Breeding Realistic D?Brane Models

Intersecting branes provide a useful mechanism to construct particle physics models from string theory with wide variety of desirable characteristics. The landscape such can be enormous, and navigating towards regions which are most phenomenologically interesting is potentially challenging. Machine learning techniques used efficiently large numbers consistent models. In this work we phrase the problem finding intersecting D-brane in terms genetic algorithms, mimic natural selection evolve population collectively optimal solutions. For four-dimensional N = 1 ${\cal N}=1$ supersymmetric type IIA orientifold D6-branes, demonstrate that O ( 10 6 ) $\mathcal {O}(10^6)$ unique, fully easily constructed, and, by judicious choice search environment hyper-parameters, 30 % {O}(30\%)$ found contain desired Standard Model gauge group factor. Having sizable sample allows us draw some preliminary statistics brane both without restriction having