NationMaster - Encyclopedia: NeuroEvolution by Augmented Topologies

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

External links

Ken Stanley's website (http://www.cs.utexas.edu/users/kstanley/)
NEAT Homepage (http://nn.cs.utexas.edu/project-view.php?RECORD_KEY(Projects)=ProjID&ProjID(Projects)=14)
Evolving Adaptive Neural Networks with and without Adaptive Synapses (http://nn.cs.utexas.edu/downloads/papers/stanley.geccolbp03.pdf)
download NEAT 1.1 (http://nn.cs.utexas.edu/downloads/software/neat.1.1.tar.gz)

Results from FactBites:

NeuroEvolution of Augmented Topologies - Wikipedia, the free encyclopedia (360 words)
	Neuro-Evolution of Augmenting Topologies (NEAT) is a genetic algorithm for evolving neural networks.
	Conventional neural network topology is defined by the developer, and the genetic algorithm is used to modify weights in the network.
	As the evolution progresses, the topology of the network may be augmented by adding a neuron along an exisiting connection, or by adding a new connection between previously unconnected neurons.

More results at FactBites »

COMMENTARY

Share your thoughts, questions and commentary here

Want to know more?
Search encyclopedia, statistics and forums:

Feeds | Contact
The Wikipedia article included on this page is licensed under the GFDL.
Images may be subject to relevant owners' copyright.
All other elements are (c) copyright NationMaster.com 2003-5. All Rights Reserved.
Usage implies agreement with terms.