jhpro.nnet

Class WeightMatrix

java.lang.Object

jhpro.nnet.WeightMatrix

All Implemented Interfaces:

java.io.Serializable

public class WeightMatrix
extends java.lang.Object
implements java.io.Serializable

The connection structure between two neuron layers of a neural net. Its elements, the weights, are changed during the net's learning process. Each neural net has at least one weight matrix.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
WeightMatrix(int i, int j, boolean flag)

Method Summary

Modifier and Type	Method and Description
void	changeWeights(float[] af, float[] af1, double d)
void	changeWeightsKFM(float[] af, float[] af1, double d)
float[]	getBiases()
float[]	getInputWeights(int i)
float[]	getOutputWeights(int i)
float[][]	getWeights()
void	init()
void	init(float[][] af)
void	init(InputValue[] ainputvalue, int i)
int	size()

Methods inherited from class java.lang.Object

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

Constructor Detail

WeightMatrix

public WeightMatrix(int i,
                    int j,
                    boolean flag)

Method Detail

init

public void init()

init

public void init(float[][] af)

init

public void init(InputValue[] ainputvalue,
                 int i)

changeWeights

public void changeWeights(float[] af,
                          float[] af1,
                          double d)

changeWeightsKFM

public void changeWeightsKFM(float[] af,
                             float[] af1,
                             double d)

getInputWeights

public float[] getInputWeights(int i)

getOutputWeights

public float[] getOutputWeights(int i)

size

public int size()

getWeights

public float[][] getWeights()

getBiases

public float[] getBiases()