The Machine Learning Landscape of Top Taggers
High Energy Physics - Phenomenology
2019-07-31 v3
Abstract
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.
Cite
@article{arxiv.1902.09914,
title = {The Machine Learning Landscape of Top Taggers},
author = {G. Kasieczka and T. Plehn and A. Butter and K. Cranmer and D. Debnath and B. M. Dillon and M. Fairbairn and D. A. Faroughy and W. Fedorko and C. Gay and L. Gouskos and J. F. Kamenik and P. T. Komiske and S. Leiss and A. Lister and S. Macaluso and E. M. Metodiev and L. Moore and B. Nachman and K. Nordstrom and J. Pearkes and H. Qu and Y. Rath and M. Rieger and D. Shih and J. M. Thompson and S. Varma},
journal= {arXiv preprint arXiv:1902.09914},
year = {2019}
}
Comments
Yet another tagger included!