Salvato in:
Dettagli Bibliografici
Autori principali: Mengel, Tanner, Steffanic, Patrick, Hughes, Charles, da Silva, Antonio Carlos Oliveira, Nattrass, Christine
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2303.08275
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916152719966208
author Mengel, Tanner
Steffanic, Patrick
Hughes, Charles
da Silva, Antonio Carlos Oliveira
Nattrass, Christine
author_facet Mengel, Tanner
Steffanic, Patrick
Hughes, Charles
da Silva, Antonio Carlos Oliveira
Nattrass, Christine
contents Jet measurements in heavy ion collisions can provide constraints on the properties of the quark gluon plasma, but the kinematic reach is limited by a large, fluctuating background. We present a novel application of symbolic regression to extract a functional representation of a deep neural network trained to subtract the background for measurements of jets in relativistic heavy ion collisions. We show that the deep neural network is approximately the same as a method using the particle multiplicity in a jet. This demonstrates that interpretable machine learning methods can provide insight into underlying physical processes.
format Preprint
id arxiv_https___arxiv_org_abs_2303_08275
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Interpretable Machine Learning Methods Applied to Jet Background Subtraction in Heavy Ion Collisions
Mengel, Tanner
Steffanic, Patrick
Hughes, Charles
da Silva, Antonio Carlos Oliveira
Nattrass, Christine
High Energy Physics - Experiment
Nuclear Experiment
Jet measurements in heavy ion collisions can provide constraints on the properties of the quark gluon plasma, but the kinematic reach is limited by a large, fluctuating background. We present a novel application of symbolic regression to extract a functional representation of a deep neural network trained to subtract the background for measurements of jets in relativistic heavy ion collisions. We show that the deep neural network is approximately the same as a method using the particle multiplicity in a jet. This demonstrates that interpretable machine learning methods can provide insight into underlying physical processes.
title Interpretable Machine Learning Methods Applied to Jet Background Subtraction in Heavy Ion Collisions
topic High Energy Physics - Experiment
Nuclear Experiment
url https://arxiv.org/abs/2303.08275