org.encog.mathutil.randomize
Class NguyenWidrowRandomizer

java.lang.Object
  extended by org.encog.mathutil.randomize.BasicRandomizer
      extended by org.encog.mathutil.randomize.NguyenWidrowRandomizer
All Implemented Interfaces:
Randomizer

public class NguyenWidrowRandomizer
extends BasicRandomizer

Implementation of Nguyen-Widrow weight initialization. This is the default weight initialization used by Encog, as it generally provides the most train-able neural network.


Field Summary
static String MSG
           
 
Constructor Summary
NguyenWidrowRandomizer()
           
 
Method Summary
 double randomize(double d)
          Starting with the specified number, randomize it to the degree specified by this randomizer.
 void randomize(double[] d)
          Randomize the array based on an array, modify the array.
 void randomize(double[][] d)
          Randomize the 2d array based on an array, modify the array.
 void randomize(double[] d, int begin, int size)
          Randomize the array based on an array, modify the array.
 void randomize(Matrix m)
          Randomize the matrix based on an array, modify the array.
 void randomize(MLMethod method)
          Randomize the synapses and biases in the basic network based on an array, modify the array.
 
Methods inherited from class org.encog.mathutil.randomize.BasicRandomizer
getRandom, nextDouble, nextDouble, randomize, setRandom, setSeed
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

MSG

public static String MSG
Constructor Detail

NguyenWidrowRandomizer

public NguyenWidrowRandomizer()
Method Detail

randomize

public void randomize(MLMethod method)
Description copied from class: BasicRandomizer
Randomize the synapses and biases in the basic network based on an array, modify the array. Previous values may be used, or they may be discarded, depending on the randomizer.

Specified by:
randomize in interface Randomizer
Overrides:
randomize in class BasicRandomizer
Parameters:
method - A network to randomize.

randomize

public double randomize(double d)
Description copied from interface: Randomizer
Starting with the specified number, randomize it to the degree specified by this randomizer. This could be a totally new random number, or it could be based on the specified number.

Parameters:
d - The number to randomize.
Returns:
A randomized number.

randomize

public void randomize(double[] d)
Description copied from class: BasicRandomizer
Randomize the array based on an array, modify the array. Previous values may be used, or they may be discarded, depending on the randomizer.

Specified by:
randomize in interface Randomizer
Overrides:
randomize in class BasicRandomizer
Parameters:
d - An array to randomize.

randomize

public void randomize(double[][] d)
Description copied from class: BasicRandomizer
Randomize the 2d array based on an array, modify the array. Previous values may be used, or they may be discarded, depending on the randomizer.

Specified by:
randomize in interface Randomizer
Overrides:
randomize in class BasicRandomizer
Parameters:
d - An array to randomize.

randomize

public void randomize(Matrix m)
Description copied from class: BasicRandomizer
Randomize the matrix based on an array, modify the array. Previous values may be used, or they may be discarded, depending on the randomizer.

Specified by:
randomize in interface Randomizer
Overrides:
randomize in class BasicRandomizer
Parameters:
m - A matrix to randomize.

randomize

public void randomize(double[] d,
                      int begin,
                      int size)
Description copied from class: BasicRandomizer
Randomize the array based on an array, modify the array. Previous values may be used, or they may be discarded, depending on the randomizer.

Specified by:
randomize in interface Randomizer
Overrides:
randomize in class BasicRandomizer
Parameters:
d - An array to randomize.
begin - The beginning element of the array.
size - The size of the array to copy.


Copyright © 2014. All Rights Reserved.