Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation

Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation

Abstract A framework is presented to extract and understand decision-making information from a deep neural network (DNN) classifier of jet substructure tagging techniques. The general method studied is to provide expert variables that augment inputs (“eXpert AUGmented” variables, or XAUG variables),...

Full description

Bibliographic Details
Main Authors: Garvita Agarwal, Lauren Hay, Ia Iashvili, Benjamin Mannix, Christine McLean, Margaret Morris, Salvatore Rappoccio, Ulrich Schubert
Format: Article
Language:English
Published: SpringerOpen 2021-05-01
Series:Journal of High Energy Physics
Subjects:
Jet substructure
Hadron-Hadron scattering (experiments)
Jets
Online Access:https://doi.org/10.1007/JHEP05(2021)208

Internet

https://doi.org/10.1007/JHEP05(2021)208

Similar Items