keel.Algorithms.Neural_Networks.NNEP_Common

Class NeuralNetIndividualSpecies

java.lang.Object

keel.Algorithms.Neural_Networks.NNEP_Common.AbstractNeuralNetSpecies<NeuralNetIndividual>

keel.Algorithms.Neural_Networks.NNEP_Common.NeuralNetIndividualSpecies

All Implemented Interfaces:

INeuralNetSpecies<NeuralNetIndividual>

public class NeuralNetIndividualSpecies
extends AbstractNeuralNetSpecies<NeuralNetIndividual>

Individuals that use a INeuralNet as genotype

Since:

JDK1.5

Version:

0.1

Author:

Written by Pedro Antonio Gutierrez Penia (University of Cordoba) 16/7/2007, Written by Aaron Ruiz Mora (University of Cordoba) 16/7/2007

Field Summary

Fields inherited from class keel.Algorithms.Neural_Networks.NNEP_Common.AbstractNeuralNetSpecies

biased, initialMaxNofneurons, initiator, initiatorNeuronTypes, maxNofneurons, minNofneurons, neuralNetType, neuronTypes, nOfHiddenLayers, nOfInputs, nOfOutputs, percentages, type, weightRanges

Constructor Summary

Constructors

Constructor and Description
NeuralNetIndividualSpecies() Empty constructor

Method Summary

Modifier and Type	Method and Description
void	configure(Configuration configuration) Configuration parameters for this species are: input-layer.number-of-inputs (int) Number of inputs.
INeuralNet	createGenotype() Creates the genotype of the individual
NeuralNetIndividual	createIndividual() Creates a new individual
NeuralNetIndividual	createIndividual(INeuralNet genotype) Creates a new individual
boolean	equals(java.lang.Object other) Compare two individuals
void	setHiddenLayerBiased(int index, boolean hiddenLayerBiased) Sets a boolean indicating if a hidden layer is biased
void	setHiddenLayerInitialNofneurons(int index, int hiddenLayerInitialMaxNofneurons) Sets initial maximum number of neurons of a hidden layer
void	setHiddenLayerInitiator(int index, java.lang.String hiddenLayerInitiator) Sets initiator of neurons of a hidden layer
void	setHiddenLayerMaxNofneurons(int index, int hiddenLayerMaxNofneurons) Sets maximum number of neurons of a hidden layer
void	setHiddenLayerMinNofneurons(int index, int hiddenLayerMinNofneurons) Sets minimum number of neurons of a hidden layer
void	setHiddenLayerType(int index, java.lang.String hiddenLayerType) Sets type of neurons of a hidden layer
void	setHiddenLayerWeightRange(int index, int indexRange, Interval hiddenLayerWeightRange) Sets weight range of a hidden layer
void	setInitiatorNeuronTypes(int index, java.lang.String[] initiatorNeuronTypes) Sets an array of initiators of neurons of hibrid layers
void	setNeuronTypes(int index, java.lang.String[] neuronTypes) Sets an array of neuron types of a concrete layer (this is an hibrid layer)
void	setNOfHiddenLayers(int nOfHiddenLayers) Sets number of hidden layers of the neural nets
void	setNOfInputs(int nOfInputs) Sets number of inputs of the neural nets
void	setNOfOutputs(int nOfOutputs) Sets number of outputs of the neural nets
void	setOutputLayerBiased(boolean outputLayerBiased) Sets a boolean indicating if the output layer is biased
void	setOutputLayerInitiator(java.lang.String outputLayerInitiator) Sets initiator of neurons of the output layer
void	setOutputLayerType(java.lang.String outputLayerType) Sets type of neurons of the output layer
void	setOutputLayerWeightRange(int indexRange, Interval outputLayerWeightRange) Sets weight range of the output layer
void	setPercentages(int index, double[] percentages) Sets an array of percentages of a concrete layer (this is an hibrid layer)

Methods inherited from class keel.Algorithms.Neural_Networks.NNEP_Common.AbstractNeuralNetSpecies

getHiddenLayerInitialMaxNofneurons, getHiddenLayerInitiator, getHiddenLayerMaxNofneurons, getHiddenLayerMinNofneurons, getHiddenLayerType, getHiddenLayerWeightRange, getInitiatorNeuronTypes, getNeuralNetType, getNeuronTypes, getNOfHiddenLayers, getNOfInputs, getNOfOutputs, getOutputLayerInitiator, getOutputLayerType, getOutputLayerWeightRange, getPercentages, isHiddenLayerBiased, isOutputLayerBiased

Methods inherited from class java.lang.Object

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

Constructor Detail

NeuralNetIndividualSpecies

public NeuralNetIndividualSpecies()

Empty constructor

Method Detail

setNOfHiddenLayers

public void setNOfHiddenLayers(int nOfHiddenLayers)

Sets number of hidden layers of the neural nets

Parameters:

nOfHiddenLayers - Number of hidden layers

setNOfInputs

public void setNOfInputs(int nOfInputs)

Sets number of inputs of the neural nets

Parameters:

nOfInputs - Number of hidden layers

setNOfOutputs

public void setNOfOutputs(int nOfOutputs)

Sets number of outputs of the neural nets

Parameters:

nOfOutputs - Number of hidden layers

setHiddenLayerWeightRange

public void setHiddenLayerWeightRange(int index,
                                      int indexRange,
                                      Interval hiddenLayerWeightRange)

