org.encog.neural.neat.training.opp
Class NEATMutateAddNode
java.lang.Object
org.encog.neural.neat.training.opp.NEATMutation
org.encog.neural.neat.training.opp.NEATMutateAddNode
- All Implemented Interfaces:
- EvolutionaryOperator
public class NEATMutateAddNode
- extends NEATMutation
Mutate a genome by adding a new node. To do this a random link is chosen. The
a neuron is created to split this link. This removes one link and adds two
new links. The weights on the new link are created to minimize changes to the
values produced by the neuron.
-----------------------------------------------------------------------------
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
Methods inherited from class org.encog.neural.neat.training.opp.NEATMutation |
chooseRandomNeuron, createLink, getElementPos, getOwner, init, isDuplicateLink, isNeuronNeeded, obtainGenome, offspringProduced, parentsNeeded, removeNeuron |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
NEATMutateAddNode
public NEATMutateAddNode()
performOperation
public void performOperation(Random rnd,
Genome[] parents,
int parentIndex,
Genome[] offspring,
int offspringIndex)
- Perform the evolutionary operation.
- Parameters:
rnd
- A random number generator.parents
- The parents.parentIndex
- The index into the parents array.offspring
- The offspring.offspringIndex
- An index into the offspring array.
Copyright © 2014. All Rights Reserved.