org.encog.neural.neat.training

Class NEATNeuronGene

java.lang.Object

org.encog.neural.neat.training.NEATBaseGene

org.encog.neural.neat.training.NEATNeuronGene

All Implemented Interfaces:

Serializable, Comparable<NEATBaseGene>

public class NEATNeuronGene
extends NEATBaseGene
implements Serializable

Implements a NEAT neuron gene. NeuroEvolution of Augmenting Topologies (NEAT) is a genetic algorithm for the generation of evolving artificial neural networks. It was developed by Ken Stanley while at The University of Texas at Austin. ----------------------------------------------------------------------------- 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

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
NEATNeuronGene() The default constructor.
NEATNeuronGene(NEATNeuronGene other) Construct this gene by comping another.
NEATNeuronGene(NEATNeuronType type, ActivationFunction theActivationFunction, long id, long innovationID) Construct a neuron gene.

Method Summary

Methods

Modifier and Type	Method and Description
void	copy(NEATNeuronGene gene) Copy another gene to this one.
ActivationFunction	getActivationFunction()
NEATNeuronType	getNeuronType()
void	setActivationFunction(ActivationFunction activationFunction)
void	setNeuronType(NEATNeuronType neuronType) Set the neuron type.
String	toString()

Methods inherited from class org.encog.neural.neat.training.NEATBaseGene

compareTo, getId, getInnovationId, setId, setInnovationId

Methods inherited from class java.lang.Object

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

Constructor Detail

NEATNeuronGene

public NEATNeuronGene()

The default constructor.

NEATNeuronGene

public NEATNeuronGene(NEATNeuronType type,
              ActivationFunction theActivationFunction,
              long id,
              long innovationID)

Construct a neuron gene.

Parameters:

type - The neuron type.

theActivationFunction - The activation function.

id - The neuron id.

innovationID - The innovation id.

NEATNeuronGene

public NEATNeuronGene(NEATNeuronGene other)

Construct this gene by comping another.

Parameters:

other - The other gene to copy.

Method Detail

copy

public void copy(NEATNeuronGene gene)

Copy another gene to this one.

Parameters:

gene - The other gene.

getNeuronType

public NEATNeuronType getNeuronType()

Returns:

The type for this neuron.

setNeuronType

public void setNeuronType(NEATNeuronType neuronType)

Set the neuron type.

Parameters:

neuronType - The neuron type.

getActivationFunction

public ActivationFunction getActivationFunction()

Returns:

the activationFunction

setActivationFunction

public void setActivationFunction(ActivationFunction activationFunction)

Parameters:

activationFunction - the activationFunction to set

toString

public String toString()

Overrides:

toString in class Object