public abstract class GDBRegressionTrainer extends GDBTrainer
GDBTrainer.GDBModel
DatasetTrainer.EmptyDatasetException
checkConvergenceStgyFactory, loss
envBuilder, environment
Constructor and Description |
---|
GDBRegressionTrainer(double gradStepSize,
Integer cntOfIterations)
Constructs instance of GDBRegressionTrainer.
|
Modifier and Type | Method and Description |
---|---|
protected double |
externalLabelToInternal(double x)
Maps external representation of label to internal.
|
protected double |
internalLabelToExternal(double x)
Maps internal representation of label to external.
|
protected <V,K> boolean |
learnLabels(DatasetBuilder<K,V> builder,
Preprocessor<K,V> preprocessor)
Defines unique labels in dataset if need (useful in case of classification).
|
GDBRegressionTrainer |
withEnvironmentBuilder(LearningEnvironmentBuilder envBuilder)
Changes learning Environment.
|
buildBaseModelTrainer, computeInitialValue, fitWithInitializedDeployingContext, getLearningStrategy, isUpdateable, updateModel, withCheckConvergenceStgyFactory
fit, fit, fit, fit, fit, fit, getLastTrainedModelOrThrowEmptyDatasetException, identityTrainer, learningEnvironment, update, update, update, update, update, withConvertedLabels
public GDBRegressionTrainer(double gradStepSize, Integer cntOfIterations)
gradStepSize
- Grad step size.cntOfIterations
- Count of learning iterations.protected <V,K> boolean learnLabels(DatasetBuilder<K,V> builder, Preprocessor<K,V> preprocessor)
learnLabels
in class GDBTrainer
builder
- Dataset builder.preprocessor
- Upstream preprocessor.protected double externalLabelToInternal(double x)
externalLabelToInternal
in class GDBTrainer
x
- Label value.protected double internalLabelToExternal(double x)
internalLabelToExternal
in class GDBTrainer
x
- Label value.public GDBRegressionTrainer withEnvironmentBuilder(LearningEnvironmentBuilder envBuilder)
withEnvironmentBuilder
in class GDBTrainer
envBuilder
- Learning environment builder.
GridGain In-Memory Computing Platform : ver. 8.9.14 Release Date : November 5 2024