Artificial neural networks are biologically-inspired computational abstractions of organic neural networks. Genetic algorithms are biologically-inspired search techniques which exploit aspects of Darwinian evolution. Both have been around for nearly half a century, but only in the past decade or so has a body of active research grown out of the concept of blending the two. A particular neuroevolutionary algorithm (NEAT--NeuroEvolution of Augmenting Topologies) will be discussed, along with a few typical experiments, followed by some possible future elaborations on this heavily interdisciplinary approach to artificial intelligence.