Package org.dllearner.learningproblems

Supported DL-Learner learning problems.

See: Description

Interface Summary

Interface	Description
AccMethod	Interface for any accuracy method
AccMethodApproximate	Implementation of approximate accuracy calculation.
AccMethodNoWeakness	Accuracy Method should implement this interface if it cannot filter weak solutions and thus does not return -1.
AccMethodThreeValued	Implementations of generalised measures according to method in A Note on the Evaluation of Inductive Concept Classification Procedures
AccMethodThreeValuedApproximate	Approximation support for @AccMethodThreeValued
AccMethodTwoValued	Accuracy calculation with true/false positive/negative
AccMethodTwoValuedApproximate	Approximation support for @AccMethodTwoValued
AccMethodWithBeta	Accuracy Method with beta factor; the beta factor is used to indicate the coverage on class learning problems.

Class Summary

Class	Description
AccMethodAMeasure
AccMethodAMeasureApprox
AccMethodFMeasure
AccMethodFMeasureApprox
AccMethodFMeasureWeighted
AccMethodGenFMeasure
AccMethodJaccard
AccMethodPredAcc
AccMethodPredAccApprox
AccMethodPredAccOCEL
AccMethodPredAccWeighted
AxiomScore
ClassAsInstanceLearningProblem	A learning problem in which positive and negative examples are classes, i.e.
ClassLearningProblem	The problem of learning the OWL class expression of an existing class in an OWL ontology.
ClassScore	The score of a class in ontology engineering.
EvaluatedDescriptionClass	An evaluated OWLClassExpression for learning classes in ontologies.
EvaluatedDescriptionPosNeg	This represents a class description, which has been evaluated by the learning algorithm, i.e.
EvaluatedDescriptionPosOnly
EvaluationCache	Caches results of previous concept evaluation to speed up further evaluations.
ExampleLoader	Load positive and negative examples from Class Expression
FuzzyPosNegLP
FuzzyPosNegLPStandard	The aim of this learning problem is to learn a concept definition such that the positive examples and the negative examples do not follow.
Heuristics	Implementation of various heuristics.
PosNegLP
PosNegLPStandard	The aim of this learning problem is to learn a concept definition such that the positive examples and the negative examples do not follow.
PosNegLPStrict
PosNegUndLP	A ternary learning problem (positive, negative and uncertain instances) to manage the problem of the Open World Assumption typically employed for ontologies
PosOnlyLP	A learning problem, where we learn from positive examples only.
PropertyAxiomLearningProblem<T extends org.semanticweb.owlapi.model.OWLPropertyAxiom>
QueryTreeScore
ScorePosNeg<T extends org.semanticweb.owlapi.model.OWLEntity>	The score class is used to store how well a class description did on a learning problem.
ScorePosOnly<T extends org.semanticweb.owlapi.model.OWLEntity>
ScoreSimple	A simple score implementation which only contains the accuracy.
ScoreThreeValued<T extends org.semanticweb.owlapi.model.OWLEntity>	Computes the score (a negative value) by comparing the classification results with ideal results.
ScoreTwoValued<T extends org.semanticweb.owlapi.model.OWLEntity>	Calculates accuracy and score (with respect to some length penalty) of a class description.

Enum Summary

Enum	Description
Heuristics.HeuristicType
ScoreThreeValued.ScoreMethod

Package org.dllearner.learningproblems Description

Supported DL-Learner learning problems.