Deep-learning top taggers or the end of QCD?

Abstract Machine learning based on convolutional neural networks can be used to study jet images from the LHC. Top tagging in fat jets offers a well-defined framework to establish our DeepTop approach and compare its performance to QCD-based top taggers. We first optimize a network architecture to i...

Full description

Bibliographic Details
Main Authors: Gregor Kasieczka, Tilman Plehn, Michael Russell, Torben Schell
Format: Article
Language:English
Published: SpringerOpen 2017-05-01
Series:Journal of High Energy Physics
Subjects:
QCD
Online Access:http://link.springer.com/article/10.1007/JHEP05(2017)006