Studying deep convolutional neural networks with hexagonal lattices for imaging atmospheric Cherenkov Telescope event reconstruction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68378271%3A_____%2F21%3A00552188" target="_blank" >RIV/68378271:_____/21:00552188 - isvavai.cz</a>

Výsledek na webu

<a href="https://pos.sissa.it/358/753/pdf" target="_blank" >https://pos.sissa.it/358/753/pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.22323/1.358.0753" target="_blank" >10.22323/1.358.0753</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Studying deep convolutional neural networks with hexagonal lattices for imaging atmospheric Cherenkov Telescope event reconstruction

Popis výsledku v původním jazyce

Deep convolutional neural networks (DCNs) are a promising machine learning technique to reconstruct events recorded by imaging atmospheric Cherenkov telescopes (IACTs), but require optimization to reach full performance. One of the most pressing challenges is processing raw images captured by cameras made of hexagonal lattices of photo-multipliers, a common layout among IACT cameras which topologically differs from the square lattices conventionally expected, as their input data, by DCN models. Strategies directed to tackle this challenge range from the conversion of the hexagonal lattices onto square lattices by means of oversampling or interpolation to the implementation of hexagonal convolutional kernels. In this contribution we present a comparison of several of those strategies, using DCN models trained on simulated IACT data.n

Název v anglickém jazyce

Studying deep convolutional neural networks with hexagonal lattices for imaging atmospheric Cherenkov Telescope event reconstruction

Popis výsledku anglicky

Deep convolutional neural networks (DCNs) are a promising machine learning technique to reconstruct events recorded by imaging atmospheric Cherenkov telescopes (IACTs), but require optimization to reach full performance. One of the most pressing challenges is processing raw images captured by cameras made of hexagonal lattices of photo-multipliers, a common layout among IACT cameras which topologically differs from the square lattices conventionally expected, as their input data, by DCN models. Strategies directed to tackle this challenge range from the conversion of the hexagonal lattices onto square lattices by means of oversampling or interpolation to the implementation of hexagonal convolutional kernels. In this contribution we present a comparison of several of those strategies, using DCN models trained on simulated IACT data.n

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10303 - Particles and field physics

Projekt

—

Návaznosti

—

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of Science

ISBN

—

ISSN

1824-8039

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

Sissa Medilab srl

Místo vydání

Trieste

Místo konání akce

Madison, WI

Datum konání akce

24. 7. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—