NEAT is Neuro-Evolution of Augmenting Topologies, a neuro-evolution technique devised by Kenneth Stanley while part of the Neural Networks Research Group, University of Texas at Austin. SharpNEAT is a complete implementation of NEAT written in C# and targeting the .Net runtime environment.
Experiment/Investigation write ups
- A Neural Network Controller for the Physical Travelling Salesperson Problem. [July 2005]
- A Fast Equivalent for System.Random. Article posted to CodeProject.com [December 2004]
- An Integer Based Neural Network [September 2004]
- Phased Searching with NEAT: Alternating Between Complexification And Simplification. [August 2004]
- Neural Network Code Optimizations [June 2004]
SharpNEAT in Academia
David D'Ambrosio and Kenneth Stanley at the University of Central Florida used SharpNeat in a paper presented at GECCO 2007 introducing their exciting new indirect encoding known as Compositional Pattern Producing Networks (CPPNs).
Their version of SharpNEAT supporting CPPNs (HyperSharpNEAT) is available from the UCF EPLEX download page. Their paper is also available from the UCF EPLEX site: A Novel Generative Encoding for Exploiting Neural Network Sensor and Output Geometry Nominated for Best Paper Award in Generative and Developmental Systems, GECCO 2007
-
Wesley Tansey extended SharpNEAT to allow parallel processing across multiple CPUs while at Virginia Tech. This work is hosted on Codeplex as ParaSharpNEAT.
SharpNEAT on the web
- Genetic Art with SharpNEAT. Holger Ferstl created this SharpNEAT based application that evolves images. It relies on a user repeatedly selecting their favourite image from a page of candidate images. The application was built on the .Net 2.0 framework and is capable of generated some quite amazing pictures. Thanks Holger! Now for the eye candy - these were generated by me, there are more examples through the link...
|
|