Uses of Class
gov.sandia.cognition.learning.function.categorization.DefaultKernelBinaryCategorizer

Packages that use DefaultKernelBinaryCategorizer

Package	Description
gov.sandia.cognition.learning.algorithm.perceptron	Provides the Perceptron algorithm and some of its variations.
gov.sandia.cognition.learning.algorithm.perceptron.kernel
gov.sandia.cognition.learning.function.kernel	Provides kernel functions.

Uses of DefaultKernelBinaryCategorizer in gov.sandia.cognition.learning.algorithm.perceptron

Methods in gov.sandia.cognition.learning.algorithm.perceptron that return DefaultKernelBinaryCategorizer

Modifier and Type	Method and Description
<InputType> DefaultKernelBinaryCategorizer<InputType>	AbstractKernelizableBinaryCategorizerOnlineLearner.createInitialLearnedObject(Kernel<? super InputType> kernel)
<InputType> DefaultKernelBinaryCategorizer<InputType>	AbstractLinearCombinationOnlineLearner.createInitialLearnedObject(Kernel<? super InputType> kernel)
<InputType> DefaultKernelBinaryCategorizer<InputType>	KernelizableBinaryCategorizerOnlineLearner.createInitialLearnedObject(Kernel<? super InputType> kernel) Creates the initial learned object with a given kernel.
<InputType> DefaultKernelBinaryCategorizer<InputType>	AbstractKernelizableBinaryCategorizerOnlineLearner.learn(Kernel<? super InputType> kernel, java.lang.Iterable<? extends InputOutputPair<? extends InputType,java.lang.Boolean>> data)
<InputType> DefaultKernelBinaryCategorizer<InputType>	KernelizableBinaryCategorizerOnlineLearner.learn(Kernel<? super InputType> kernel, java.lang.Iterable<? extends InputOutputPair<? extends InputType,java.lang.Boolean>> data) Run this algorithm on a batch of data using the given kernel function.

Methods in gov.sandia.cognition.learning.algorithm.perceptron that return types with arguments of type DefaultKernelBinaryCategorizer

Modifier and Type	Method and Description
<InputType> SupervisedBatchAndIncrementalLearner<InputType,java.lang.Boolean,DefaultKernelBinaryCategorizer<InputType>>	AbstractKernelizableBinaryCategorizerOnlineLearner.createKernelLearner(Kernel<? super InputType> kernel)
<InputType> SupervisedBatchAndIncrementalLearner<InputType,java.lang.Boolean,DefaultKernelBinaryCategorizer<InputType>>	KernelizableBinaryCategorizerOnlineLearner.createKernelLearner(Kernel<? super InputType> kernel) Creates a new kernel-based learner using the standard learning interfaces based on this learner and its parameters.

Methods in gov.sandia.cognition.learning.algorithm.perceptron with parameters of type DefaultKernelBinaryCategorizer

Modifier and Type	Method and Description
protected <InputType> double	AbstractLinearCombinationOnlineLearner.computeDecay(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted, double update) Computes the decay scalar for the existing weights.
protected <InputType> double	OnlineShiftingPerceptron.computeDecay(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted, double update)
protected <InputType> double	AbstractLinearCombinationOnlineLearner.computeRescaling(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted, double update, double decay) Computes the rescaling for the new weights.
protected abstract <InputType> double	AbstractLinearCombinationOnlineLearner.computeUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted) Compute the update weight in the linear case.
protected <InputType> double	OnlineBinaryMarginInfusedRelaxedAlgorithm.computeUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted)
<InputType> double	OnlinePassiveAggressivePerceptron.computeUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted)
<InputType> double	OnlinePerceptron.computeUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted)
<InputType> double	OnlineRampPassiveAggressivePerceptron.computeUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory, double predicted)
<InputType> double	OnlineShiftingPerceptron.computeUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label, double predicted)
protected <InputType> void	AbstractLinearCombinationOnlineLearner.initialize(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory) Initializes the kernel binary categorizer.
protected <InputType> void	OnlineBinaryMarginInfusedRelaxedAlgorithm.initialize(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean actualCategory)
<InputType> void	AbstractKernelizableBinaryCategorizerOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputOutputPair<? extends InputType,java.lang.Boolean> data)
<InputType> void	KernelizableBinaryCategorizerOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputOutputPair<? extends InputType,java.lang.Boolean> data) Performs a kernel-based incremental update step on the given object using the given supervised data.
<InputType> void	AbstractLinearCombinationOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean output)
<InputType> void	AggressiveRelaxedOnlineMaximumMarginAlgorithm.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
<InputType> void	Ballseptron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
<InputType> void	KernelizableBinaryCategorizerOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean output) Performs a kernel-based incremental update step on the given object using the given supervised data.
<InputType> void	RelaxedOnlineMaximumMarginAlgorithm.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
<InputType> void	AbstractKernelizableBinaryCategorizerOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, java.lang.Boolean output)
<InputType> void	KernelizableBinaryCategorizerOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, java.lang.Boolean output) Performs a kernel-based incremental update step on the given object using the given supervised data.
<InputType> void	AbstractKernelizableBinaryCategorizerOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, java.lang.Iterable<? extends InputOutputPair<? extends InputType,java.lang.Boolean>> data)
<InputType> void	KernelizableBinaryCategorizerOnlineLearner.update(DefaultKernelBinaryCategorizer<InputType> target, java.lang.Iterable<? extends InputOutputPair<? extends InputType,java.lang.Boolean>> data) Performs a kernel-based incremental update step on the given object using the given supervised data.

