Themen der Lehrveranstaltung
- Knowledge Graphs - RDF and OWL - Query Answering over KGs - Virtual Knowledge Graphs - Vector Databases - KNN - Approximated KNN - RAG

Unterrichtsform
Lectures. In person.

Bildungsziele
D1 - Knowledge and Understanding - Understand the principles of semantic data representation using RDF, OWL, and SPARQL. - Demonstrate deep knowledge of virtual knowledge graphs, description logics, and vector database technologies. - Grasp the integration of symbolic and vector-based approaches in AI systems, including RAG. D2 - Applying Knowledge and Understanding - Design and query ontologies and knowledge graphs using tools such as Protégé and Ontop. - Build and optimize vector search systems, similarity measures, and indexing structures. - Implement retrieval-augmented pipelines combining vector search and large language models. D3 - Making Judgements - Critically assess semantic and vector-based methods for data management and AI integration. - Evaluate modeling and system design choices based on scalability, expressiveness, and performance. - Analyze and interpret experimental results to improve system design and methodology. D4 - Communication - Clearly present complex technical content in both academic and interdisciplinary settings. - Produce well-structured documentation, presentations, and research papers in the field. D5 - Learning Skills - Independently explore advanced literature and technologies in semantic and AI-driven data systems. - Design and conduct original research projects, demonstrating scholarly autonomy and innovation.

Art der Prüfung
The final exam will consist of either: - A critical presentation based on scientific literature, or - A small applied project related to the course topics (e.g., knowledge graphs, vector databases, retrieval-augmented generation).

Bewertungskriterien
Evaluation will be on a pass/fail basis, according to the following criteria: 1. Relevance and Understanding - The work demonstrates a solid grasp of the selected topic and its connection to the course content. 2. Analytical and Critical Thinking - The student shows the ability to analyze and explain key concepts, methods, or design choices. 3. Technical or Conceptual Accuracy - Presentations accurately synthesize the literature; projects are functional and coherent. 4. Communication and Clarity - The student clearly presents the material and responds appropriately to questions. To pass, students must meet acceptable standards in all areas. Outstanding work may be acknowledged informally during feedback.

Pflichtliteratur

All the required reading material will be provided during the course and will be available in electronic format. Copy of the slides will be available as well.

While not strictly required, a useful reference for the first part of the course is An Introduction to Description Logic by Franz Baader, Ian Horrocks, Carsten Lutz, and Uli Sattler (Cambridge University Press).

Subject Librarian: David Gebhardi, David.Gebhardi@unibz.it and Ilaria Miceli, Ilaria.Miceli@unibz.it

Weiterführende Literatur

Scientific papers and additional books will be specified on each course topic during lectures.

Weitere Informationen
Protege, Ontop, Milvus