yawn.nn.appart
Class PredictionNeuralNode

java.lang.Object
  yawn.nn.NeuralNode
      yawn.nn.appart.PredictionNeuralNode

public class PredictionNeuralNode
extends NeuralNode

A prediction layer node. Receives as input the activation of the F2 layer, v. $Id: PredictionNeuralNode.java,v 1.9 2005/04/07 17:28:25 supermarti Exp $

Version:

$Revision: 1.9 $

Author:

Luis Martí (luis dot marti at uc3m dot es)

Field Summary

protected double	e
protected Pattern	weights

Fields inherited from class yawn.nn.NeuralNode

input, inputSize

Method Summary

protected double	activationFunction(Pattern input)
double	getE()
int	getInputSize()
Pattern	getWeights()
void	setE(double e)
void	setWeights(Pattern weights)
void	updateStructure(double newInputFeature, double newWeightFeature)

Methods inherited from class yawn.nn.NeuralNode

output, reset, setInput, setInputElement, setInputSize

Methods inherited from class java.lang.Object

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

Field Detail

e

protected double e

weights

protected Pattern weights

Method Detail

activationFunction

protected double activationFunction(Pattern input)

Specified by:

activationFunction in class NeuralNode

See Also:

NeuralNode.activationFunction(yawn.util.Pattern)

getE

public double getE()

Returns:

the value of `e'

getInputSize

public int getInputSize()

Overrides:

getInputSize in class NeuralNode

See Also:

NeuralNode.getInputSize()

getWeights

public Pattern getWeights()

Returns:

the value

setE

public void setE(double e)

Parameters:

e -

setWeights

public void setWeights(Pattern weights)

Parameters:

weights - the weigths to set

updateStructure

public void updateStructure(double newInputFeature,
                            double newWeightFeature)

Parameters:

newInputFeature -

newWeightFeature -