DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC

<!--HTML-->In this talk, I will present a Generative-Adversarial Network (GAN) based on convolutional neural networks that is used to simulate the production of pairs of jets at the LHC. The GAN is trained on events generated using MadGraph5 + Pythia8, and Delphes3 fast detector simulation. A...

Descripción completa

Detalles Bibliográficos
Autor principal: Palazzo, Serena
Lenguaje:eng
Publicado: 2019
Materias:
LPCC Workshops
Acceso en línea:http://cds.cern.ch/record/2672123
_version_ 1780962441952231424
author Palazzo, Serena
author_facet Palazzo, Serena
author_sort Palazzo, Serena
collection CERN
description <!--HTML-->In this talk, I will present a Generative-Adversarial Network (GAN) based on convolutional neural networks that is used to simulate the production of pairs of jets at the LHC. The GAN is trained on events generated using MadGraph5 + Pythia8, and Delphes3 fast detector simulation. A number of kinematic distributions both at Monte Carlo truth level and after the detector simulation can be reproduced by the generator network with a very good level of agreement.
id cern-2672123
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2019
record_format invenio
spelling cern-26721232022-11-02T22:33:37Zhttp://cds.cern.ch/record/2672123engPalazzo, SerenaDijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC3rd IML Machine Learning WorkshopLPCC Workshops<!--HTML-->In this talk, I will present a Generative-Adversarial Network (GAN) based on convolutional neural networks that is used to simulate the production of pairs of jets at the LHC. The GAN is trained on events generated using MadGraph5 + Pythia8, and Delphes3 fast detector simulation. A number of kinematic distributions both at Monte Carlo truth level and after the detector simulation can be reproduced by the generator network with a very good level of agreement.oai:cds.cern.ch:26721232019
spellingShingle LPCC Workshops
Palazzo, Serena
DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
title DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
title_full DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
title_fullStr DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
title_full_unstemmed DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
title_short DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
title_sort dijetgan: a generative-adversarial network approach for the simulation of qcd dijet events at the lhc
topic LPCC Workshops
url http://cds.cern.ch/record/2672123
work_keys_str_mv AT palazzoserena dijetganagenerativeadversarialnetworkapproachforthesimulationofqcddijeteventsatthelhc
AT palazzoserena 3rdimlmachinelearningworkshop

Ejemplares similares