Package org.ojalgo.ann
Class TrainingConfiguration
java.lang.Object
org.ojalgo.ann.TrainingConfiguration
-
Field Summary
FieldsModifier and TypeFieldDescription(package private) boolean
(package private) ArtificialNeuralNetwork.Error
(package private) double
(package private) boolean
(package private) double
(package private) boolean
(package private) double
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionprivate double
doL1
(double current) private double
doL2
(double current) boolean
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) DoubleUnaryOperator
-
Field Details
-
dropouts
boolean dropouts -
error
-
learningRate
double learningRate -
regularisationL1
boolean regularisationL1 -
regularisationL1Factor
double regularisationL1Factor -
regularisationL2
boolean regularisationL2 -
regularisationL2Factor
double regularisationL2Factor
-
-
Constructor Details
-
TrainingConfiguration
TrainingConfiguration()
-
-
Method Details
-
equals
-
hashCode
public int hashCode() -
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
DoubleUnaryOperator regularisation()
-