Kamp Lab
Machine Learning and Artificial Intelligence at TU Dortmund University
Kamp Lab is the Machine Learning and Artificial Intelligence research group at TU Dortmund University, led by Prof. Dr. Michael Kamp. We develop principled machine-learning methods for settings in which data are distributed, sensitive, heterogeneous, or difficult to centralize and where automated decisions require particular care.
Our work combines fundamental machine-learning research with interdisciplinary applications. We study the foundations of learning and generalization as well as federated, causal, and trustworthy machine learning, with particular interest in medical and other high-stakes environments.
Our Approach
We investigate fundamental properties of learning algorithms and neural networks to better understand when models generalize, how training affects their behavior, and which properties are associated with reliable predictions.
Many real-world applications involve data that are distributed across institutions or cannot readily be centralized. We develop and study methods that enable collaborative machine learning under these constraints.
We investigate causal and interpretable approaches that can provide information beyond predictive correlations and help connect model behavior with meaningful concepts.
We work with interdisciplinary partners to evaluate machine-learning methods under realistic constraints, particularly in medicine and healthcare.
Kamp Lab is based at the Department of Computer Science at TU Dortmund University.
The group is closely connected with the Lamarr Institute for Machine Learning and Artificial Intelligence, where Prof. Dr. Michael Kamp is a faculty member. We also maintain research collaborations with the Institute for Artificial Intelligence in Medicine (IKIM) at University Medicine Essen and other academic and clinical partners.
The Lamarr Institute and IKIM are presented as institutional affiliations and research collaborations; Kamp Lab — Machine Learning and Artificial Intelligence at TU Dortmund University remains the identity of the group.
- We congratulate Osman Ali Mian and collaborators on receiving an AAAI Outstanding Paper Award 2026, “Causal Structure Learning for Dynamical Systems with Theoretical Score Analysis“.
- FLIP-IT brings federated-learning research into networks of primary-care practices and investigates decentralized learning on distributed healthcare data.
our PhD student Ting Han, our colleagues Linara Adilova, Henning Petzka, Jens Kleesiek, and Michael Kamp published a paper on “Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking” at NeurIPS 2025 .