org.ai_heuristic.algo.cluster.som.network

Class DefaultNeuron

java.lang.Object

org.ai_heuristic.algo.cluster.som.network.DefaultNeuron

All Implemented Interfaces:

NeuronModel

Direct Known Subclasses:

DefaultNeuronWithBias, KohonenNeuron

public class DefaultNeuron
extends java.lang.Object
implements NeuronModel

Updated version of the source code for the kohonen self-organising map at http://jknnl.sourceforge.net/ Note that the neuron value is simply the input vector times the weight values, there is no distance function, but there can be an activation function. Some classes or packages may have been moved or changed. See above for the copyright notices.

Author:

Kieran Greer.

Field Summary

Fields

Modifier and Type	Field and Description
protected FunctionActivate	activationFunction Activation function
protected FunctionLearn	learnFunction Learning function
protected double[]	weight Array of the weight

Constructor Summary

Constructors

Constructor and Description
DefaultNeuron(double[] weightArray, FunctionActivate activationFunction) Creates a new instance of DefaultNeuronWithBias with specified weights defined in array
DefaultNeuron(int weightNumber, double[] maxWeight, FunctionActivate activationFunction) Creates a new instance of DefaultNeuronWithBias with random weights value

Method Summary

Modifier and Type	Method and Description
void	changeNeuronWeight(double[] vector, double factor) Change neuron weights for specified neuron number,iteration and input data vector
void	changeNeuronWeight(double[] vector, double factor, double influence) Change neuron weights for specified neuron number,iteration and input data vector
FunctionActivate	getActivationFunction() Return reference to activation function
double	getValue(double[] inputVector) Return value of the neuron after activation.
double[]	getWeight() Returns array contains value of the weights
void	setActivationFunction(FunctionActivate activationFunction) Set activation function
void	setWeight(double[] weight) Set weights from array as parameter
protected double	valueTimesWeights(double[] inputVector) Return value of the neuron after activation.

Methods inherited from class java.lang.Object

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

Field Detail

weight

protected double[] weight

Array of the weight

learnFunction

protected FunctionLearn learnFunction

Learning function

activationFunction

protected FunctionActivate activationFunction

Activation function

Constructor Detail

DefaultNeuron

public DefaultNeuron(int weightNumber,
                     double[] maxWeight,
                     FunctionActivate activationFunction)

Creates a new instance of DefaultNeuronWithBias with random weights value

Parameters:

weightNumber - numbers of weigths

maxWeight - max value of the weight. If null or different number of entries to weightNumber, then start with random value between 0 and 1.

activationFunction - reference to activation function

DefaultNeuron

public DefaultNeuron(double[] weightArray,
                     FunctionActivate activationFunction)

Creates a new instance of DefaultNeuronWithBias with specified weights defined in array

Parameters:

weightArray - array of weights value

activationFunction - reference to activation function

Method Detail

getWeight

public double[] getWeight()

Returns array contains value of the weights

Specified by:

getWeight in interface NeuronModel

Returns:

array of the weights

setWeight

public void setWeight(double[] weight)

Set weights from array as parameter

Specified by:

setWeight in interface NeuronModel

Parameters:

weight - array of the weights

getValue

public double getValue(double[] inputVector)
                throws java.lang.Exception

Return value of the neuron after activation.

Specified by:

getValue in interface NeuronModel

Parameters:

inputVector - input vector for neuron

Returns:

return

Throws:

java.lang.Exception - any error.

valueTimesWeights

protected double valueTimesWeights(double[] inputVector)
                            throws java.lang.Exception

Return value of the neuron after activation.

Parameters:

inputVector - input vector for neuron

Returns:

return

Throws:

java.lang.Exception - any error

changeNeuronWeight

public void changeNeuronWeight(double[] vector,
                               double factor)
                        throws java.lang.Exception

Change neuron weights for specified neuron number,iteration and input data vector

Specified by:

changeNeuronWeight in interface NeuronModel

Parameters:

vector - input data vector.

factor - the iteration number or factor.

Throws:

java.lang.Exception - any error.

changeNeuronWeight

public void changeNeuronWeight(double[] vector,
                               double factor,
                               double influence)
                        throws java.lang.Exception

Change neuron weights for specified neuron number,iteration and input data vector

Specified by:

changeNeuronWeight in interface NeuronModel

Parameters:

vector - input data vector.

factor - the iteration number or factor.

influence - cells in neighbourhood have a reduced influence.

Throws:

java.lang.Exception - any error.

getActivationFunction

public FunctionActivate getActivationFunction()

Return reference to activation function

Returns:

reference to activation function

setActivationFunction

public void setActivationFunction(FunctionActivate activationFunction)

Set activation function

Parameters:

activationFunction - reference to activation function