Legend for the figure illustrating GAN training (from the referenced Goodfellow et al., 2014 paper): $\mathbf{z}$: noise distribution (mapped to $\mathbf{x}$). $\mathbf{x}$: data distribution. Blue: discriminative distribution. Green: generative distribution. Black: data distribution (real data). Read left to right, the discriminative distribution is repeatedly updated to minimize the difference between the generative distribution and the true data distribution, so that the generative distribution becomes a more accurate approximation of the real data.