Inception Neural Network for Complete Intersection Calabi-Yau 3-folds

Abstract

We introduce a neural network inspired by Google's Inception model to compute the Hodge number $h^{1,1}$ of complete intersection Calabi-Yau (CICY) 3-folds. This architecture improves largely the accuracy of the predictions over existing results, giving already 97% of accuracy with just 30% of the data for training. Moreover, accuracy climbs to 99% when using 80% of the data for training. This proves that neural networks are a valuable resource to study geometric aspects in both pure mathematics and string theory.

arXiv comment13 pages; improved ablation study, additional figures, references updated

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Geometric deep learning: going beyond Euclidean data
• Machine Learning in the String Landscape
• Evolving neural networks with genetic algorithms to study the String Landscape
• Machine Learning CICY Threefolds
• Fibrations in CICY Threefolds
• Machine Learning Line Bundle Cohomologies of Hypersurfaces in Toric Varieties
• Machine Learning Line Bundle Cohomology
• Getting CICY High
• Distinguishing Elliptic Fibrations with AI
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study

Cited by in corpus (14)

• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Machine Learning Calabi-Yau Hypersurfaces
• Machine Learning Calabi-Yau Four-folds
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Deep multi-task mining Calabi-Yau four-folds
• Characterizing 4-string contact interaction using machine learning
• Deep learning complete intersection Calabi-Yau manifolds
• Universes as Big Data
• Constructing and Machine Learning Calabi-Yau Five-folds
• Machine learning the dimension of a Fano variety
• Black holes and the loss landscape in machine learning
• Calabi-Yau Four/Five/Six-folds as ${\mathbb{P}}_{\text{w}}^n$ Hypersurfaces: Machine Learning, Approximation, and Generation
• Machine learning complete intersection Calabi-Yau 3-folds
• Deep Learning Calabi-Yau four folds with hybrid and recurrent neural network architectures