Features

Features of DL-Learner:

• implements different algorithms:
  • two refinement operator based algorithms
  • a genetic programming algorithm
  • a hybrid algorithm using genetic refinement operators
  • (random learning, brute force learning)
• supports different kinds of learning problems:
  • learning concept definitions and inclusion axioms
  • learning from positive and negative examples as well as only from positive examples
• supports different input formats:
  • OWL files
  • N-triple files
  • internal representation in config files
  • SPARQL endpoints
• different reasoner adapters:
  • DIG interface: allows all major reasoners
  • OWL API interface (alpha): FaCT++, Pellet
  • KAON2: direct Java API access (may be removed in the future, because KAON2 is not open source)
• different user interfaces:
  • command line
  • web service
  • Java Swing based GUI 
• easily extensible through a component model
  • 4 types of components: knowledge sources, reasoners, learning problems, learning algorithms
  • to implement a new component of one of the above types you only have to extend the correct class in org.dllearner.core and add the name of your file to the components.ini file
• allows a wide range of configuration options