Package | Description |
---|---|
org.encog.mathutil.randomize | |
org.encog.neural.networks.training.pso |
Modifier and Type | Class and Description |
---|---|
class |
BasicRandomizer
Provides basic functionality that most randomizers will need.
|
class |
ConsistentRandomizer
A randomizer that takes a seed and will always produce consistent results.
|
class |
ConstRandomizer
A randomizer that will create always set the random number to a const value,
used mainly for testing.
|
class |
Distort
A randomizer that distorts what is already present in the neural network.
|
class |
FanInRandomizer
A randomizer that attempts to create starting weight values that are
conducive to propagation training.
|
class |
GaussianRandomizer
Generally, you will not want to use this randomizer as a pure neural network
randomizer.
|
class |
NguyenWidrowRandomizer
Implementation of Nguyen-Widrow weight initialization.
|
class |
RangeRandomizer
A randomizer that will create random weight and bias values that are between
a specified range.
|
Modifier and Type | Field and Description |
---|---|
protected Randomizer |
NeuralPSO.m_randomizer |
Constructor and Description |
---|
NeuralPSO(BasicNetwork network,
Randomizer randomizer,
CalculateScore calculateScore,
int populationSize)
Constructor.
|
Copyright © 2014. All Rights Reserved.