Illustration of the activations in the output layers of the CNN. While training the CNN, target activation values are provided as a 3D Gaussian distribution for age, extinction, and mass (centered on true values as denoted by the red dot) and as 1D Gaussian distributions for r_h (the blue line) and visibility (the red line). class_c/b is represented as a value of 0 or 1. During inference the network produces similar outputs, examples of which are depicted in Figs. 8 and 20.