scholarly journals ATLAS Jet Reconstruction, Calibration, and Tagging of Lorentzboosted Objects

2018 ◽  
Vol 182 ◽  
pp. 02113
Author(s):  
Steven Schramm
Keyword(s):  
Neural Networks ◽  
Top Quark ◽  
Z Boson ◽  
Mass Scale ◽  
Hadronic Decay ◽  
Jet Substructure ◽  
In Situ Calibration ◽  
Boosted Decision Trees ◽  
Jet Images

Jet reconstruction in the ATLAS detector takes multiple forms, as motivated by the intended usage of the jet. Different jet definitions are used in particular for the study of QCD jets and jets containing the hadronic decay of boosted massive particles. These different types of jets are calibrated through a series of mostly sequential steps, providing excellent uncertainties, including a first in situ calibration of the jet mass scale. Jet tagging is investigated, including both not-top-quark vs gluon discrimination as well as W/Z boson, H → bb, and top-quark identification. This includes a first look at the use of Boosted Decision Trees and Deep Neural Networks built from jet substructure variables, as well as Convolutional Neural Networks built from jet images. In all cases, these advanced techniques are seen to provide gains over the standard approaches, with the magnitude of the gain depending on the use case. Future methods for improving jet tagging are briefly discussed, including jet substructure-oriented particle flow primarily for W/Z tagging and new subjet reconstruction strategies for H → bb tagging.

scholarly journals A COMPARATIVE STUDY OF JET SUBSTRUCTURE TAGGERS

2013 ◽  
Vol 28 (18) ◽  
pp. 1350087 ◽  
Author(s):  
PALOMA QUIROGA-ARIAS ◽  
SEBASTIAN SAPETA
Keyword(s):  
Comparative Study ◽  
Z Boson ◽  
Hadronic Decay ◽  
Jet Substructure ◽  
Background Events ◽  
Insight Into

We explicitly study how jet substructure taggers act on a set of signal and background events. We focus on two-pronged hadronic decay of a boosted Z-boson. The background to this process comes from QCD jets with masses of the order of mZ. We find a way to compare various taggers within a single framework by applying them to the most relevant splitting in a jet. We develop a tool, TOY-TAG, which allows one to get insight into what happens when a particular tagger is applied to a set of signal or background events. It also provides estimates for significance and purity. We use our tool to analyze differences between various taggers and potential ways to improve the performance by combining several of them.

scholarly journals Reports of my demise are greatly exaggerated: $N$-subjettiness taggers take on jet images

2019 ◽  
Vol 7 (3) ◽  
Author(s):  
Liam Moore ◽  
Karl Nordström ◽  
Sreedevi Varma ◽  
Malcolm Fairbairn
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Top Quark ◽  
Quark Decays ◽  
Body Kinematic ◽  
Highly Correlated ◽  
Object Tagging ◽  
Jet Images ◽  
Mass Information ◽  
Image Network

We compare the performance of a convolutional neural network (CNN) trained on jet images with dense neural networks (DNNs) trained on nn-subjettiness variables to study the distinguishing power of these two separate techniques applied to top quark decays. We find that they perform almost identically and are highly correlated once jet mass information is included, which suggests they are accessing the same underlying information which can be intuitively understood as being contained in 4-, 5-, 6-, and 8-body kinematic phase spaces depending on the sample. This suggests both of these methods are highly useful for heavy object tagging and provides a tentative answer to the question of what the image network is actually learning.

scholarly journals Combine and conquer: event reconstruction with Bayesian Ensemble Neural Networks

2021 ◽  
Vol 2021 (4) ◽  
Author(s):  
Jack Y. Araz ◽  
Michael Spannowsky
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Top Quark ◽  
Feature Space ◽  
Training Sample ◽  
Bayesian Techniques ◽  
Training Sample Size ◽  
Event Reconstruction ◽  
Neural Network Classifiers ◽  
Quark Jets

Abstract Ensemble learning is a technique where multiple component learners are combined through a protocol. We propose an Ensemble Neural Network (ENN) that uses the combined latent-feature space of multiple neural network classifiers to improve the representation of the network hypothesis. We apply this approach to construct an ENN from Convolutional and Recurrent Neural Networks to discriminate top-quark jets from QCD jets. Such ENN provides the flexibility to improve the classification beyond simple prediction combining methods by linking different sources of error correlations, hence improving the representation between data and hypothesis. In combination with Bayesian techniques, we show that it can reduce epistemic uncertainties and the entropy of the hypothesis by simultaneously exploiting various kinematic correlations of the system, which also makes the network less susceptible to a limitation in training sample size.

scholarly journals Hybrid memristor-CMOS neurons for in-situ learning in fully hardware memristive spiking neural networks

2021 ◽  
Author(s):  
Xumeng Zhang ◽  
Jian Lu ◽  
Zhongrui Wang ◽  
Rui Wang ◽  
Jinsong Wei ◽  
...  
Keyword(s):  
Neural Networks ◽  
Spiking Neural Networks

scholarly journals Performance of the SoLid reactor neutrino detector

2019 ◽  
Vol 219 ◽  
pp. 08003
Author(s):  
Maja Verstraeten
Keyword(s):  
Quality Control ◽  
Energy Resolution ◽  
Neutrino Detector ◽  
Channel Response ◽  
In Situ Calibration ◽  
Reactor Neutrino ◽  
Li Isotope ◽  
Better Than

The SoLid Collaboration is currently operating a 1.6 ton neutrino detector near the Belgian BR2 reactor. Its main goal is the observation of the oscillation of electron antineutrinos to previously undetected flavour states. The highly segmented SoLid detector employs a compound scintillation technology based on PVT scintillator in combination with LiF-ZnS(Ag) screens containing the 6Li isotope. The experiment has demonstrated a channel-to-channel response that can be controlled to the level of a few percent, an energy resolution of better than 14% at 1 MeV, and a determination of the interaction vertex with a precision of 5 cm. This contribution highlights the major outcomes of the R&D program, the quality control during component manufacture and integration, the current performance and stability of the full-scale system, as well as the in-situ calibration of the detector with various radioactive sources.

scholarly journals Jet substructure classification in high-energy physics with deep neural networks

2016 ◽  
Vol 93 (9) ◽  
Author(s):  
Pierre Baldi ◽  
Kevin Bauer ◽  
Clara Eng ◽  
Peter Sadowski ◽  
Daniel Whiteson
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
High Energy Physics ◽  
High Energy ◽  
Jet Substructure ◽  
Energy Physics

scholarly journals Automatic In Situ Calibration of a Spinning Beam LiDAR System in Static and Kinematic Modes

2015 ◽  
Vol 7 (8) ◽  
pp. 10480-10500 ◽  
Author(s):  
Ting Chan ◽  
Derek Lichti
Keyword(s):  
Lidar System ◽  
In Situ Calibration
Sign in / Sign up

Export Citation Format

Share Document