Machine Learning for Jet Physics

Session

Jet tagging

11 Dec 2017, 12:30

2-100 (Lawrence Berkeley National Laboratory)

29. Introduction and Overview (15'+5')

Matt Dolan (The University of Melbourne)

11/12/2017, 12:30

8. Recursive Neural Networks in quark/gluon tagging (15'+5')

Taoli Cheng (University of Chinese Academy of Sciences)

11/12/2017, 12:50

I am writing to propose a talk based on the recent paper https://arxiv.org/abs/1711.02633. The main topic is exploring the performance of Recursive Neural Networks in quark/gluon tagging.

7. Top tagging with jet constituents and Long Short-Term Memory (LSTM) networks. (15'+5')

Wojciech Fedorko (UBC), Dr Wojciech Fedorko (University of British Columbia)

11/12/2017, 13:10

Multivariate techniques based on engineered features have found wide adoption in the identification of jets resulting from hadronic top decays at the Large Hadron Collider (LHC). Recent Deep Learning developments in this area include the treatment of the calorimeter activation as an image or supplying a list of jet constituent momenta to a fully connected network. This latter approach lends...

6. Deep(Boosted)Jet: Boosted jet identification using particle-level convolutional neural networks (15'+5')

Qu Huilin (UCSB)

11/12/2017, 13:30

dentification of boosted top quarks from their hadronic decays can play an important role in searches for new physics at the LHC. We present DeepBoostedJet, a new approach for boosted jet identification using particle-flow jets at CMS. One dimensional convolutional neural networks are utilized to classify a jet directly from its reconstructed constituent particles. The new method shows...

24. Deep-Learned Top Taggers from Images & Lorentz Invariance (15'+5')

Gregor Kasieczka (Uni Hamburg)

11/12/2017, 13:50

Distinguishing hadronic top quark decays from light quark and gluon jets (top tagging) is an important tool for new physics searches at the LHC and allows the comparison of different machine learning approaches. We present results on using convolutional neural networks as well as recent studies employing a physics motivated network architecture based on Lorentz Invariance (and not much else)...

35. Jets as graphs: W tagging with neural message passing (15'+5')

Isaac Henrion (NYU)

11/12/2017, 14:10