Renormalization-group-inspired neural networks for computing topological invariants

We show that artificial neural networks (ANNs) can, to high accuracy, determine the topological invariant of a disordered system given its two-dimensional real-space Hamiltonian. Furthermore, we describe ``renormalization-group'' (RG) network, an ANN which converts Hamiltonian on large lattice another small while preserving invariant. By iteratively applying RG network ``base'' computes Chern number set size, are able process larger lattices without retraining system. therefore it is possible compute invariants for systems than those was trained. This opens door computation times significantly faster and more scalable previous methods.