Classification of Fermi-LAT blazars with Bayesian neural networks. (arXiv:2112.01403v1 [astro-ph.HE])
<a href="http://arxiv.org/find/astro-ph/1/au:+Butter_A/0/1/0/all/0/1">Anja Butter</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Finke_T/0/1/0/all/0/1">Thorben Finke</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Keil_F/0/1/0/all/0/1">Felicitas Keil</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kramer_M/0/1/0/all/0/1">Michael Krämer</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Manconi_S/0/1/0/all/0/1">Silvia Manconi</a>
The use of Bayesian neural networks is a novel approach for the
classification of gamma-ray sources. We focus on the classification of
Fermi-LAT blazar candidates, which can be divided into BL Lacertae objects and
Flat Spectrum Radio Quasars. In contrast to conventional dense networks,
Bayesian neural networks provide a reliable estimate of the uncertainty of the
network predictions. We explore the correspondence between conventional and
Bayesian neural networks and the effect of data augmentation. We find that
Bayesian neural networks provide a robust classifier with reliable uncertainty
estimates and are particularly well suited for classification problems that are
based on comparatively small and imbalanced data sets. The results of our
blazar candidate classification are valuable input for population studies aimed
at constraining the blazar luminosity function and to guide future
observational campaigns.
The use of Bayesian neural networks is a novel approach for the
classification of gamma-ray sources. We focus on the classification of
Fermi-LAT blazar candidates, which can be divided into BL Lacertae objects and
Flat Spectrum Radio Quasars. In contrast to conventional dense networks,
Bayesian neural networks provide a reliable estimate of the uncertainty of the
network predictions. We explore the correspondence between conventional and
Bayesian neural networks and the effect of data augmentation. We find that
Bayesian neural networks provide a robust classifier with reliable uncertainty
estimates and are particularly well suited for classification problems that are
based on comparatively small and imbalanced data sets. The results of our
blazar candidate classification are valuable input for population studies aimed
at constraining the blazar luminosity function and to guide future
observational campaigns.
http://arxiv.org/icons/sfx.gif