Uses of DefaultKernelBinaryCategorizer in gov.sandia.cognition.learning.algorithm.perceptron.kernel

Subclasses of DefaultKernelBinaryCategorizer in gov.sandia.cognition.learning.algorithm.perceptron.kernel

Modifier and Type	Class and Description
static class	Forgetron.Result<InputType> The result object learned by the Forgetron, which extends the DefaultKernelBinaryCategorizer with some additional state information needed in the update step.

Methods in gov.sandia.cognition.learning.algorithm.perceptron.kernel that return DefaultKernelBinaryCategorizer

Modifier and Type	Method and Description
DefaultKernelBinaryCategorizer<InputType>	AbstractOnlineKernelBinaryCategorizerLearner.createInitialLearnedObject()
DefaultKernelBinaryCategorizer<InputType>	Forgetron.createInitialLearnedObject()
DefaultKernelBinaryCategorizer<InputType>	Forgetron.Basic.createInitialLearnedObject()
DefaultKernelBinaryCategorizer<InputType>	KernelBinaryCategorizerOnlineLearnerAdapter.createInitialLearnedObject()
DefaultKernelBinaryCategorizer<InputType>	RemoveOldestKernelPerceptron.createInitialLearnedObject()
DefaultKernelBinaryCategorizer<InputType>	KernelPerceptron.getResult()

Methods in gov.sandia.cognition.learning.algorithm.perceptron.kernel with parameters of type DefaultKernelBinaryCategorizer

Modifier and Type	Method and Description
protected void	Projectron.applyUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, double actual, double margin, double kernelInputInput, double delta, Vector d) Apply the update for the Projectron.
protected void	Projectron.LinearSoftMargin.applyUpdate(DefaultKernelBinaryCategorizer<InputType> target, InputType input, double actual, double margin, double kernelInputInput, double delta, Vector d)
protected void	KernelPerceptron.setResult(DefaultKernelBinaryCategorizer<InputType> result) Sets the object currently being result.
void	KernelBinaryCategorizerOnlineLearnerAdapter.update(DefaultKernelBinaryCategorizer<InputType> target, InputOutputPair<? extends InputType,java.lang.Boolean> data)
abstract void	AbstractOnlineKernelBinaryCategorizerLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean output) Updates the target categorizer based on the given input and its associated output.
void	Forgetron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
void	Forgetron.Basic.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
void	KernelBinaryCategorizerOnlineLearnerAdapter.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean output)
void	OnlineKernelPerceptron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
void	OnlineKernelRandomizedBudgetPerceptron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean output)
void	Projectron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
void	RemoveOldestKernelPerceptron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
void	Stoptron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
void	AbstractOnlineKernelBinaryCategorizerLearner.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, java.lang.Boolean output)
void	KernelBinaryCategorizerOnlineLearnerAdapter.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, java.lang.Boolean output)
static <InputType> boolean	OnlineKernelPerceptron.update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label, boolean updateBias) Performs a Perceptron update step on the given target.

Uses of DefaultKernelBinaryCategorizer in gov.sandia.cognition.learning.function.kernel

Methods in gov.sandia.cognition.learning.function.kernel with parameters of type DefaultKernelBinaryCategorizer

Modifier and Type	Method and Description
static <InputType> double	KernelUtil.norm2(DefaultKernelBinaryCategorizer<InputType> target) Computes the 2-norm of the weight vector implied by the given kernel binary categorizer.
static <InputType> double	KernelUtil.norm2Squared(DefaultKernelBinaryCategorizer<InputType> target) Computes the squared 2-norm of the weight vector implied by the given kernel binary categorizer.
static void	KernelUtil.scaleEquals(DefaultKernelBinaryCategorizer<?> target, double scale) Scales all of the weights in the given kernel binary categorizer by the given value.