gov.sandia.cognition.learning.algorithm

Interface SupervisedIncrementalLearner<InputType,OutputType,ResultType extends Evaluator<? super InputType,? extends OutputType>>

Type Parameters:

InputType - The type of input data in the input-output pair that the learner can learn from. The Evaluator learned from the algorithm also takes this as the input parameter.

OutputType - The type of output data in the input-output pair that the learner can learn from. The Evaluator learned from the algorithm also produces this as its output.

ResultType - The type of object created by the learning algorithm. For example, a LinearBinaryCategorizer.

All Superinterfaces:

java.lang.Cloneable, CloneableSerializable, IncrementalLearner<InputOutputPair<? extends InputType,OutputType>,ResultType>, java.io.Serializable

All Known Subinterfaces:

KernelizableBinaryCategorizerOnlineLearner, LinearizableBinaryCategorizerOnlineLearner<InputType>, SupervisedBatchAndIncrementalLearner<InputType,OutputType,ResultType>

All Known Implementing Classes:

AbstractKernelizableBinaryCategorizerOnlineLearner, AbstractLinearCombinationOnlineLearner, AbstractOnlineBudgetedKernelBinaryCategorizerLearner, AbstractOnlineKernelBinaryCategorizerLearner, AbstractOnlineLinearBinaryCategorizerLearner, AbstractSupervisedBatchAndIncrementalLearner, AdaptiveRegularizationOfWeights, AggressiveRelaxedOnlineMaximumMarginAlgorithm, Ballseptron, ConfidenceWeightedDiagonalDeviation, ConfidenceWeightedDiagonalDeviationProject, ConfidenceWeightedDiagonalVariance, ConfidenceWeightedDiagonalVarianceProject, Forgetron, Forgetron.Basic, Forgetron.Greedy, KernelBinaryCategorizerOnlineLearnerAdapter, OnlineBaggingCategorizerLearner, OnlineBinaryMarginInfusedRelaxedAlgorithm, OnlineKernelPerceptron, OnlineKernelRandomizedBudgetPerceptron, OnlinePassiveAggressivePerceptron, OnlinePassiveAggressivePerceptron.AbstractSoftMargin, OnlinePassiveAggressivePerceptron.LinearSoftMargin, OnlinePassiveAggressivePerceptron.QuadraticSoftMargin, OnlinePerceptron, OnlineRampPassiveAggressivePerceptron, OnlineShiftingPerceptron, OnlineVotedPerceptron, Projectron, Projectron.LinearSoftMargin, RelaxedOnlineMaximumMarginAlgorithm, RemoveOldestKernelPerceptron, Stoptron, Winnow

public interface SupervisedIncrementalLearner<InputType,OutputType,ResultType extends Evaluator<? super InputType,? extends OutputType>>
extends IncrementalLearner<InputOutputPair<? extends InputType,OutputType>,ResultType>

Interface for supervised incremental learning algorithms. It contains the typical generic definition conventions for an incremental, supervised learning algorithm. It also contains a convenience method for providing a new input/output example without packing it into an InputOutputPair.

Since:

3.2.0

Author:

Justin Basilico

Method Summary

Modifier and Type	Method and Description
void	update(ResultType target, InputType input, OutputType output) The update method updates an object of ResultType using the given a new supervised input-output pair, using some form of "learning" algorithm.

Methods inherited from interface gov.sandia.cognition.learning.algorithm.IncrementalLearner

createInitialLearnedObject, update, update

Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable

clone

Method Detail

update

void update(ResultType target,
            InputType input,
            OutputType output)

The update method updates an object of ResultType using the given a new supervised input-output pair, using some form of "learning" algorithm.

Parameters:

target - The object to update.

input - The supervised input to learn from.

output - The supervised output to learn from.