org.encog.neural.neat.training.opp.links

Interface SelectLinks

All Known Implementing Classes:

SelectFixed, SelectProportion

public interface SelectLinks

This interface defines ways that NEAT links can be chosen for mutation. ----------------------------------------------------------------------------- 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

Methods

Modifier and Type	Method and Description
EvolutionaryAlgorithm	getTrainer()
void	init(EvolutionaryAlgorithm theTrainer) Setup the selector.
List<NEATLinkGene>	selectLinks(Random rnd, NEATGenome genome) Select links from the specified genome.

Method Detail

getTrainer

EvolutionaryAlgorithm getTrainer()

Returns:

The trainer being used.

init

void init(EvolutionaryAlgorithm theTrainer)

Setup the selector.

Parameters:

theTrainer - The trainer.

selectLinks

List<NEATLinkGene> selectLinks(Random rnd,
                             NEATGenome genome)

Select links from the specified genome.

Parameters:

rnd - A random number generator.

genome - The genome to select from.

Returns:

A List of link genomes.