Machine Learning for Jet Physics

Session

Jet Tagging (Chairs: Gregor Kasieczka and Matt Dolan)

14 Nov 2018, 12:30

One West (WH1W) (Fermilab)

28. Introduction and overview (20'+10')

Gregor Kasieczka (Hamburg University (DE))

14/11/2018, 12:30

29. top and W tagging with ATLAS (20’+5’)

Samuel Ross Meehan (University of Washington (US))

14/11/2018, 13:05

30. top and W tagging with CMS (20’+5’)

Justin Pilot (University of California Davis (US))

14/11/2018, 13:35

31. b-tagging in ATLAS (25’+5’)

Matthew Feickert (Southern Methodist University (US))

14/11/2018, 14:20

39. ML Techniques for heavy flavour identification in CMS (25'+5')

Emil Sorensen Bols (Vrije Universiteit Brussel (BE))

14/11/2018, 14:50

Jet flavour identification is a fundamental component for the physics program of the LHC-based experiments. The presence of multiple flavours to be identified leads to a multiclass classification problem. In this presentation we will present the performance on both simulated and real data of our latest resolved heavy flavour taggers, DeepCSV and DeepFlavour as well as the future prospects for...

1. Deep Learning Strange Jets (20’+5’)

Yuichiro Nakai (Rutgers University)

14/11/2018, 15:20

By applying deep learning techniques, we explore the possibility of strange-quark tagging, which is the last missing piece among quark and gluon identifications in jets. The main difficulty here is of distinguishing strange-quark jets from down-quark jets. However, strange-quark jets are likely to contain more Kaons carrying large fractions of the jet $p_T$ than down-quark jets. A strategy for...