Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Jet charge and machine learning

Journal Article · · Journal of High Energy Physics (Online)
 [1];  [2]
  1. Harvard Univ., Cambridge, MA (United States); Department of Physics, Harvard University, Cambridge, MA
  2. Harvard Univ., Cambridge, MA (United States)

Modern machine learning techniques, such as convolutional, recurrent and recursive neural networks, have shown promise for jet substructure at the Large Hadron Collider. For example, they have demonstrated effectiveness at boosted top or W boson identification or for quark/gluon discrimination. We explore these methods for the purpose of classifying jets according to their electric charge. We find that both neural networks that incorporate distance within the jet as an input and boosted decision trees including radial distance information can provide significant improvement in jet charge extraction over current methods. Specifically, convolutional, recurrent, and recursive networks can provide the largest improvement over traditional methods, in part by effectively utilizing distance within the jet or clustering history. Furthermore, the advantages of using a fixed-size input representation (as with the CNN) or a small input representation (as with the RNN) suggest that both convolutional and recurrent networks will be essential to the future of modern machine learning at colliders.

Research Organization:
Harvard Univ., Cambridge, MA (United States)
Sponsoring Organization:
USDOE Office of Science (SC)
Grant/Contract Number:
SC0013607
OSTI ID:
1483678
Journal Information:
Journal of High Energy Physics (Online), Journal Name: Journal of High Energy Physics (Online) Journal Issue: 10 Vol. 2018; ISSN 1029-8479
Publisher:
Springer BerlinCopyright Statement
Country of Publication:
United States
Language:
English

References (40)

Deep learning in color: towards automated quark/gluon jet discrimination journal January 2017
Maximizing boosted top identification by minimizing N-subjettiness journal February 2012
Jet-images: computer vision inspired techniques for jet tagging journal February 2015
(Machine) learning to do more with less journal February 2018
Multivariate discrimination and the Higgs+W/Z search journal April 2011
Quark and gluon jet substructure journal April 2013
Deep-learning top taggers or the end of QCD? journal May 2017
Playing tag with ANN: boosted top identification with pattern recognition journal July 2015
Jet-images — deep learning edition journal July 2016
Classification without labels: learning from mixed samples in high energy physics journal October 2017
Pileup Mitigation with Machine Learning (PUMML) journal December 2017
Recursive Neural Networks in Quark/Gluon Tagging journal June 2018
A direct observation of quark-gluon jet differences at LEP journal August 1991
A parametrization of the properties of quark jets journal April 1978
A brief introduction to PYTHIA 8.1 journal June 2008
Jet substructure at the Tevatron and LHC: new results, new tools, new benchmarks journal May 2012
How to tell quark jets from gluon jets journal October 1991
Substructure of high- p T jets at the LHC journal April 2009
W -jet tagging: Optimizing the identification of boosted hadronically-decaying W bosons journal April 2011
Calculating the charge of a jet journal November 2012
Measurement of jet charge in dijet events from s = 8     TeV p p collisions with the ATLAS detector journal March 2016
Jet substructure classification in high-energy physics with deep neural networks journal May 2016
Jet flavor classification in high-energy physics with deep neural networks journal December 2016
Learning to classify from impure samples with high-dimensional data journal July 2018
Top Tagging: A Method for Identifying Boosted Hadronically Decaying Top Quarks journal October 2008
Quark and Gluon Tagging at the LHC journal October 2011
Jet Charge at the LHC journal May 2013
Finding gluon jets with a neural trigger journal September 1990
Towards jetography journal May 2010
Light-quark and gluon jet discrimination in $$pp$$ p p collisions at $$\sqrt{s}=7\mathrm {\ TeV}$$ s = 7 TeV with the ATLAS detector journal August 2014
Deep-learned Top Tagging with a Lorentz Layer journal January 2018
Jet Substructure at the Tevatron And LHC: New Results, New Tools, New Benchmarks report November 2012
Deep-learning top taggers or the end of QCD text January 2017
Deep-learned Top Tagging with a Lorentz Layer text January 2018
Quark and Gluon Tagging at the LHC text January 2011
Maximizing Boosted Top Identification by Minimizing N-subjettiness text January 2011
Jet-Images: Computer Vision Inspired Techniques for Jet Tagging text January 2014
Deep learning in color: towards automated quark/gluon jet discrimination text January 2016
Deep-learning Top Taggers or The End of QCD? text January 2017
Recursive Neural Networks in Quark/Gluon Tagging text January 2017

Cited By (23)

QCD-aware recursive neural networks for jet physics journal January 2019
Energy flow networks: deep sets for particle jets journal January 2019
Infrared safety of a neural-net top tagging algorithm journal February 2019
A theory of quark vs. gluon discrimination journal October 2019
Adversarially-trained autoencoders for robust unsupervised new physics searches journal October 2019
An operational definition of quark and gluon jets journal November 2018
Uncovering latent jet substructure journal September 2019
Automating the construction of jet observables with machine learning journal November 2019
Higgs bosons with large couplings to light quarks journal December 2019
Extending the search for new resonances with machine learning journal January 2019
Learning new physics from a machine journal January 2019
binary junipr: An Interpretable Probabilistic Model for Discrimination journal October 2019
Beyond $$M_{t\bar{t}}$$: learning to search for a broad $$t\bar{t}$$ resonance at the LHC journal February 2020
QCD or what? journal January 2019
Quark-gluon tagging: Machine learning vs detector journal January 2019
Automating the construction of jet observables with machine learning text January 2019
QCD-Aware Recursive Neural Networks for Jet Physics text January 2017
Infrared Safety of a Neural-Net Top Tagging Algorithm text January 2018
Energy Flow Networks: Deep Sets for Particle Jets text January 2018
Quark-Gluon Tagging: Machine Learning vs Detector text January 2018
Automating the Construction of Jet Observables with Machine Learning text January 2019
A Theory of Quark vs. Gluon Discrimination text January 2019
Beyond $M_{t\bar{t}}$: learning to search for a broad $t\bar t$ resonance at the LHC text January 2019

Similar Records

Predictive Skill of Deep Learning Models Trained on Limited Sequence Data
Technical Report · Thu Oct 01 00:00:00 EDT 2020 · OSTI ID:1688570

The predictive skill of convolutional neural networks models for disease forecasting
Journal Article · Fri Jul 09 00:00:00 EDT 2021 · PLoS ONE · OSTI ID:1806600