Neuroevolution with Analog Genetic Encoding

The evolution of artificial neural networks (ANNs) is often used to tackle difficult control problems. There are different approaches to the encoding of neural networks in artificial genomes. Analog Genetic Encoding (AGE) is a new implicit method derived from the observation of biological genetic regulatory networks. This paper shows how AGE can be used to simultaneously evolve the topology and the weights of ANNs for complex control systems. AGE is applied to a standard benchmark problem and we show that its performance is equivalent or superior to some of the most powerful algorithms for neuroevolution in the literature.

Published in:
Proceedings of the 9th Conference on Parallel Problem Solving from Nature (PPSN iX), 9, 671--680
Presented at:
Parallel Problem Solving from Nature - PPSN iX, Reykjavik, Iceland, 9-13 September 2006
Other identifiers:

Note: The status of this file is: Anyone

 Record created 2006-06-27, last modified 2020-10-24

Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
(Not yet reviewed)