The Machine Learning landscape of top taggers
Journal Article
·
· SciPost Physics
more »
- University of Hamburg
- Heidelberg University
- New York University
- Rutgers, The State University of New Jersey
- Jožef Stefan Institute
- King's College London
- University of British Columbia
- University of California, Santa Barbara
- Jožef Stefan Institute, University of Ljubljana
- Massachusetts Institute of Technology
- New York University, Rutgers, The State University of New Jersey
- Université catholique de Louvain
- Lawrence Berkeley National Laboratory, University of California, Berkeley
- Laboratory of Theoretical and High Energy Physics, National Institute for Subatomic Physics
- RWTH Aachen University
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.
- Research Organization:
- Univ. of California, Santa Barbara, CA (United States)
- Sponsoring Organization:
- NSF; USDOE; USDOE Office of Science (SC), High Energy Physics (HEP)
- Grant/Contract Number:
- AC02-05CH11231; SC0011090; SC0011702; SC0012567
- OSTI ID:
- 1568892
- Alternate ID(s):
- OSTI ID: 1777252
- Journal Information:
- SciPost Physics, Journal Name: SciPost Physics Journal Issue: 1 Vol. 7; ISSN 2542-4653
- Publisher:
- Stichting SciPostCopyright Statement
- Country of Publication:
- Netherlands
- Language:
- English
Similar Records
Jet charge and machine learning
Journal Article
·
Sun Oct 14 20:00:00 EDT 2018
· Journal of High Energy Physics (Online)
·
OSTI ID:1483678