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),...
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: | |
Online Access: | https://doi.org/10.1007/JHEP05(2021)208 |
Similar Items
-
Deep-learning top taggers or the end of QCD?
by: Gregor Kasieczka, et al.
Published: (2017-05-01) -
Measurements of jet charge with dijet events in pp collisions at s = 8 $$ \sqrt{s}=8 $$ TeV
by: The CMS collaboration, et al.
Published: (2017-10-01) -
Search for low mass vector resonances decaying into quark-antiquark pairs in proton-proton collisions at s=13 $$ \sqrt{s}=13 $$ TeV
by: The CMS collaboration, et al.
Published: (2018-01-01) -
Prospects for a measurement of the W boson mass in the all-jets final state at hadron colliders
by: Marat Freytsis, et al.
Published: (2019-02-01) -
Tag N’ Train: a technique to train improved classifiers on unlabeled data
by: Oz Amram, et al.
Published: (2021-01-01)