Gemeinsamer Vortrag "Einführung in die KI: Anomalieerkennung, medizinische Anwendungen, Datenschutz und Ethik" von Marius Kloft und Steffen Reithermann am Universitätsklinikum Düsseldorf (UKD)

• Event Location: Universitätsklinikum Düsseldorf, Moorenstr. 5, 40225 Düsseldorf

  Event Date: 06.10.2026

  Contact Person: Prof. Dr. Marius Kloft

  

  Talk: "Introduction to AI: Anomaly Detection, Medical Applications, Privacy, and Ethics"
  Marius Kloft, Steffen Reithermann @ Universitätsklinikum Düsseldorf (UKD), 06.10.2026
  
  Abstract:
  
  We begin with an overview of the Machine Learning Group at RPTU Kaiserslautern-Landau, whose research combines learning theory with deep learning,
  focusing on anomaly detection and explainable AI. We then illustrate the rapid progress of AI with recent examples.
  These range from contributions to long-standing mathematical problems
  to studies where AI systems are reaching or exceeding expert-level performance on specific diagnostic tasks.
  Next, we explain how modern AI works, from neural networks to today's foundation models.
  We then introduce anomaly detection, which aims to model what "normal" looks like and flags deviations,
  making it well suited to medicine, where abnormal findings are rare and diverse.
  Examples include our work on cancer detection in breast MRI and histopathology.
  We conclude with ethical and privacy aspects of medical AI, including the protection of patient data, bias, explainability, human oversight,
  and responsibility in clinical decision-making.
  
  Bios:
  
  Marius Kloft is Professor of Machine Learning at RPTU Kaiserslautern-Landau, Germany.
  He received his Ph.D. from TU Berlin and UC Berkeley and previously held positions at NYU’s Courant Institute, Memorial Sloan-Kettering Cancer Center,
  Humboldt University of Berlin, and the University of Southern California.
  He is co-affiliated with the German Research Center for Artificial Intelligence (DFKI),
  the International Max Planck Research School on Trustworthy Computing (IMPRS-TRUST) and ELLIS.
  His research focuses on the theoretical foundations of machine learning, deep anomaly detection, and trustworthy AI.
  His work has appeared at leading venues including NeurIPS, ICML, ICLR, AISTATS, AAAI, and IJCAI,
  and in journals such as IEEE Transactions on Information Theory and IEEE TPAMI, and has received around 15,000 citations (h-index ≈ 50).
  His paper Deep One-Class Classification (ICML 2018) received the 2022 ANDEA Test-of-Time Award.
  He is a recipient of the DFG Emmy Noether Career Award and the Google Most Influential Papers Award.
  He leads several large-scale national research consortia in Germany.
  He regularly serves as (Senior) Area Chair at major international conferences,
  most recently in 2026: AAAI, AISTATS, ICML, ICLR, and IJCAI, and is an Action Editor of IEEE TPAMI.
  
  Steffen Reithermann is AI Project Manager of the Machine Learning Group at RPTU Kaiserslautern-Landau
  and Managing Director of the AI Project Office of the AI Alliance Rhineland-Palatinate.
  His background in computer science and AI infrastructure is complemented by additional training
  in medicine, data protection, and legal aspects.
  His work focuses on AI research and transfer, AI infrastructure and sovereignty,
  as well as the practical, regulatory, and societal implications of artificial intelligence.
  He regularly speaks on a broad range of AI-related topics.
  
  A lecture event for a select group of participants.