraman J. Thiagarajan, Rahul Sridhar, Peer-Timo Bremer
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-05-01
Series:Frontiers in Big Data
Subjects:
graph signal processing
interpretability
influence sampling
adversarial attacks
machine learning
Online Access:https://www.frontiersin.org/articles/10.3389/fdata.2021.589417/full

Internet

https://www.frontiersin.org/articles/10.3389/fdata.2021.589417/full

Similar Items