Chosen architecture of the neural network (NN) to predict single zone model's SEDs. The NN consists of an input layer (orange) with 18 neurons (18 free parameters), 6 hidden layers (blue circles) with 300 neurons each, and an output layer (red) with 140 neurons (the SED values at wavelength i of the 140 points (SED(λ_i)). All neurons are connected to every neuron in the adjacent layer. This sums up to 499 340 trainable parameters.