Getting CICY High

Abstract

Supervised machine learning can be used to predict properties of string geometries with previously unknown features. Using the complete intersection Calabi-Yau (CICY) threefold dataset as a theoretical laboratory for this investigation, we use low \(h^{1,1}\) geometries for training and validate on geometries with large \(h^{1,1}\). Neural networks and Support Vector Machines successfully predict trends in the number of K\"ahler parameters of CICY threefolds. The numerical accuracy of machine learning improves upon seeding the training set with a small number of samples at higher \(h^{1,1}\).