org.neuroph.util.random

Class NguyenWidrowRandomizer

java.lang.Object

org.neuroph.util.random.WeightsRandomizer

org.neuroph.util.random.RangeRandomizer

org.neuroph.util.random.NguyenWidrowRandomizer

public class NguyenWidrowRandomizer
extends RangeRandomizer

This class provides NguyenWidrow randmization technique, which gives very good results for Multi Layer Perceptrons trained with back propagation family of learning rules. Based on NguyenWidrowRandomizer from Encog

Author:

Zoran Sevarac

Field Summary

Fields inherited from class org.neuroph.util.random.RangeRandomizer

max, min

Fields inherited from class org.neuroph.util.random.WeightsRandomizer

randomGen

Constructor Summary

Constructors

Constructor and Description
NguyenWidrowRandomizer(double min, double max)

Method Summary

Modifier and Type	Method and Description
void	randomize(NeuralNetwork neuralNetwork) Iterates and randomizes all layers in specified network

Methods inherited from class org.neuroph.util.random.RangeRandomizer

nextRandomWeight

Methods inherited from class org.neuroph.util.random.WeightsRandomizer

getRandomGen, randomize, randomize

Methods inherited from class java.lang.Object

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

Constructor Detail

NguyenWidrowRandomizer

public NguyenWidrowRandomizer(double min,
                              double max)

Method Detail

randomize

public void randomize(NeuralNetwork neuralNetwork)

Description copied from class: WeightsRandomizer

Iterates and randomizes all layers in specified network

Overrides:

randomize in class WeightsRandomizer

Parameters:

neuralNetwork - neural network to randomize