Complexification
Ordinarily, a neural network topology is designed by a human experimenter, and a genetic algorithm is used to try out effective connection weights for it. The topology of the network remains unaltered.
The NEAT approach begins with a perceptron-like feed-forward network of only input neurons and output neurons. As evolution progresses through discrete steps, the complexity of the network's topology may grow, either by inserting a new neuron into a connection path, or by creating a new connection between (formerly unconnected) neurons.
Read more about this topic: Neuroevolution Of Augmenting Topologies