Neuroevolution of Augmenting Topologies - Complexification

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