Jet flavor classification in high-energy physics with deep neural networks
Authors:
Open Access
- 2 December 2016
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review D
- Vol. 94 (11) , 112002
Abstract
Classification of jets as originating from light-flavor or heavy-flavor quarks is an important task for inferring the nature of particles produced in high-energy collisions. The large and variable dimensionality of the data provided by the tracking detectors makes this task difficult. The current state-of-the-art tools require expert data reduction to convert the data into a fixed low-dimensional form that can be effectively managed by shallow classifiers. We study the application of deep networks to this task, attempting classification at several levels of data, starting from a raw list of tracks. We find that the highest-level lowest-dimensionality expert information sacrifices information needed for classification, that the performance of current state-of-the-art taggers can be matched or slightly exceeded by deep-network-based taggers using only track and vertex information, that classification using only lowest-level highest-dimensionality tracking information remains a difficult task for deep networks, and that adding lower-level track and vertex information to the classifiers provides a significant boost in performance compared to the state of the art.Keywords
All Related Versions
Funding Information
- Nvidia
- National Science Foundation (IIS-1321053)
- U.S. Department of Energy
This publication has 26 references indexed in Scilit:
- FastJet user manualThe European Physical Journal C, 2012
- NNcon: improved protein contact map prediction using 2D-recursive neural networksNucleic Acids Research, 2009
- Learning to play Go using recursive neural networksNeural Networks, 2008
- The ATLAS Experiment at the CERN Large Hadron ColliderJournal of Instrumentation, 2008
- The RAVE/VERTIGO vertex reconstruction toolkit and frameworkJournal of Physics: Conference Series, 2008
- The anti-ktjet clustering algorithmJournal of High Energy Physics, 2008
- PYTHIA 6.4 physics and manualJournal of High Energy Physics, 2006
- Learning to Forget: Continual Prediction with LSTMNeural Computation, 2000
- 10.1162/153244304773936054Applied Physics Letters, 2000
- Hybrid Modeling, HMM/NN Architectures, and Protein ApplicationsNeural Computation, 1996