Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Felix J., Kamp, Nicholas, Argüelles, Carlos A.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.13148
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908674534932480
author Yu, Felix J.
Kamp, Nicholas
Argüelles, Carlos A.
author_facet Yu, Felix J.
Kamp, Nicholas
Argüelles, Carlos A.
contents Neutrino telescopes detect rare interactions of particles produced in some of the most extreme environments in the Universe. This is accomplished by instrumenting a cubic-kilometer scale volume of naturally occurring transparent medium with light sensors. Given their substantial size and the high frequency of background interactions, these telescopes amass an enormous quantity of large variance, high-dimensional data. These attributes create substantial challenges for analyzing and reconstructing interactions, particularly when utilizing machine learning (ML) techniques. In this paper, we present a novel approach, called om2vec, that employs transformer-based variational autoencoders to efficiently represent the detected photon arrival time distributions of neutrino telescope events by learning compact and descriptive latent representations. We demonstrate that these latent representations offer enhanced flexibility and improved computational efficiency, thereby facilitating downstream tasks in data analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13148
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Efficient Representations of Neutrino Telescope Events
Yu, Felix J.
Kamp, Nicholas
Argüelles, Carlos A.
Data Analysis, Statistics and Probability
Instrumentation and Methods for Astrophysics
Machine Learning
High Energy Physics - Experiment
Neutrino telescopes detect rare interactions of particles produced in some of the most extreme environments in the Universe. This is accomplished by instrumenting a cubic-kilometer scale volume of naturally occurring transparent medium with light sensors. Given their substantial size and the high frequency of background interactions, these telescopes amass an enormous quantity of large variance, high-dimensional data. These attributes create substantial challenges for analyzing and reconstructing interactions, particularly when utilizing machine learning (ML) techniques. In this paper, we present a novel approach, called om2vec, that employs transformer-based variational autoencoders to efficiently represent the detected photon arrival time distributions of neutrino telescope events by learning compact and descriptive latent representations. We demonstrate that these latent representations offer enhanced flexibility and improved computational efficiency, thereby facilitating downstream tasks in data analysis.
title Learning Efficient Representations of Neutrino Telescope Events
topic Data Analysis, Statistics and Probability
Instrumentation and Methods for Astrophysics
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2410.13148