Deep learning complete intersection Calabi-Yau manifolds

Abstract

We review advancements in deep learning techniques for complete intersection Calabi-Yau (CICY) 3- and 4-folds, with the aim of understanding better how to handle algebraic topological data with machine learning. We first discuss methodological aspects and data analysis, before describing neural networks architectures. Then, we describe the state-of-the art accuracy in predicting Hodge numbers. We include new results on extrapolating predictions from low to high Hodge numbers, and conversely.

19 pages; match version published in "Machine Learning in Pure Mathematics and Theoretical Physics" (edited by Y.-H. He, World Scientific Press)

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• An Overview of Multi-Task Learning in Deep Neural Networks
• Computational complexity of the landscape I
• Fibrations in CICY Threefolds
• Getting CICY High
• Machine-Learning Mathematical Structures
• Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification