org.joone.engine
Class RpropParameters

java.lang.Object
  extended by org.joone.engine.RpropParameters

public class RpropParameters
extends java.lang.Object

This object holds the global parameters for the RPROP learning algorithm (RpropLearner).

Author:
Boris Jansen

Constructor Summary
RpropParameters()
          Creates a new instance of RpropParameters
 
Method Summary
 int getBatchSize()
          Gets the batchsize.
 double getEtaDec()
          Gets the decremental learning factor/rate.
 double getEtaInc()
          Gets the incremental learning factor/rate.
 double getInitialDelta(int i, int j)
          Gets the initial delta value.
 double getMaxDelta()
          Gets the maximum allowed delta value.
 double getMinDelta()
          Gets the minimum allowed delta value.
 void setBatchSize(int aBatchsize)
          Sets the batchsize.
 void setEtaDec(double anEtaDec)
          Sets the decremental learning factor/rate.
 void setEtaInc(double anEtaInc)
          Sets the incremental learning factor/rate.
 void setInitialDelta(double anInitialDelta)
          Sets the initial delta for all delta's.
 void setMaxDelta(double aMaxDelta)
          Sets the maximum allowed delta value.
 void setMinDelta(double aMinDelta)
          Sets the minimum allowed delta value.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

RpropParameters

public RpropParameters()
Creates a new instance of RpropParameters

Method Detail

getInitialDelta

public double getInitialDelta(int i,
                              int j)
Gets the initial delta value.

Parameters:
i - the index (i, j) of the weight/bias for which it should get the initial value. The RPROP learning algorithm gives every bias/weight the same initial value, but by passing the index of the weight/bias to this method, a user is able to give different initial values to different weights/biases based on their index by extending this class.
j -

setInitialDelta

public void setInitialDelta(double anInitialDelta)
Sets the initial delta for all delta's.

Parameters:
anInitialDelta - the initial delta value.

getMaxDelta

public double getMaxDelta()
Gets the maximum allowed delta value.

Returns:
the maximum allowed delta value.

setMaxDelta

public void setMaxDelta(double aMaxDelta)
Sets the maximum allowed delta value.

Parameters:
aMaxDelta - the maximum allowed delta value.

getMinDelta

public double getMinDelta()
Gets the minimum allowed delta value.

Returns:
the minimum allowed delta value.

setMinDelta

public void setMinDelta(double aMinDelta)
Sets the minimum allowed delta value.

Parameters:
aMinDelta - the minimum allowed delta value.

getEtaInc

public double getEtaInc()
Gets the incremental learning factor/rate.

Returns:
the incremental learning factor/rate.

setEtaInc

public void setEtaInc(double anEtaInc)
Sets the incremental learning factor/rate.

Parameters:
anEtaInc - the incremental learning factor/rate.

getEtaDec

public double getEtaDec()
Gets the decremental learning factor/rate.

Returns:
the decremental learning factor/rate.

setEtaDec

public void setEtaDec(double anEtaDec)
Sets the decremental learning factor/rate.

Parameters:
anEtaDec - the decremental learning factor/rate.

getBatchSize

public int getBatchSize()
Gets the batchsize.

Returns:
the batch size.

setBatchSize

public void setBatchSize(int aBatchsize)
Sets the batchsize. param aBatchsize the new batchsize.



Submit Feedback to pmarrone@users.sourceforge.net