org.encog.neural.networks.training.neat
Class NEATInnovation

java.lang.Object
  org.encog.solve.genetic.innovation.BasicInnovation
      org.encog.neural.networks.training.neat.NEATInnovation

All Implemented Interfaces:

Innovation

public class NEATInnovation
extends BasicInnovation

Implements a NEAT innovation. This lets NEAT track what changes it has previously tried with a neural network. 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/

Constructor Summary

NEATInnovation()
Default constructor, used mainly for persistence.

NEATInnovation(long fromNeuronID, long toNeuronID, NEATInnovationType innovationType, long innovationID)
Construct an innovation.

NEATInnovation(long fromNeuronID, long toNeuronID, NEATInnovationType innovationType, long innovationID, NEATNeuronType neuronType, double x, double y)
Construct an innovation.

NEATInnovation(NEATNeuronGene neuronGene, long innovationID, long neuronID)
Construct an innovation.

Method Summary

long	getFromNeuronID()
NEATInnovationType	getInnovationType()
long	getNeuronID()
NEATNeuronType	getNeuronType()
double	getSplitX()
double	getSplitY()
long	getToNeuronID()
void	setNeuronID(long neuronID) Set the neuron id.
String	toString()

Methods inherited from class org.encog.solve.genetic.innovation.BasicInnovation

getInnovationID, setInnovationID

Methods inherited from class java.lang.Object

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

Constructor Detail

NEATInnovation

public NEATInnovation()

Default constructor, used mainly for persistence.

NEATInnovation

public NEATInnovation(long fromNeuronID,
                      long toNeuronID,
                      NEATInnovationType innovationType,
                      long innovationID)

Construct an innovation.

Parameters:

fromNeuronID - The from neuron.

toNeuronID - The two neuron.

innovationType - The innovation type.

innovationID - The innovation id.

NEATInnovation

public NEATInnovation(long fromNeuronID,
                      long toNeuronID,
                      NEATInnovationType innovationType,
                      long innovationID,
                      NEATNeuronType neuronType,
                      double x,
                      double y)

Construct an innovation.

Parameters:

fromNeuronID - The from neuron.

toNeuronID - The to neuron.

innovationType - The innovation type.

innovationID - The innovation id.

neuronType - The neuron type.

x - The x coordinate.

y - THe y coordinate.

NEATInnovation

public NEATInnovation(NEATNeuronGene neuronGene,
                      long innovationID,
                      long neuronID)

Construct an innovation.

Parameters:

neuronGene - The neuron gene.

innovationID - The innovation id.

neuronID - The neuron id.

Method Detail

getFromNeuronID

public long getFromNeuronID()

Returns:

The from neuron id.

getInnovationType

public NEATInnovationType getInnovationType()

Returns:

The innovation type.

getNeuronID

public long getNeuronID()

Returns:

The neuron ID.

getNeuronType

public NEATNeuronType getNeuronType()

Returns:

The neuron type.

getSplitX

public double getSplitX()

Returns:

The split x.

getSplitY

public double getSplitY()

Returns:

The split y.

getToNeuronID

public long getToNeuronID()

Returns:

The to neuron id.

setNeuronID

public void setNeuronID(long neuronID)

Set the neuron id.

Parameters:

neuronID - The neuron id.

toString

public String toString()

Overrides:

toString in class Object