Breakfast seminar: To Trust, or Not to Trust? That is the Question with Amir Aminifar

Breakfast is served at 09:00, the presentation will start shortly after. For breakfast, please sign up no later than April 20: Sign up here.

Recent research in Artificial Intelligence (AI) and Machine Learning (ML) has shown that these technologies are especially vulnerable to fundamental decision-making errors. Even state-of-the-art methods, including Large Language Models (LLMs), can exhibit major weaknesses in robustness, safety, and fairness. Therefore, the adoption of such techniques has to be with extreme care, particularly in safety-critical domains such as health care and e-health. This talk examines how trust in AI/ML systems can be built, while also highlighting the key challenges involved.

Amir Aminifar is an Associate Professor and Wallenberg AI, Autonomous Systems and Software Program (WASP) Fellow in the Department of Electrical and Information Technology at Lund University, Sweden. He received his Ph.D. degree from the Swedish National Computer Science Graduate School (CUGS), Linköping University, Sweden, in 2016. Before joining Lund University, he was with the Institute of Electrical Engineering at the Swiss Federal Institute of Technology (EPFL), Switzerland. His current research interests cover a wide range of topics, including trustworthy artificial intelligence and machine learning.