Uses of Class
org.neuroph.util.random.WeightsRandomizer

Packages that use WeightsRandomizer

Package	Description
org.neuroph.core	Provides base classes and basic building components for neural networks.
org.neuroph.util.random	Provides weights randomization techniques

Uses of WeightsRandomizer in org.neuroph.core

Methods in org.neuroph.core with parameters of type WeightsRandomizer

Modifier and Type	Method and Description
void	NeuralNetwork.randomizeWeights(WeightsRandomizer randomizer) Randomizes connection weights for the whole network using specified randomizer

Uses of WeightsRandomizer in org.neuroph.util.random

Subclasses of WeightsRandomizer in org.neuroph.util.random

Modifier and Type	Class and Description
class	DistortRandomizer This class provides distort randomization technique, which distorts existing weight values using specified distortion factor.
class	GaussianRandomizer This class provides Gaussian randomization technique using Box Muller method.
class	HeZhangRenSunUniformWeightsRandomizer Sources: https://arxiv.org/abs/1502.01852 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification https://stats.stackexchange.com/questions/47590/what-are-good-initial-weights-in-a-neural-network https://github.com/keras-team/keras/blob/master/keras/initializers.py
class	NguyenWidrowRandomizer This class provides NguyenWidrow randmization technique, which gives very good results for Multi Layer Perceptrons trained with back propagation family of learning rules.
class	RangeRandomizer This class provides ranged weights randomizer, which randomize weights in specified [min, max] range.