jhpro.nnet.jknnl

Class KohonenNeuron

java.lang.Object

jhpro.nnet.jknnl.KohonenNeuron

All Implemented Interfaces:

NeuronModel

Direct Known Subclasses:

KohonenNeuronWithTired

public class KohonenNeuron
extends java.lang.Object
implements NeuronModel

Class representing neuron with bias and specified activation function

See Also:

ActivationFunctionModel

Constructor Summary

Constructors

Constructor and Description
KohonenNeuron(double[] weightArray, ActivationFunctionModel activationFunction) Creates new neuron with weight specyfied by array and specified activation funciton.
KohonenNeuron(int weightNumber, double[] maxWeight, ActivationFunctionModel activationFunction) Creates new neuron with specified numbers of weight.

Method Summary

Modifier and Type	Method and Description
MetricModel	getDistanceFunction() Return reference to distance function
double	getValue(double[] inputVector) Return value of the neuron after activation.
double[]	getWeight() Return array of neuron weigths
void	setDistanceFunction(MetricModel distanceFunction) Set distance function
void	setWeight(double[] weight) Set weights from array as parameter
java.lang.String	toString() Returns a string representation of the NeuronModel.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

KohonenNeuron

public KohonenNeuron(int weightNumber,
                     double[] maxWeight,
                     ActivationFunctionModel activationFunction)

Creates new neuron with specified numbers of weight. Value of the weight is random where max value is definite by maxWeight. Activation function is defined by activationFunction parameter.

Parameters:

weightNumber - numbers of weight

maxWeight - max value of the weight

activationFunction - activation function

KohonenNeuron

public KohonenNeuron(double[] weightArray,
                     ActivationFunctionModel activationFunction)

Creates new neuron with weight specyfied by array and specified activation funciton. Numbers of weights are the same as length of the array.

Parameters:

weightArray - array of the weight

activationFunction - activation function

Method Detail

getWeight

public double[] getWeight()

Return array of neuron weigths

Specified by:

getWeight in interface NeuronModel

Returns:

array of neuron weigths

getValue

public double getValue(double[] inputVector)

Return value of the neuron after activation. if activation function is not set, function return sum of the multiplication of vector v_i and weight w_i for each i (numbers of weigth and lenght of the input vector)

Specified by:

getValue in interface NeuronModel

Parameters:

inputVector - input vector for neuron

Returns:

return

setWeight

public void setWeight(double[] weight)

Set weights from array as parameter

Specified by:

setWeight in interface NeuronModel

Parameters:

weight - array of the weights

toString

public java.lang.String toString()

Returns a string representation of the NeuronModel. NeuronModel is describe by its weights [w_1,w_2,...]

Overrides:

toString in class java.lang.Object

Returns:

a string representation of the NeuronModel

getDistanceFunction

public MetricModel getDistanceFunction()

Return reference to distance function

Returns:

reference to distance function

setDistanceFunction

public void setDistanceFunction(MetricModel distanceFunction)

Set distance function

Parameters:

distanceFunction - reference to distance function