AI classifies space-time
More in Learning the universe
Neural networks find efficient ways to compute the Hilbert series, an important counting function in algebraic geometry and gauge theory.
Neural networks find numerical solutions to Hermitian Yang-Mills equations, a difficult system of PDEs crucial to mathematics and physics.
Unsupervised machine-learning of the Hodge numbers of Calabi-Yau hypersurfaces detects new patterns with an unexpected linear dependence.