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

Harold Erbin, Riccardo Finotello
7/27/2020
hep-thcs.LGmath.AG

Official code: thesfinox/ml-cicy (7 stars, last commit 2021-01-03).

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.

View on arXivView PDF

Code Implementations(1)

thesfinox/ml-cicyOfficial100%

Machine Learning for CICY 3-folds

73Jupyter NotebookFeb 18, 20205 years ago
analysisartificial-intelligencecalabi-yau-manifoldsdifferential-geometryhodge-number+5 more

Similar Papers

Deep learning complete intersection Calabi-Yau manifolds

84% match2023

Graph Neural Networks and 3-Dimensional Topology

78% match1 repo52023

Deep Manifold Part 2: Neural Network Mathematics

78% match2025

Defining Neural Network Architecture through Polytope Structures of Dataset

78% match2024

When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task

77% match1 repo2026

E(n) Equivariant Topological Neural Networks

77% match1 repo412024

Cite this paper

@article{erbin2020inception,
  title  = {Inception Neural Network for Complete Intersection Calabi-Yau 3-folds},
  author = {Harold Erbin and Riccardo Finotello},
  year   = {2020},
  eprint = {2007.13379},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2007.13379}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2007.13379.svg)](https://codeofpaper.com/paper/2007.13379)

Discussion