The Machine Learning landscape of top taggers

Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. Unlike most established methods they rely on low-level input, for instance calorimeter output. While their network architectures are vastly different...

Full description

Saved in:
Bibliographic Details
Published inSciPost physics Vol. 7; no. 1; p. 014
Main Authors Kasieczka, Gregor, Plehn, Tilman, Butter, Anja, Cranmer, Kyle, Debnath, Dipsikha, Dillon, Barry M., Fairbairn, Malcolm, Faroughy, Darius A., Fedorko, Wojtek, Gay, Christophe, Gouskos, Loukas, Kamenik, Jernej Fesel, Komiske, Patrick, Leiss, Simon, Lister, Alison, Macaluso, Sebastian, Metodiev, Eric, Moore, Liam, Nachman, Benjamin, Nordström, Karl, Pearkes, Jannicke, Qu, Huilin, Rath, Yannik, Rieger, Marcel, Shih, David, Thompson, Jennifer, Varma, Sreedevi
Format Journal Article
LanguageEnglish
Published United States SciPost Foundation 30.07.2019
SciPost
Subjects
MATHEMATICS AND COMPUTING
Online AccessGet full text

Cover

More Information
Summary:Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. Unlike most established methods they rely on low-level input, for instance calorimeter output. While their network architectures are vastly different, their performance is comparatively similar. In general, we find that these new approaches are extremely powerful and great fun.
Bibliography:USDOE
USDOE Office of Science (SC), High Energy Physics (HEP)
National Science Foundation (NSF)
SC0011702; SC0011090; AC02-05CH11231; OAC-1836650; ACI-1450310; SC-0011090; SC0012567
ISSN:2542-4653
2542-4653
DOI:10.21468/SciPostPhys.7.1.014