Comment Re:seems a lot like human vision to me (Score 1) 130
I think it was fairly clear what was going on, the neural networks latch on to conditions that are necessary but not sufficient because they found common characteristics of real images but never got any negative feedback. Like in the peacock photo the colors and pattern are similar, but clearly not in the shape of a bird but if it's never seen any non-bird peacock colored items how's the algorithm supposed to know? At any rate, it seems like the neural network is excessively focusing on one thing, maybe it would perform better if you divided up the work so one factor didn't become dominant. For example you send outlines to one network, textures to a second network and colors to a third network then using a fourth network to try learning which of the other three to listen to. After all, the brain has very clear centers too, it's not just one big chunk of goo.