Neuroevolution with NEAT
Alexandre Bergel · Apress eBooks · 2020
NEAT is an algorithm that builds neural networks following an incremental and evolutionary process. It uses a genetic algorithm to evolve networks. In the very early generations, neural networks are very simple, composed of a few nodes and connections. However, complexity is added in each generation. NEAT supports a number of mutations, and these mutations may add new nodes or new connections. As such, networks can only become more complex over time.