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

All Known Implementing Classes:
MutatePerturbLinkWeight, MutateResetLinkWeight

public interface MutateLinkWeight

This interface defines various ways that a NEAT network can have its link weights mutated. ----------------------------------------------------------------------------- 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
 EvolutionaryAlgorithm getTrainer()
           
 void init(EvolutionaryAlgorithm theTrainer)
          Setup the link mutator.
 void mutateWeight(Random rnd, NEATLinkGene linkGene, double weightRange)
          Perform the weight mutation on the specified link.
 

Method Detail

getTrainer

EvolutionaryAlgorithm getTrainer()
Returns:
The training class that this mutator is being used with.

init

void init(EvolutionaryAlgorithm theTrainer)
Setup the link mutator.

Parameters:
theTrainer - The training class that this mutator is used with.

mutateWeight

void mutateWeight(Random rnd,
                  NEATLinkGene linkGene,
                  double weightRange)
Perform the weight mutation on the specified link.

Parameters:
rnd - A random number generator.
linkGene - The link to mutate.
weightRange - The weight range, weights are between -weightRange and +weightRange.


Copyright © 2014. All Rights Reserved.