Machine Learning the Spin-glass State

Machine learning techniques have found use in the supervised classification of computational condensed matter phases by generalizing their training to situations where Monte Carlo data may be hard to obtain or is unavailable. We present evidence that a convolutional neural network can characterize the spin-glass state and distinguish it from paramagnetic and ferromagnetic states in short-range three-dimensional Ising spin-glass models. As a generalization test, we find that such a neural network does not find a significant spin-glass state in the Gaussian disordered Edwards-Anderson model in a field, in accord with previous Monte Carlo results attempting to find a de Almeida-Thouless line in short-ranged models.