Figure 2: Variational Autoencoder Architecture for the UCI Digits Dataset The key point is that a VAE learns the distribution of its source data rather than memorizing the source data. A data ...

The autoencoder has the same number of inputs and outputs (9) as the demo program, but for simplicity the illustrated autoencoder has architecture 9-2-9 (just 2 hidden nodes) instead of the 9-6-9 ...