- Journal Article
Rights / licenseCreative Commons Attribution 4.0 International
Machine learning based on convolutional neural networks can be used to study jet images from the LHC. Top tagging in fat jets o ers a well-de ned framework to estab- lish our DeepTop approach and compare its performance to QCD-based top taggers. We rst optimize a network architecture to identify top quarks in Monte Carlo simulations of the Standard Model production channel. Using standard fat jets we then compare its per- formance to a multivariate QCD-based top tagger. We nd that both approaches lead to comparable performance, establishing convolutional networks as a promising new approach for multivariate hypothesis-based top tagging. Show more
Journal / seriesJournal of High Energy Physics
Pages / Article No.
SubjectJet substructure; QCD; Hadron-Hadron scattering (experiments); Top physics
MoreShow all metadata