Section: New Results

RDF Mining

Participant : Andrea Tettamanzi.

We started investigating an approach to RDF mining based on grammatical evolution and possibility theory: the aim is to mine large RDF graphs by automatically generating and testing OWL 2 axioms based on the known facts. This research effort brings together expertise on metaheuristics for machine learning and data mining, fuzzy logic and possibility theory for representing and handling uncertainty, and the core interests of the Wimmics team, namely, knowledge graphs and the Semantic Web.

Finally, an article describing work on the automatic design of multilayer feedforward neural networks with evolutionary algorithms carried out while still at the University of Milan, got published in [75] .