org.encog.neural.networks.training.genetic
Class NeuralGenome

java.lang.Object
  org.encog.solve.genetic.genome.BasicGenome
      org.encog.neural.networks.training.genetic.NeuralGenome

All Implemented Interfaces:

Comparable<Genome>, Genome

public class NeuralGenome
extends BasicGenome

Implements a genome that allows a feedforward neural network to be trained using a genetic algorithm. The chromosome for a feed forward neural network is the weight and bias matrix.

Constructor Summary

NeuralGenome(NeuralGeneticAlgorithm nga, BasicNetwork network)
Construct a neural genome.

Method Summary

void	decode() Decode the genomes into a neural network.
void	encode() Encode the neural network into genes.

Methods inherited from class org.encog.solve.genetic.genome.BasicGenome

calculateGeneCount, compareTo, getAdjustedScore, getAmountToSpawn, getChromosomes, getGeneticAlgorithm, getGenomeID, getOrganism, getScore, mate, setAdjustedScore, setAmountToSpawn, setGeneticAlgorithm, setGenomeID, setOrganism, setScore, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

NeuralGenome

public NeuralGenome(NeuralGeneticAlgorithm nga,
                    BasicNetwork network)

Construct a neural genome.

Parameters:

nga - The NeuralGeneticAlgorithm class to use.

network - The network to use.

Method Detail

decode

public void decode()

Decode the genomes into a neural network.

encode

public void encode()

Encode the neural network into genes.