Bayesian Neural Networks for classification tasks in the Rubin big data
era
A. Möller, and T. de Boissière. (2022)cite arxiv:2207.04578Comment: Accepted at the ICML 2022 Workshop on Machine Learning for Astrophysics.
Abstract
Upcoming surveys such as the Vera C. Rubin Observatory Legacy Survey of Space
and Time (LSST) will detect up to 10 million time-varying sources in the sky
every night for ten years. This information will be transmitted in a continuous
stream to brokers that will select the most promising events for a variety of
science cases using machine learning algorithms. We study the benefits and
challenges of Bayesian Neural Networks (BNNs) for this type of classification
tasks. BNNs are found to be accurate classifiers which also provide additional
information: they quantify the classification uncertainty which can be
harnessed to analyse this upcoming data avalanche more efficiently.
Description
Bayesian Neural Networks for classification tasks in the Rubin big data era
%0 Generic
%1 moller2022bayesian
%A Möller, Anais
%A de Boissière, Thibault
%D 2022
%K library
%T Bayesian Neural Networks for classification tasks in the Rubin big data
era
%U http://arxiv.org/abs/2207.04578
%X Upcoming surveys such as the Vera C. Rubin Observatory Legacy Survey of Space
and Time (LSST) will detect up to 10 million time-varying sources in the sky
every night for ten years. This information will be transmitted in a continuous
stream to brokers that will select the most promising events for a variety of
science cases using machine learning algorithms. We study the benefits and
challenges of Bayesian Neural Networks (BNNs) for this type of classification
tasks. BNNs are found to be accurate classifiers which also provide additional
information: they quantify the classification uncertainty which can be
harnessed to analyse this upcoming data avalanche more efficiently.
@misc{moller2022bayesian,
abstract = {Upcoming surveys such as the Vera C. Rubin Observatory Legacy Survey of Space
and Time (LSST) will detect up to 10 million time-varying sources in the sky
every night for ten years. This information will be transmitted in a continuous
stream to brokers that will select the most promising events for a variety of
science cases using machine learning algorithms. We study the benefits and
challenges of Bayesian Neural Networks (BNNs) for this type of classification
tasks. BNNs are found to be accurate classifiers which also provide additional
information: they quantify the classification uncertainty which can be
harnessed to analyse this upcoming data avalanche more efficiently.},
added-at = {2022-07-12T08:44:34.000+0200},
author = {Möller, Anais and de Boissière, Thibault},
biburl = {https://www.bibsonomy.org/bibtex/25e13754484b6c1e6ff97160f640ccc71/gpkulkarni},
description = {Bayesian Neural Networks for classification tasks in the Rubin big data era},
interhash = {3d5ca54639e8351e2388e6935d3d4d68},
intrahash = {5e13754484b6c1e6ff97160f640ccc71},
keywords = {library},
note = {cite arxiv:2207.04578Comment: Accepted at the ICML 2022 Workshop on Machine Learning for Astrophysics},
timestamp = {2022-07-12T08:44:34.000+0200},
title = {Bayesian Neural Networks for classification tasks in the Rubin big data
era},
url = {http://arxiv.org/abs/2207.04578},
year = 2022
}