Reconstruction mean squared error (MSE) and values of the minimized Kullback-Leibler Divergence (Loss) ΔD_KL (D_KL in Eq. (8) except constant terms) depending on the dimension of the latent space (also called number of features, x-axis). The values were determined using the NEAT-VAE with a configuration of six layers, 30 hidden neurons in the encoder and decoder layers, noise transformation parameters μ_N = −7 and σ_N = 1, learning rates of 0.005 for the network weights and 0.001 for ξ_N, and a batchsize of 128. We did not track all normalization constants through the calculations, which leads to negative values for the loss.