How to Train a Neural Net to Remove Noise From Noise

In Wolfram language, the network kind of looks at a high level like this schematically. It makes an informationally compressed version of each image and then to expand it again through what's usually called the unit neural net. But what if we apply this network to pure noise? The network has been set up to always eventually evolve either to the A attractor or the B attractor, but which it chooses in a particular case will depend on the details of the initial noise. So in effect, the network seems to be picking at random to fish either the A or B out of the noise. Let me see if I can show you that.