Deep learning and k-means clustering in heterotic string vacua with line bundles
From MaRDI portal
(Redirected from Publication:779316)
Abstract: We apply deep-learning techniques to the string landscape, in particular, heterotic string theory on simply-connected Calabi-Yau threefolds with line bundles. It turns out that three-generation models cluster in particular islands specified by deep autoencoder networks and k-means++ clustering. Especially, we explore mutual relations between model parameters and the cluster with densest three-generation models (called "3-generation island"). We find that the 3-generation island has a strong correlation with the topological data of Calabi-Yau threefolds, in particular, second Chern class of the tangent bundle of the Calabi-Yau threefolds. Our results also predict a large number of Higgs pairs in the 3-generation island.
Recommendations
- Deep learning for K3 fibrations in heterotic/type IIA string duality
- Deep learning in the heterotic orbifold landscape
- Moduli-dependent Calabi-Yau and SU(3)-structure metrics from machine learning
- Machine learning in the string landscape
- Heterotic String Model Building with Monad Bundles and Reinforcement Learning
- Explore and Exploit with Heterotic Line Bundle Models
- Machine Learning Calabi–Yau Metrics
- Line bundle embeddings for heterotic theories
- Machine learning Calabi-Yau four-folds
- Kähler geometry of framed quiver moduli and machine learning
Cites work
- scientific article; zbMATH DE number 6381735 (Why is no real title available?)
- Branes with brains: exploring string vacua with deep reinforcement learning
- Breaking GUT groups in \(F\)-theory
- D-brane probes, RR tadpole cancellation and \(K\)-theory charge
- D-branes and K-theory
- Data science applications to string theory
- Deep learning in the heterotic orbifold landscape
- Evolving neural networks with genetic algorithms to study the string landscape
- Getting CICY high
- Guts and exceptional branes in F-theory. II: Experimental predictions
- Heterotic GUT and standard model vacua from simply connected Calabi--Yau manifolds
- Heterotic line bundle standard models
- Hilbert's Tenth Problem is Unsolvable
- Machine learning in the string landscape
- On Information and Sufficiency
- On free quotients of complete intersection Calabi-Yau manifolds
- Realistic three-generation models from \(\mathrm{SO}(32)\) heterotic string theory
- Reducing the Dimensionality of Data with Neural Networks
- SO(32) heterotic line bundle models
- SO(32) heterotic standard model vacua in general Calabi-Yau compactifications
- Scikit-learn: machine learning in Python
- Searching the landscape of flux vacua with genetic algorithms
Cited in
(15)- Branes with brains: exploring string vacua with deep reinforcement learning
- Eigenvalues and eigenforms on Calabi-Yau threefolds
- Generalized vanishing theorems for Yukawa couplings in heterotic compactifications
- Heterotic line bundle models on generalized complete intersection Calabi Yau manifolds
- On the Search for Low W0
- Neural network learning and quantum gravity
- Autoencoder-driven clustering of intersecting D-brane models via tadpole charge
- Statistical Predictions in String Theory and Deep Generative Models
- Explore and Exploit with Heterotic Line Bundle Models
- Algorithmically solving the tadpole problem
- 134 billion intersecting brane models
- Computation of quark masses from string theory
- Machine learning in the string landscape
- Deep learning in the heterotic orbifold landscape
- Upper bound on the Atiyah-Singer index from tadpole cancellation
This page was built for publication: Deep learning and k-means clustering in heterotic string vacua with line bundles
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q779316)
