Machine Learning Methods for Histogram Deconvolution in High Energy Physics

Keras sequential neural networks are developed to perform histogram deconvolution on Z-boson mass spectra generated by the MadGraph5_aMC@NLO event generator using Pythia8 and Delphes. Three ways of interpreting the problem with neural networks are presented, tested and then compared with each other...

Descripción completa

Detalles Bibliográficos
Autor principal: Wiederhold, Aidan Richard
Lenguaje:eng
Publicado: 2019
Materias:
Particle Physics - Experiment
Detectors and Experimental Techniques
Acceso en línea:http://cds.cern.ch/record/2690260
_version_ 1780963765612707840
author Wiederhold, Aidan Richard
author_facet Wiederhold, Aidan Richard
author_sort Wiederhold, Aidan Richard
collection CERN
description Keras sequential neural networks are developed to perform histogram deconvolution on Z-boson mass spectra generated by the MadGraph5_aMC@NLO event generator using Pythia8 and Delphes. Three ways of interpreting the problem with neural networks are presented, tested and then compared with each other and the popular unfolding method TUnfold. A bin classification method is identified as a robust deconvolution method, with results comparable to that of TUnfold.
id cern-2690260
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2019
record_format invenio
spelling cern-26902602019-09-30T06:29:59Zhttp://cds.cern.ch/record/2690260engWiederhold, Aidan RichardMachine Learning Methods for Histogram Deconvolution in High Energy PhysicsParticle Physics - ExperimentDetectors and Experimental TechniquesKeras sequential neural networks are developed to perform histogram deconvolution on Z-boson mass spectra generated by the MadGraph5_aMC@NLO event generator using Pythia8 and Delphes. Three ways of interpreting the problem with neural networks are presented, tested and then compared with each other and the popular unfolding method TUnfold. A bin classification method is identified as a robust deconvolution method, with results comparable to that of TUnfold.CERN-STUDENTS-Note-2019-221oai:cds.cern.ch:26902602019-09-20
spellingShingle Particle Physics - Experiment
Detectors and Experimental Techniques
Wiederhold, Aidan Richard
Machine Learning Methods for Histogram Deconvolution in High Energy Physics
title Machine Learning Methods for Histogram Deconvolution in High Energy Physics
title_full Machine Learning Methods for Histogram Deconvolution in High Energy Physics
title_fullStr Machine Learning Methods for Histogram Deconvolution in High Energy Physics
title_full_unstemmed Machine Learning Methods for Histogram Deconvolution in High Energy Physics
title_short Machine Learning Methods for Histogram Deconvolution in High Energy Physics
title_sort machine learning methods for histogram deconvolution in high energy physics
topic Particle Physics - Experiment
Detectors and Experimental Techniques
url http://cds.cern.ch/record/2690260
work_keys_str_mv AT wiederholdaidanrichard machinelearningmethodsforhistogramdeconvolutioninhighenergyphysics

Ejemplares similares