Module ojalgo

Package org.ojalgo.ann

Class TrainingConfiguration

java.lang.Object

org.ojalgo.ann.TrainingConfiguration

final class TrainingConfiguration
extends java.lang.Object

Field Summary

Fields

Modifier and Type	Field	Description
(package private) boolean	dropouts
(package private) ArtificialNeuralNetwork.Error	error
(package private) double	learningRate
(package private) boolean	regularisationL1
(package private) double	regularisationL1Factor
(package private) boolean	regularisationL2
(package private) double	regularisationL2Factor

Constructor Summary

Constructors

Constructor	Description
TrainingConfiguration()

Method Summary

Modifier and Type	Method	Description
private double	doL1(double current)
private double	doL2(double current)
boolean	equals(java.lang.Object obj)
int	hashCode()
(package private) double	probabilityDidKeepInput(int layer)	Used to scale the weights after training with dropouts, and also to adjut the learning rate
(package private) double	probabilityWillKeepOutput(int layer, int depth)	Used to modify the activation function – with this probabilty it will be used as is, for the other parts the output is 0.
(package private) java.util.function.DoubleUnaryOperator	regularisation()

Methods inherited from class java.lang.Object

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

Field Detail

dropouts

boolean dropouts

error

ArtificialNeuralNetwork.Error error

learningRate

double learningRate

regularisationL1

boolean regularisationL1

regularisationL1Factor

double regularisationL1Factor

regularisationL2

boolean regularisationL2

regularisationL2Factor

double regularisationL2Factor

Constructor Detail

TrainingConfiguration

TrainingConfiguration()

Method Detail

equals

public boolean equals(java.lang.Object obj)

Overrides:

equals in class java.lang.Object

hashCode

public int hashCode()

Overrides:

hashCode in class java.lang.Object

doL1

private double doL1(double current)

doL2

private double doL2(double current)

probabilityDidKeepInput

double probabilityDidKeepInput(int layer)

Used to scale the weights after training with dropouts, and also to adjut the learning rate

Parameters:

layer -

Returns:

The probabilityToKeep (as in not drop) the input nodes of this layer

probabilityWillKeepOutput

double probabilityWillKeepOutput(int layer,
                                 int depth)

Used to modify the activation function – with this probabilty it will be used as is, for the other parts the output is 0.

Parameters:

layer -

depth -

Returns:

regularisation

java.util.function.DoubleUnaryOperator regularisation()