Deep Learning, where large data sets “train” a computer algorithm to recognize patterns and features much better then people (think chess and go) - is a black box that we can’t look inside to view the clockwork. The answers are presented in a small window in the side of the box but what’s in the box - programmers, physicists and the like have no clue.
Add to that now neuroevolution programming where these deep learning algorithms are set loose to “evolve” efficiently. Adding insult to injury is the programming game of the century.
“The core idea of neuroevolution, then, is simple: it’s essentially just breeding. But beyond that, things get a lot more interesting. Over the decades since the first fixed-topology neuroevolution algorithms began to appear, researchers have continually run into the frustrating reality that even as the algorithms create new possibilities, the brains they can evolve remain far from what evolved in nature. There are many reasons for this gap, but a fascinating aspect of the field is that every so often a surprising new insight into the workings of natural evolution emerges, resulting in a leap in the capability of neuroevolution algorithms. Often, these insights are counter-intuitive, overturning previous assumptions and highlighting the mysteriousness of nature. As we gradually chip away at these mysteries, we discover how to fashion increasingly powerful algorithms for evolving brains.”