2023 Activity Report -- Orpailleur Team (LORIA) : Knowledge Discovery and Knowledge Engineering
Résumé
The research topics of the Orpailleur Team of 2023 gravitated the federating theme “Exploratory and hybrid knowledge discovery” of the team, but opened to new research directions, such as, “Explainability, transparence and fairness” and “Analogy based reasoning” that bridge the gap between Knowledge Representation and Reasoning (KRR) and in Machine Learning (ML). The Orpailleur Team has always advocated for “Knowledge Discovery guided by Domain Knowledge”, a research line which gained a role of paramount importance in ML and Artificial Intelligence (AI). In particular, the recent seminal paper on “Interpretable Machine Learning” lists 10 grand challenges in ML. In these challenges, it can be noticed that knowledge integration in ML is a basic ingredient quite everywhere, while emerging topics are materialized by analogy based reasoning, explainable and trustworthy ML&AI models, in particular, topics pertaining to algorithmic complexity and fairness. These are all represented in the Orpailleur’s research program of 2023.
Origine : Fichiers éditeurs autorisés sur une archive ouverte