Sets weight range of a hidden layer

Parameters:

index - Index of the desired hidden layer

indexRange - Index of the desired range into the layer (useful for hibrid layer)

hiddenLayerWeightRange - New weight range

setOutputLayerWeightRange

public void setOutputLayerWeightRange(int indexRange,
                                      Interval outputLayerWeightRange)

Sets weight range of the output layer

Parameters:

indexRange - Index of the desired range into the layer (useful for hibrid layer)

outputLayerWeightRange - New weight range

setHiddenLayerMaxNofneurons

public void setHiddenLayerMaxNofneurons(int index,
                                        int hiddenLayerMaxNofneurons)

Sets maximum number of neurons of a hidden layer

Parameters:

index - Index of the desired hidden layer

hiddenLayerMaxNofneurons - Maximum number of neurons

setHiddenLayerMinNofneurons

public void setHiddenLayerMinNofneurons(int index,
                                        int hiddenLayerMinNofneurons)

Sets minimum number of neurons of a hidden layer

Parameters:

index - Index of the desired hidden layer

hiddenLayerMinNofneurons - Minimum number of neurons

setHiddenLayerInitialNofneurons

public void setHiddenLayerInitialNofneurons(int index,
                                            int hiddenLayerInitialMaxNofneurons)

Sets initial maximum number of neurons of a hidden layer

Parameters:

index - Index of the desired hidden layer

hiddenLayerInitialMaxNofneurons - Initial maximum number of neurons

setHiddenLayerType

public void setHiddenLayerType(int index,
                               java.lang.String hiddenLayerType)

Sets type of neurons of a hidden layer

Parameters:

index - Index of the desired hidden layer

hiddenLayerType - Type of neurons

setOutputLayerType

public void setOutputLayerType(java.lang.String outputLayerType)

Sets type of neurons of the output layer

Parameters:

outputLayerType - Type of neurons

setHiddenLayerInitiator

public void setHiddenLayerInitiator(int index,
                                    java.lang.String hiddenLayerInitiator)

Sets initiator of neurons of a hidden layer

Parameters:

index - Index of the desired hidden layer

hiddenLayerInitiator - Initiator of neurons

setOutputLayerInitiator

public void setOutputLayerInitiator(java.lang.String outputLayerInitiator)

Sets initiator of neurons of the output layer

Parameters:

outputLayerInitiator - Initiator of neurons

setHiddenLayerBiased

public void setHiddenLayerBiased(int index,
                                 boolean hiddenLayerBiased)

Sets a boolean indicating if a hidden layer is biased

Parameters:

index - Index of the desired hidden layer

hiddenLayerBiased - Is hidden layer biased?

setOutputLayerBiased

public void setOutputLayerBiased(boolean outputLayerBiased)

Sets a boolean indicating if the output layer is biased

Parameters:

outputLayerBiased - Is output layer biased?

setNeuronTypes

public void setNeuronTypes(int index,
                           java.lang.String[] neuronTypes)

Sets an array of neuron types of a concrete layer (this is an hibrid layer)

Parameters:

index - Index of the desired hidden layer

neuronTypes - Array of neurons types

setPercentages

public void setPercentages(int index,
                           double[] percentages)

Sets an array of percentages of a concrete layer (this is an hibrid layer)

Parameters:

index - Index of the desired hidden layer

percentages - Array of percentages

setInitiatorNeuronTypes

public void setInitiatorNeuronTypes(int index,
                                    java.lang.String[] initiatorNeuronTypes)

Sets an array of initiators of neurons of hibrid layers

Parameters:

index - Index of the desired hidden layer

initiatorNeuronTypes - Array of initiators of neurons

createIndividual

public NeuralNetIndividual createIndividual()

Creates a new individual

Returns:

A NeuraNetIndividual

createIndividual

public NeuralNetIndividual createIndividual(INeuralNet genotype)

Creates a new individual

Parameters:

genotype - Genotype of the individual

Returns:

A NeuraNetIndividual

createGenotype

public INeuralNet createGenotype()

Creates the genotype of the individual

Returns:

The Genotype <(p>

equals

public boolean equals(java.lang.Object other)

Compare two individuals

Overrides:

equals in class java.lang.Object

Parameters:

other - other individual to compare with.

Returns:

True if the two individuals are equals

configure

public void configure(Configuration configuration)

Configuration parameters for this species are: input-layer.number-of-inputs (int) Number of inputs. Number of inputs of this species neural nets. output-layer.number-of-outputs (int) Number of inputs. Number of outputs of this species neural nets. hidden-layer(i).weight-range (complex) Weigth range of the hidden layer number "i". output-layer.weight-range (complex) Weigth range of the outputlayer. hidden-layer(i).maximum-number-of-neurons (int) Maximum number of neurons of hidden layer number "i". hidden-layer(i).initial-number-of-neurons (int) Initial number of neurons of hidden layer number "i". hidden-layer(i)[@type] (string) Layer type of the hidden layer number "i". output-layer[@type] (string) Layer type of the output layer. hidden-layer(i)[@biased] (string) Boolean indicating if hidden layer number "i" is biased. output-layer[@type] (string) Boolean indicating if the output layer is biased.

Parameters:

configuration - Configuration if the Individual