Abstract
We use the machine learning technique to search the polytope which can result in an orientifold Calabi-Yau hypersurface and the ``naive type IIB string vacua.'' We show that neural networks can be trained to give a high accuracy for classifying the orientifold property and vacua based on the newly generated orientifold Calabi-Yau database with ${h}^{1,1}(X)\ensuremath{\le}6$ [R. Altman, J. Carifio, X. Gao, and B. Nelson, Orientifold Calabi-Yau threefolds with divisor involutions and string landscape, arXiv:2111.03078]. This indicates the orientifold symmetry may already be encoded in the polytope structure. In the end, we try to use the trained neural networks model to go beyond the database and predict the orientifold signal of polytope for higher ${h}^{1,1}(X)$.
Highlights
Orientifold Calabi-Yau threefolds represent a rich phenomenological starting point for the construction of concrete string models for both particle physics and cosmology
In [1], constructing orientifold Calabi-Yau involves several technical procedures which we summarized in Sec
“background” distributions is extremely small and we are confident to claim that our neural network is an accurate and good classifier to pick out the polytopes which can result in an orientifold Calabi-Yau and string vacua
Summary
Orientifold Calabi-Yau threefolds represent a rich phenomenological starting point for the construction of concrete string models for both particle physics and cosmology. The number of possible involutions increase exponentially and for some of them it is extremely slow to get the fixed loci Putting all these difficulties together, it is very unlikely to scan all the Kreuzer-Skarke database in a brute force way to get the orientifold Calabi-Yau with an accessible computer power.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
