Compositional Pattern Producing Networks (CPPNs) are cool, so I wrote a C# implementation and generated some!  This was a just-for-fun project unrelated to any class assignments, games or competitions.

Fitness of a network was based on how well the resulting image didn’t compress via the Deflate algorithm – hence I refer to these networks as Complex Pattern Producing Networks.  There’s some nifty Nyquistian nonsense where the evolved networks take advantage of how I’m sampling.  GAs are so exploitative.

I was pleased with the results of this experiment because I had no expectations or goals – that’s usually a recipe for happiness.  The other cool part is I’ve got all the genomes saved, so it’s trivial to expand one of the 256 x 256 images to N x M and use it as a desktop background.  Genome sizes varied between 16 and 2048 bytes.

If you want the code for some reason, let me know – it’s all C# WinForm horribleness with most of the comments being commented out code, so don’t go using it to judge me.  If you really want to play with it, tell me to reimplement with JavaScript and HTML5.

Google Photo Galleries (Populations): 1 2 3 4 5 6 7 8 9 10 11 12 13 14