Unsupervised machine-learning of the Hodge numbers of Calabi-Yau hypersurfaces detects new patterns with an unexpected linear dependence.
Machine learning Calabi-Yau hypersurfaces
We revisit the classic database of weighted -P^4s which admit Calabi-Yau 3-fold hypersurfaces equipped with a diverse set of tools from the machine-learning toolbox. Unsupervised techniques identify an unanticipated almost linear dependence of the topological data on the weights. This then allows us to identify a previously unnoticed clustering in the Calabi-Yau data. Supervised techniques are successful in predicting the topological parameters of the hypersurface from its weights with an accuracy of R^2>95%. Supervised learning also allows us to identify weighted-P^4s which admit Calabi-Yau hypersurfaces to 100% accuracy by making use of partitioning supported by the clustering behavior.
More in Learning the universe
AI classifies space-time
A neural network learns to classify different types of spacetime in general relativity according to their algebraic Petrov classification.
Machine learning Hilbert series
Neural networks find efficient ways to compute the Hilbert series, an important counting function in algebraic geometry and gauge theory.
Line bundle connections
Neural networks find numerical solutions to Hermitian Yang-Mills equations, a difficult system of PDEs crucial to mathematics and physics.