Author here.<p>I've been thinking about minimal models of evolution. I concluded that you need information to be copied with some transformation, some death, and a way for the information in question to encode its ability to avoid death.<p>In trying to simulate that, neural networks were a good fit since they are universal function solvers. I definitely took some inspiration from NEAT[0], though I'm not using any form of crossover.<p>AMA<p>[0] <a href="https://en.wikipedia.org/wiki/Neuroevolution_of_augmenting_topologies" rel="nofollow">https://en.wikipedia.org/wiki/Neuroevolution_of_augmenting_t...</a>