Machine learning string standard models
We study machine learning of phenomenologically relevant properties of string compactifications, which arise in the context of heterotic line bundle models. Both supervised and unsupervised learning are considered. We find that, for a fixed compactification manifold, relatively small neural networks...
Main Authors: | , , , |
---|---|
Format: | Journal article |
Language: | English |
Published: |
American Physical Society
2022
|
_version_ | 1797107462784942080 |
---|---|
author | Deen, R He, Y-H Lee, S-J Lukas, A |
author_facet | Deen, R He, Y-H Lee, S-J Lukas, A |
author_sort | Deen, R |
collection | OXFORD |
description | We study machine learning of phenomenologically relevant properties of string compactifications, which arise in the context of heterotic line bundle models. Both supervised and unsupervised learning are considered. We find that, for a fixed compactification manifold, relatively small neural networks are capable of distinguishing consistent line bundle models with the correct gauge group and the correct chiral asymmetry from random models without these properties. The same distinction can also be achieved in the context of unsupervised learning, using an autoencoder. Learning nontopological properties, specifically the number of Higgs multiplets, turns out to be more difficult, but is possible using sizeable networks and feature-enhanced datasets. |
first_indexed | 2024-03-07T07:14:58Z |
format | Journal article |
id | oxford-uuid:32e0d0fa-a99a-447e-851f-c2c5604a3970 |
institution | University of Oxford |
language | English |
last_indexed | 2024-03-07T07:14:58Z |
publishDate | 2022 |
publisher | American Physical Society |
record_format | dspace |
spelling | oxford-uuid:32e0d0fa-a99a-447e-851f-c2c5604a39702022-08-09T15:01:56ZMachine learning string standard modelsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:32e0d0fa-a99a-447e-851f-c2c5604a3970EnglishSymplectic ElementsAmerican Physical Society2022Deen, RHe, Y-HLee, S-JLukas, AWe study machine learning of phenomenologically relevant properties of string compactifications, which arise in the context of heterotic line bundle models. Both supervised and unsupervised learning are considered. We find that, for a fixed compactification manifold, relatively small neural networks are capable of distinguishing consistent line bundle models with the correct gauge group and the correct chiral asymmetry from random models without these properties. The same distinction can also be achieved in the context of unsupervised learning, using an autoencoder. Learning nontopological properties, specifically the number of Higgs multiplets, turns out to be more difficult, but is possible using sizeable networks and feature-enhanced datasets. |
spellingShingle | Deen, R He, Y-H Lee, S-J Lukas, A Machine learning string standard models |
title | Machine learning string standard models |
title_full | Machine learning string standard models |
title_fullStr | Machine learning string standard models |
title_full_unstemmed | Machine learning string standard models |
title_short | Machine learning string standard models |
title_sort | machine learning string standard models |
work_keys_str_mv | AT deenr machinelearningstringstandardmodels AT heyh machinelearningstringstandardmodels AT leesj machinelearningstringstandardmodels AT lukasa machinelearningstringstandardmodels |