@PublicationReference(author={"Koby Crammer","Mark Dredze","Fernando Pereira"}, title="Exact Convex Confidence-Weighted Learning", year=2008, type=Conference, publication="Advances in Neural Information Processing Systems", url="http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.169.3364") public class ConfidenceWeightedDiagonalDeviationProject extends ConfidenceWeightedDiagonalDeviation
confidence, DEFAULT_CONFIDENCE, DEFAULT_DEFAULT_VARIANCE, defaultVariance, epsilon, phi, psi
Constructor and Description |
---|
ConfidenceWeightedDiagonalDeviationProject()
Creates a new
ConfidenceWeightedDiagonalDeviationProject with
default parameters. |
ConfidenceWeightedDiagonalDeviationProject(double confidence,
double defaultVariance)
Creates a new
ConfidenceWeightedDiagonalDeviationProject with the given
parameters. |
Modifier and Type | Method and Description |
---|---|
void |
update(DiagonalConfidenceWeightedBinaryCategorizer target,
Vector input,
boolean label)
Updates the target using the given input and associated label.
|
createInitialLearnedObject, getConfidence, getDefaultVariance, setConfidence, setDefaultVariance, update
update
clone, learn, learn, update
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
learn
learn
update
clone
public ConfidenceWeightedDiagonalDeviationProject()
ConfidenceWeightedDiagonalDeviationProject
with
default parameters.public ConfidenceWeightedDiagonalDeviationProject(double confidence, double defaultVariance)
ConfidenceWeightedDiagonalDeviationProject
with the given
parameters.confidence
- The confidence to use. Must be in [0, 1].defaultVariance
- The default value to initialize the covariance matrix to.public void update(DiagonalConfidenceWeightedBinaryCategorizer target, Vector input, boolean label)
ConfidenceWeightedDiagonalDeviation
update
in class ConfidenceWeightedDiagonalDeviation
target
- The target to update.input
- The supervised input value.label
- The output label associated with the input.