Classification of Fermi-LAT unassociated sources with machine learning in the presence of dataset shifts

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Malyshev, Dmitry V.
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929743979347968
author Malyshev, Dmitry V.
author_facet Malyshev, Dmitry V.
contents About one third of Fermi Large Area Telescope (LAT) sources are unassociated. We perform multi-class classification of Fermi-LAT sources using machine learning with the goal of probabilistic classification of the unassociated sources. A particular attention is paid to the fact that the distributions of associated and unassociated sources are different as functions of source parameters. In this work, we address this problem in the framework of dataset shifts in machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04675
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Classification of Fermi-LAT unassociated sources with machine learning in the presence of dataset shifts
Malyshev, Dmitry V.
High Energy Astrophysical Phenomena
Instrumentation and Methods for Astrophysics
About one third of Fermi Large Area Telescope (LAT) sources are unassociated. We perform multi-class classification of Fermi-LAT sources using machine learning with the goal of probabilistic classification of the unassociated sources. A particular attention is paid to the fact that the distributions of associated and unassociated sources are different as functions of source parameters. In this work, we address this problem in the framework of dataset shifts in machine learning.
title Classification of Fermi-LAT unassociated sources with machine learning in the presence of dataset shifts
topic High Energy Astrophysical Phenomena
Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2412.04675