Distinguishing Calabi-Yau Topology Using Machine Learning
Harvard Data Science Review · 30.01.2026 · 8 (1)
DOI: 10.1162/99608f92.b56a4380 ↗Kurz gefasst
Fachartikel in der Zeitschrift Harvard Data Science Review, online erschienen am 30.01.2026. Verfasst von Yang-Hui He und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
While the earliest applications of AI methodologies to pure mathematics and theoretical physics began with the study of Hodge numbers of Calabi-Yau manifolds, the topology type of such manifold also crucially depend on their intersection theory. Continuing the paradigm of machine learning algebraic geometry, we here investigate the triple intersection numbers, focusing on certain divisibility invariants constructed therefrom, using the Inception convolutional neural network. We find $\sim90\%$ accuracies in prediction in a standard fivefold cross-validation, signifying that more sophisticated tasks of identification of manifold topologies can also be performed by machine learning.
Zitieren
APA
He, Y., Yao, Z., & Yau, S. (2026). Distinguishing Calabi-Yau Topology Using Machine Learning. Harvard Data Science Review, 8(1). https://doi.org/10.1162/99608f92.b56a4380
Vancouver
He Y, Yao Z, Yau S. Distinguishing Calabi-Yau Topology Using Machine Learning. Harvard Data Science Review. 2026;8(1). doi:10.1162/99608f92.b56a4380
BibTeX
@article{He2026,
author = {He, Yang-Hui and Yao, Zhi-Gang and Yau, Shing-Tung},
title = {Distinguishing Calabi-Yau Topology Using Machine Learning},
journal = {Harvard Data Science Review},
year = {2026},
volume = {8},
number = {1},
doi = {10.1162/99608f92.b56a4380}
}
EUVIMED