%0 Journal Article
%T A simple guide from machine learning outputs to statistical criteria in particle physics
%A Khosa, C. K.
%A Sanz, V.
%A Soughton, M.
%J Scipost Physics Core
%D 2022
%V 5
%N 4
%I Scipost Foundation
%G English
%F Khosa_etal2022
%O WOS:000929724800002
%O exported from refbase (https://references.ific.uv.es/refbase/show.php?record=5475), last updated on Sun, 05 Mar 2023 12:15:20 +0000
%X In this paper we propose ways to incorporate Machine Learning training outputs into a study of statistical significance. We describe these methods in supervised classification tasks using a CNN and a DNN output, and unsupervised learning based on a VAE. As use cases, we consider two physical situations where Machine Learning are often used: high-pT hadronic activity, and boosted Higgs in association with a massive vector boson.
%R 10.21468/SciPostPhysCore.5.4.050
%U https://arxiv.org/abs/2203.03669
%U https://doi.org/10.21468/SciPostPhysCore.5.4.050
%P 050-31pp