A simple guide from machine learning outputs to statistical criteria in particle physics
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 situ...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SciPost
2022-11-01
|
| Series: | SciPost Physics Core |
| Online Access: | https://scipost.org/SciPostPhysCore.5.4.050 |
| _version_ | 1811248418190786560 |
|---|---|
| author | Charanjit Kaur Khosa, Veronica Sanz, Michael Soughton |
| author_facet | Charanjit Kaur Khosa, Veronica Sanz, Michael Soughton |
| author_sort | Charanjit Kaur Khosa, Veronica Sanz, Michael Soughton |
| collection | DOAJ |
| description | 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-$p_T$ hadronic activity, and
boosted Higgs in association with a massive vector boson. |
| first_indexed | 2024-04-12T15:26:41Z |
| format | Article |
| id | doaj.art-0d8005e8e4924b2b9128310e51761b3d |
| institution | Directory Open Access Journal |
| issn | 2666-9366 |
| language | English |
| last_indexed | 2024-04-12T15:26:41Z |
| publishDate | 2022-11-01 |
| publisher | SciPost |
| record_format | Article |
| series | SciPost Physics Core |
| spelling | doaj.art-0d8005e8e4924b2b9128310e51761b3d2022-12-22T03:27:13ZengSciPostSciPost Physics Core2666-93662022-11-015405010.21468/SciPostPhysCore.5.4.050A simple guide from machine learning outputs to statistical criteria in particle physicsCharanjit Kaur Khosa, Veronica Sanz, Michael SoughtonIn 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-$p_T$ hadronic activity, and boosted Higgs in association with a massive vector boson.https://scipost.org/SciPostPhysCore.5.4.050 |
| spellingShingle | Charanjit Kaur Khosa, Veronica Sanz, Michael Soughton A simple guide from machine learning outputs to statistical criteria in particle physics SciPost Physics Core |
| title | A simple guide from machine learning outputs to statistical criteria in particle physics |
| title_full | A simple guide from machine learning outputs to statistical criteria in particle physics |
| title_fullStr | A simple guide from machine learning outputs to statistical criteria in particle physics |
| title_full_unstemmed | A simple guide from machine learning outputs to statistical criteria in particle physics |
| title_short | A simple guide from machine learning outputs to statistical criteria in particle physics |
| title_sort | simple guide from machine learning outputs to statistical criteria in particle physics |
| url | https://scipost.org/SciPostPhysCore.5.4.050 |
| work_keys_str_mv | AT charanjitkaurkhosaveronicasanzmichaelsoughton asimpleguidefrommachinelearningoutputstostatisticalcriteriainparticlephysics AT charanjitkaurkhosaveronicasanzmichaelsoughton simpleguidefrommachinelearningoutputstostatisticalcriteriainparticlephysics |