Looking at face recognition where there could be shapes combining eyes, ears, mouth and facial expressions. I wonder.
Could this be used for some sort of fractal version of machine learning. Like the old fractal mountain landscape generator.
My idea is to see if shapes could be used on the output from the weight matrices from the various layers. That is. You have some ?grid like shape that you drag connected lines on. Making the output shape look different.
Change the shape a little and see what happens. What can it be used for?
So this could be a GIMP or Photoshop like layer where you input insert non optimizable parameters. Like colors, contrast, local scaling etc. I think it can be artist preferences.
That is. Easy changeable user input. Like the mountain seed generator where you change a single number.