Abstract
We revisit the classic database of weighted-${\mathbb{P}}^{4}\mathrm{s}$ 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-${\mathbb{P}}^{4}\mathrm{s}$ which admit Calabi-Yau hypersurfaces to 100% accuracy by making use of partitioning supported by the clustering behavior.
Highlights
We revisit the classic database of weighted-P4s which admit Calabi-Yau 3-fold hypersurfaces equipped with a diverse set of tools from the machine-learning toolbox
Supervised learning allows us to identify weighted-P4s which admit Calabi-Yau hypersurfaces to 100% accuracy by making use of partitioning supported by the clustering behavior
Machine-learning (ML) has become, in this age driven by big data, as indispensable a tool as calculus was to the Age of Enlightenment [1]
Summary
Artificial intelligence has permeated through all disciplines of human enterprise. As the second database of geometries in string theory, another generalization of the quintic was undertaken by placing weights on the ambient P4 and considering a single, generic Calabi-Yau hypersurface therein [45] This produced a much more balanced set of Calabi-Yau 3-folds with Æ Euler numbers, and the rough outline of the famous “mirror plot” of the distributions of 2ðh1;1 − h2;1Þ vs ðh1;1 þ h2;1Þ could already be seen to emerge. All these datasets were subsequently subsumed into the dataset created through the extraordinary work of Kreuzer and Skarke [46,47].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have