Neuroevolution with NEAT

The NEAT is an algorithm that builds neural networks following an incremental and evolutionary process. It uses genetic algorithms to evolve neural networks. In the very early generation, neural networks are very simple, composed of a few nodes and connections. However, complexity is added to each generation, leading to complex networks able to solve complex problems. NEAT supports a number of mutation operators, including adding a new node and adding a new connection. As such, networks can only become more complex over time.