Machine learning for complete intersection Calabi-Yau manifolds

Harold Erbin (1) , Riccardo Finotello (2) , Mohamed Tamaazousti (1)

1 DIASI - Département Intelligence Ambiante et Systèmes Interactifs
2 LANIE - Laboratoire de développement Analytique Nucléaire Isotopique et Elémentaire

We describe the recent developments in using machine learning techniques to compute Hodge numbers of complete intersection Calabi-Yau (CICY) 3- and 4-folds. The main motivation is to understand how to study data from algebraic geometry and solve problems relevant for string theory with machine learning. We describe the state-of-the art methods which reach near-perfect accuracy for several Hodge numbers, and discuss extrapolating from low to high Hodge numbers, and conversely.

Domains: High Energy Physics - Theory [hep-th]

Harold Erbin, Riccardo Finotello, Mohamed Tamaazousti. Machine learning for complete intersection Calabi-Yau manifolds. NeurIPS 2022 - The 36th conference on Neural Information Processing Systems, Dec 2022, New Orléans, United States. , 2022. ⟨cea-04082321⟩