When AI must never fail

Artificial intelligence is increasingly shaping decisions that matter deeply to society – from medical diagnoses and autonomous mobility to critical infrastructure and security. When systems learn and adapt on their own, a central question arises: How can we make sure AI behaves safely and reliably, even under uncertainty?

This question lies at the heart of the upcoming AI Colloquium lecture by Prof. Dr. Nils Jansen. In his talk Safe Learning Systems – Artificial Intelligence and Formal Methods, he explores how modern AI can be combined with rigorous mathematical techniques to build systems we can truly trust. Drawing on examples from safety-critical domains, Jansen illustrates why robustness and verification are no longer optional, but essential foundations for responsible AI deployment.

Prof. Jansen is a leading expert at the intersection of artificial intelligence and formal methods. He holds a professorship at Ruhr University Bochum and is an ELLIS fellow, with an additional appointment in the Netherlands. His research focuses on making learning systems dependable by design. In his lecture, he will explain how formal verification techniques such as model checking can be integrated with reinforcement learning – an AI approach that enables systems to act autonomously in unknown environments. By explicitly modeling uncertainty, these methods help ensure that learning systems remain safe even when conditions change or knowledge is incomplete.

The lecture will show how neural and symbolic approaches can complement each other, offering a path toward AI systems that are not only powerful, but also transparent, verifiable, and trustworthy. This makes the topic highly relevant for researchers developing new methods, policymakers concerned with regulation and accountability, students interested in responsible AI, and a broader public seeking to understand how safety can be embedded into intelligent technologies.

Event details
The lecture takes place on Thursday, 15 January 2026, starting at 10:15 AM, at TU Dortmund University, Joseph-von-Fraunhofer-Straße 25, 3rd floor. Participation is open to all interested audiences.
Zoom: ​​​​​​https://tu-dortmund.zoom.us/j/93319743997?pwd=cjNuZzFEOTNXdFRBbmk4M0FmV01LQT09#success 

AI Colloquium
The AI Colloquium is a series of lectures dedicated to cutting-edge research in the field of machine learning and artificial intelligence, coorganized by the Research Center Trustworthy Data Science and Security (RC Trust), the Lamarr Institute for Machine Learning and Artificial Intelligence (Lamarr Institute), and the Center for Data Science & Simulation at TU Dortmund University (DoDas).