|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
public interface NEATGenomeFactory
This interface defines additional methods defined to create NEAT genomes. It is an extension to the non-NEAT specific GenomeFactory. ----------------------------------------------------------------------------- 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
Method Summary | |
---|---|
NEATGenome |
factor(List<NEATNeuronGene> neurons,
List<NEATLinkGene> links,
int inputCount,
int outputCount)
Create a NEAT genome from a list of links and neurons. |
NEATGenome |
factor(Random rnd,
NEATPopulation pop,
int inputCount,
int outputCount,
double connectionDensity)
Create a new random NEAT genome. |
Methods inherited from interface org.encog.ml.ea.genome.GenomeFactory |
---|
factor, factor |
Method Detail |
---|
NEATGenome factor(List<NEATNeuronGene> neurons, List<NEATLinkGene> links, int inputCount, int outputCount)
neurons
- A list of neuron genes.links
- A list of link genes.inputCount
- The input count.outputCount
- The output count.
NEATGenome factor(Random rnd, NEATPopulation pop, int inputCount, int outputCount, double connectionDensity)
rnd
- A random number generator.pop
- The NEAT population.inputCount
- The input count.outputCount
- The output count.connectionDensity
- The connection density. Specify 1.0 for fully connected.
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |