mlsanityData to 7 Oct 2026

Deep multi-task mining Calabi-Yau four-folds

arXiv 2108.02221 ↗First posted 4 Aug 2021hep-th cs.LG math.AGcited by 11

Not on the map. Why?

Abstract (arXiv)

We continue earlier efforts in computing the dimensions of tangent space cohomologies of Calabi-Yau manifolds using deep learning. In this paper, we consider the dataset of all Calabi-Yau four-folds constructed as complete intersections in products of projective spaces. Employing neural networks inspired by state-of-the-art computer vision architectures, we improve earlier benchmarks and demonstrate that all four non-trivial Hodge numbers can be learned at the same time using a multi-task architecture. With 30% (80%) training ratio, we reach an accuracy of 100% for h(1,1) and 97% for h(2,1) (100% for both), 81% (96%) for h(3,1), and 49% (83%) for h(2,2). Assuming that the Euler number is known, as it is easy to compute, and taking into account the linear constraint arising from index computations, we get 100% total accuracy.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 24 of its 57 references that are in the map. First posted on arXiv 4 Aug 2021.

Builds on

24 of 57 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Layer Normalizationcited by 5,579
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  11. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
  12. 2017A Survey on Multi-Task Learningcited by 838
12 more
  1. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 688
  2. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  3. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  4. 2021Explaining Neural Scaling Lawscited by 353
  5. 2020Detecting Symmetries with Neural Networkscited by 33
  6. 2018Machine Learning CICY Threefoldscited by 22
  7. 2017Deep-Learning the Landscapecited by 21
  8. 2020Machine learning for complete intersection Calabi-Yau manifolds: a methodological studycited by 17
  9. 2020Machine Learning Calabi-Yau Four-foldscited by 17
  10. 2020Inception Neural Network for Complete Intersection Calabi-Yau 3-foldscited by 14
  11. 2020Explore and Exploit with Heterotic Line Bundle Modelscited by 11
  12. 2021Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identificationcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 5; 2024: 1.

11 papers.

  1. 2021Machine Learning Calabi-Yau Hypersurfacescited by 15
  2. 2023The R-mAtrIx Netcited by 4
  3. 2023Constructing and Machine Learning Calabi-Yau Five-foldscited by 4
  4. 2022Machine Learning Algebraic Geometry for Physicscited by 3
  5. 2022Identifying equivalent Calabi--Yau topologies: A discrete challenge from math and physics for machine learningcited by 2
  6. 2024Deep Learning Calabi-Yau four folds with hybrid and recurrent neural network architecturescited by 2
  7. 2023Deep learning complete intersection Calabi-Yau manifoldscited by 1
  8. 2022Trustworthiness of Laser-Induced Breakdown Spectroscopy Predictions via Simulation-based Synthetic Data Augmentation and Multitask Learningcited by 0
  9. 2022Characterizing 4-string contact interaction using machine learningcited by 0
  10. 2023Black holes and the loss landscape in machine learningcited by 0
  11. 2023Calabi-Yau Four/Five/Six-folds as mathbbPnw Hypersurfaces: Machine Learning, Approximation, and Generationcited by 0