Neuro-Evolution of Augmenting Topologies (NEAT) is a genetic algorithm for evolving neural networks. Developed by Ken Stanley at University of Texas at Austin and published under the GPL; it integrates with Guile, a GNU common lisp interpreter. Ken Stanley's NEAT is considered the base reference for implementations of the NEAT algorithm.

Complexification

Conventional neural network topology is defined by the developer, and the genetic algorithm is used to modify weights in the network. The complexity of such a network stays constant through the evolution process, as the number of nodes, and connections between nodes remains constant. The NEAT approach begins with perceptron like structure, with no hidden neurons. It is a simplistic feed-forward network of input neurons and output neurons, representing the input and output signals. As the evolution progresses, the topology of the network may be augmented by adding a neuron along an exisiting connection, or by adding anew connection between previously unconnected neurons.

Phased Pruning

An extension of Ken Stanley's NEAT, developed by Colin Green, adds periodic pruning of the network topologies of candidate solutions during the evolution process. This addition addressed concern that unbounded automated growth would generate unessessary structure.

rtNEAT

In 2003 Stanley devised an extension to NEAT that allows evolution to occur in real time rather than through an iteration of generations as used by most genetic algorithm. The basic idea is to put the population under constant evaluation with a "lifetime" timer on each individual in the population. When a network's timer expires its current fitness measure is examined to see whether it falls near the bottom of the population, and if so it is discarded and replaced by a new network bred from two high-fitness parents. A timer is set for the new neuron and it is placed in the population to participate in the ongoing evaluations.

External links

• Ken Stanley's website
• NEAT Homepage
• Project NERO Website, description of an example application of rtNEAT.
• "Evolving Adaptive Neural Networks with and without Adaptive Synapses".
• download NEAT 1.1