Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC

Abstract

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 itself well to the use of Recurrent Neural Networks. In this work the applicability of architectures incorporating Long Short-Term Memory (LSTM) networks is explored. Several network architectures, methods of ordering of jet constituents, and input pre-processing are studied. The best performing LSTM network achieves a background rejection of 100 for 50% signal efficiency. This represents more than a factor of two improvement over a fully connected Deep Neural Network (DNN) trained on similar types of inputs.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• An Introduction to PYTHIA 8.2
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• A search for $t\bar{t}$ resonances using lepton-plus-jets events in proton-proton collisions at $\sqrt{s}=8$ TeV with the ATLAS detector
• Search for resonant t t-bar production in proton-proton collisions at sqrt(s) = 8 TeV
• Search for vector-like T quarks decaying to top quarks and Higgs bosons in the all-hadronic channel using jet substructure
• Jet Constituents for Deep Neural Network Based Top Quark Tagging
• Search for single production of vector-like quarks decaying to a Z boson and a top or a bottom quark in proton-proton collisions at sqrt(s) = 13 TeV
• Search for the production of an excited bottom quark decaying to tW in proton-proton collisions at sqrt(s) = 8 TeV

Cited by in corpus (20)

• ParticleNet: Jet Tagging via Particle Clouds
• Deep Learning and its Application to LHC Physics
• Searching for New Physics with Deep Autoencoders
• Performance of top-quark and $W$-boson tagging with ATLAS in Run 2 of the LHC
• DisCo Fever: Robust Networks Through Distance Correlation
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Quark-Gluon Tagging: Machine Learning vs Detector
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Boosted $W/Z$ Tagging with Jet Charge and Deep Learning
• End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data
• Per-Object Systematics using Deep-Learned Calibration
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Classification of Fermi-LAT sources with deep learning using energy and time spectra
• Particle Convolution for High Energy Physics
• Boosted Top Tagging Method Overview
• Strange Jet Tagging
• Sequence-based Machine Learning Models in Jet Physics
• Interpretability Study on Deep Learning for Jet Physics at the Large Hadron Collider