Deep learning in the heterotic orbifold landscape

We use deep autoencoder neural networks to draw a chart of the heterotic Z6-II orbifold landscape. Even though the autoencoder is trained without knowing the phenomenological properties of the Z6-II orbifold models, it identifies fertile islands in this chart where phenomenologically promising model...

Full description

Saved in:
Bibliographic Details
Published inNuclear physics. B Vol. 940; pp. 113 - 129
Main Authors Mütter, Andreas, Parr, Erik, Vaudrevange, Patrick K.S.
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.03.2019
Elsevier
Online AccessGet full text

Cover

More Information
Summary:We use deep autoencoder neural networks to draw a chart of the heterotic Z6-II orbifold landscape. Even though the autoencoder is trained without knowing the phenomenological properties of the Z6-II orbifold models, it identifies fertile islands in this chart where phenomenologically promising models cluster. Then, we apply a decision tree to our chart in order to extract the defining properties of the fertile islands. Based on this information we propose a new search strategy for phenomenologically promising string models.
ISSN:0550-3213
1873-1562
DOI:10.1016/j.nuclphysb.2019.01.013