ScaDS.AI Public Colloquium Session, Nov 24, 2022

ScaDS.AI announces and welcomes you to join our public colloquium session Concept Learning with Multiple Representations on Thursday, Nov 24, 2022, 15:30-17:00 at ScaDS.AI Leipzig, onsite in the big seminar room (A03.07 Zwenkauer See) and in parallel online (details 2-3 days before the session). Add this event to your calendar (iCal).

Concept Learning with Multiple Representations

We adress the problem of learning concepts in description logics at large scale in a supervised setting. This form of machine learning has a plethora of advantages. First, complex models can be learned from small training data sets by exploiting background knowledge. Moreover, the models computed in this manner are ante-hoc explainable. In this talk, we focus on approchaes which improve the runtime of concept learning approcheas by exploiting multiple representations. For example, we show how binary tensors can be used to improve graph storage and accelerate instance checks. We discuss current challenges daced by this family of approaches as well as some surprising experimental outcomes.

About Prof. Axel Ngonga


Prof. Axel Ngonga is head of the Data Science Group at Paderborn University (DICE group) that focuses on: Data Analysis, Data Integration, Data Storage and Querying, Machine Learning, NLP and Data Access. Further, he was co-lead of the Agile Knowledge Engineering and Semantic Web (AKSW) group and its SIMBA subgroup on ‚Semantic Abstraction‘. He is fellow of the Next Einstein Forum. While working at the Computer Science Institute at Leipzig University, Ngonga was awarded as one of the top-15 African researchers under 42 in 2016. In 2009 he defended his doctoral thesis, working on which he had started as the youngest graduate of all times at Leipzig University at the age of 19.

Check out our event calendar for more information about our upcoming events!

TU
Universität
Max
Leibnitz-Institut
Helmholtz
Hemholtz
Institut
Fraunhofer-Institut
Fraunhofer-Institut
Max-Planck-Institut
Institute
Max-Plank-Institut