Deep convolutional neural network for symmetry classification. (a) Schematic of the DCNN structure. A lattice image is input and transformed via a 2D fast Fourier Transform (FFT). This image is input to the DCNN, which outputs probability of classification into one of the six classes (five Bravais lattice types, and one for “noise”, i.e., no periodicity). (b) Training and validation accuracy as a function of epoch. One epoch is one complete pass through the training data. The dashed line is a guide only with a value of 0.85