org.encog.neural.neat
Class NEATCODEC
java.lang.Object
org.encog.neural.neat.NEATCODEC
- All Implemented Interfaces:
- Serializable, GeneticCODEC
public class NEATCODEC
- extends Object
- implements GeneticCODEC, Serializable
This CODEC is used to create phenomes (NEATNetwork) objects using a genome
(NEATGenome). Conversion is only one direction. You are allowed to transform
a NEAT genome into a NEATNetwork, but you cannot transform a NEAT phenome
back into a genome. The main reason is I have not found a great deal of need
to go the other direction. If someone ever does find a need and creates a
encode method, please consider contributing it to the Encog project. :)
-----------------------------------------------------------------------------
http://www.cs.ucf.edu/~kstanley/
Encog's NEAT implementation was drawn from the following three Journal
Articles. For more complete BibTeX sources, see NEATNetwork.java.
Evolving Neural Networks Through Augmenting Topologies
Generating Large-Scale Neural Networks Through Discovering Geometric
Regularities
Automatic feature selection in neuroevolution
- See Also:
- Serialized Form
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
NEATCODEC
public NEATCODEC()
decode
public MLMethod decode(Genome genome)
- Decode the specified genome into a phenome. A phenome is an actual
instance of a genome that you can query.
- Specified by:
decode
in interface GeneticCODEC
- Parameters:
genome
- The genome to decode.
- Returns:
- The phenome.
encode
public Genome encode(MLMethod phenotype)
- This method is not currently implemented. If you have need of it, and do
implement a conversion from a NEAT phenotype to a genome, consider
contribution to the Encog project.
- Specified by:
encode
in interface GeneticCODEC
- Parameters:
phenotype
- Not used.
- Returns:
- Not used.
Copyright © 2014. All Rights Reserved.