Work

Machine learning Kreuzer–Skarke Calabi–Yau threefolds

Year: 2025

Type: article

Abstract: By using a fully connected feedforward neural network, we study topological invariants of a class of Calabi–Yau manifolds constructed as hypersurfaces in toric varieties associated with reflexive polytopes from the Kreuzer–Skarke database. In particular, we find the existence of a simple expression for the Euler number that can be learned in terms of limited data extracted from the polytope and its dual.

Source: International Journal of Modern Physics A

DOI: 10.1142/s0217751x25500976

Authors: Per Berglund, Ben Campbell, Vishnu Jejjala

Institutions: University of New Hampshire, University of the Witwatersrand, National Institute for Theoretical Physics

Language: English

Topic: Algebraic Geometry and Number Theory

Subfield: Geometry and Topology

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

Funders: U.S. Department of Energy, National Research Foundation

Award: THEORETICAL HIGH ENERGY PHYSICS AT THE UNIVERSITY OF NEW HAMPSHIRE