JProf. Tanya Braun, Institut für Informatik

Private Homepagehttps://www.uni-muenster.de/Informatik.AGBraun/
Research InterestsStatistical relational artificial intelligence, specifically, probabilistic inference (probability- as well as decision-theoretic) in relational domains
Human-aware AI, specifically, inference in human-aware agents
Text understanding, specifically, annotations and context representations
Current TalksExploiting Structure in Decision Making under the Lens of Recent Advances in StaRAI. KI-24 47th German Conference on Artificial Intelligence, Würzburg Slides Link to event
What Can Explainability Mean for Probabilistic Inference?. sAIOnARA 2024 (Conference on Shaping Trustworthy AI: Opportunities, Innovation, and Achievements for Reliable Approaches), Bielefeld Slides Link to event
What’s Intelligence Got To Do With It? An Introduction into Artificial Intelligence Research. Grand Rounds - Interdisziplinäres Klinikcurriculum, University Hospital Münster, Department of Mental Health Slides
Let's Talk about Palm Leaves - From Minimal Data to Text Understanding. 46th German Conference on Artificial Intelligence, 26-29 September 2023, Berlin, Germany, Berlin Slides Link to event
On Domain-specific Topic Modelling Using the Case of a Humanities Journal. CHAI 2023 3rd Workshop on Humanities-centred AI, co-located with KI 2023, Berlin Slides Link to event
Statistical Relational AI - Exploiting Symmetries (Tutorial). 20th International Conference on Principles of Knowledge Representation and Reasoning (KR 2023), Rhodes Slides Link to event
What’s Intelligence Got To Do With It? A Brief History and Overview of Artificial Intelligence Research. German-Swiss Geodynamics Workshop, Haltern am See Slides Link to event
A Glimpse into Statistical Relalional AI - Indistinguishability for the Win!. GI Forum, Münster Slides
Inference Techniques for Resilience. Resilienzkolloquium, Virtual Slides Link to event
Current PublicationsLuttermann, Malte; Speller, Jan; Gehrke, Marcel; Braun, Tanya; Möller, Ralf; Hartwig, Mattis Approximate Lifted Model Construction. IJCAI-25 Proceedings of the 34th International Joint Conference on Artificial Intelligence, 2025 online
Hamid, Sagad; Braun, Tanya Combining Local Symmetry Exploitation and Reinforcement Learning for Optimised Probabilistic Inference - A Work In Progress. , 2025 online
Bender, Magnus; Braun, Tanya; Möller, Ralf; Gehrke, Marcel Unsupervised Estimation of Subjective Content Descriptions in an Information System. International Journal of Semantic Computing Vol. 18 (1), 2024 online
Bender, Magnus; Braun, Tanya; Möller, Ralf; Gehrke, Marcel ReFrESH – Relation-preserving Feedback-reliant Enhancement of Subjective Content Descriptions. , 2024 online
Luttermann, Malte; Braun, Tanya; Möller, Ralf; Gehrke, Marcel Colour Passing Revisited: Lifted Model Construction with Commutative Factors. AAAI-24 Proceedings of the 38th AAAI Conference on Artificial IntelligenceProceedings of the AAAI Conference on Artificial Intelligence Vol. 18, 2024 online
Hartwig, Mattis; Möller, Ralf; Braun, Tanya An Extended View on Lifting Gaussian Bayesian Networks. Artificial Intelligence Vol. 330, 2024 online
Gehrke, Marcel; Liebenow, Johannes; Mohammadi, Esfandiar; Braun, Tanya Lifting in Support of Privacy-preserving Probabilistic Inference. Künstliche Intelligenz Vol. 38 (3), 2024 online
• AI in Healthcare and the Public Sector. Künstliche Intelligenz Vol. 38 (3), 2024 online
Braun, Tanya; Möller, Ralf Lessons from Resource-aware Machine Learning for Healthcare: An Interview with Katharina Morik. Künstliche Intelligenz Vol. 38 (3), 2024 online
Current ProjectsHAPPI - Human-aware PGMs and Probabilistic Inference via Lifted Model Reconciliation

Bei diesem Projekt geht es darum, die Kommunikation zwischen KI-Systemen und Menschen zu verbessern. In KI-basierten Systemen werden häufig Modelle aus Daten gelernt. Diese Modelle können zwar auch Wissen von Expertinnen und Experten beinhalten, sind aber häufig durch die gelernten Informationen aus den Daten nicht mehr einfach zu erklären. In dem Projekt wird dort angesetzt, indem Methoden erforscht werden, wie solche gelernten Modelle mit den Erwartungen von Expertinnen und Experten in Übereinstimmung gebracht werden können und Mensch und System sich gegenseitig ihre Wissenslücken erklären können. Auf lange Sicht sollen diese Systeme zum Beispiel in Medizin oder Geisteswissenschaften ihre Vorschläge erklären können.

online
E-Mailtanya dot braun at uni-muenster dot de
Phone+49 251 83-38417
Room609
Secretary   Sekretariat Steinhoff
Frau Gerlinde Steinhoff
Telefon +49 251 83-38447
Zimmer 602
AddressJProf. Tanya Braun
Institut für Informatik
Fachbereich Mathematik und Informatik der Universität Münster
Einsteinstrasse 62
48149 Münster
Deutschland
Diese Seite editieren