The demo begins by creating a Dataset object that stores the images in memory. Next, the demo creates a 65-32-8-32-65 neural autoencoder. An autoencoder learns to predict its input. Therefore, the ...

An autoencoder learns to predict its input. Therefore, the autoencoder input and output both have 65 values -- 64 pixel grayscale values (0 to 16) plus a label (0 to 9). Notice that the demo program ...