scholarly journals On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case

2020 ◽  
Vol 1 (4) ◽  
pp. 045006
Author(s):  
Giles Chatham Strong
2018 ◽  
Vol 68 (1) ◽  
pp. 161-181 ◽  
Author(s):  
Dan Guest ◽  
Kyle Cranmer ◽  
Daniel Whiteson

Machine learning has played an important role in the analysis of high-energy physics data for decades. The emergence of deep learning in 2012 allowed for machine learning tools which could adeptly handle higher-dimensional and more complex problems than previously feasible. This review is aimed at the reader who is familiar with high-energy physics but not machine learning. The connections between machine learning and high-energy physics data analysis are explored, followed by an introduction to the core concepts of neural networks, examples of the key results demonstrating the power of deep learning for analysis of LHC data, and discussion of future prospects and concerns.


Author(s):  
Valentina Avati ◽  
Milosz Blaszkiewicz ◽  
Enrico Bocchi ◽  
Luca Canali ◽  
Diogo Castro ◽  
...  

2021 ◽  
Vol 9 ◽  
Author(s):  
N. Demaria

The High Luminosity Large Hadron Collider (HL-LHC) at CERN will constitute a new frontier for the particle physics after the year 2027. Experiments will undertake a major upgrade in order to stand this challenge: the use of innovative sensors and electronics will have a main role in this. This paper describes the recent developments in 65 nm CMOS technology for readout ASIC chips in future High Energy Physics (HEP) experiments. These allow unprecedented performance in terms of speed, noise, power consumption and granularity of the tracking detectors.


2020 ◽  
pp. 183-203
Author(s):  
M. Brugger ◽  
H. Burkhardt ◽  
B. Goddard ◽  
F. Cerutti ◽  
R. G. Alia

AbstractWith the exceptions of Synchrotron Radiation sources, beams of accelerated particles are generally designed to interact either with one another (in the case of colliders) or with a specific target (for the operation of Fixed Target experiments, the production of secondary beams and for medical applications). However, in addition to the desired interactions there are unwanted interactions of the high energy particles which can produce undesirable side effects. These interactions can arise from the unavoidable presence of residual gas in the accelerator vacuum chamber, or from the impact of particles lost from the beam on aperture limits around the accelerator, as well as the final beam dump. The wanted collisions of the beams in a collider to produce potentially interesting High Energy Physics events also reduces the density of the circulating beam and can produce high fluxes of secondary particles.


2019 ◽  
Vol 214 ◽  
pp. 02019
Author(s):  
V. Daniel Elvira

Detector simulation has become fundamental to the success of modern high-energy physics (HEP) experiments. For example, the Geant4-based simulation applications developed by the ATLAS and CMS experiments played a major role for them to produce physics measurements of unprecedented quality and precision with faster turnaround, from data taking to journal submission, than any previous hadron collider experiment. The material presented here contains highlights of a recent review on the impact of detector simulation in particle physics collider experiments published in Ref. [1]. It includes examples of applications to detector design and optimization, software development and testing of computing infrastructure, and modeling of physics objects and their kinematics. The cost and economic impact of simulation in the CMS experiment is also presented. A discussion on future detector simulation needs, challenges and potential solutions to address them is included at the end.


2021 ◽  
Vol 2 (3) ◽  
pp. 035005
Author(s):  
Jeffrey Krupa ◽  
Kelvin Lin ◽  
Maria Acosta Flechas ◽  
Jack Dinsmore ◽  
Javier Duarte ◽  
...  

2019 ◽  
Vol 214 ◽  
pp. 06017 ◽  
Author(s):  
Celia Fernández Madrazo ◽  
Ignacio Heredia ◽  
Lara Lloret ◽  
Jesús Marco de Lucas

The application of deep learning techniques using convolutional neural networks for the classification of particle collisions in High Energy Physics is explored. An intuitive approach to transform physical variables, like momenta of particles and jets, into a single image that captures the relevant information, is proposed. The idea is tested using a well-known deep learning framework on a simulation dataset, including leptonic ttbar events and the corresponding background at 7 TeV from the CMS experiment at LHC, available as Open Data. This initial test shows competitive results when compared to more classical approaches, like those using feedforward neural networks.


Author(s):  
Dawit Belayneh ◽  
Federico Carminati ◽  
Amir Farbin ◽  
Benjamin Hooberman ◽  
Gulrukh Khattak ◽  
...  

Abstract Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.


Sign in / Sign up

Export Citation Format

Share Document