Emily Schiller and Anton Hummel from XITASO will give a talk in the elite program’s special lecture series. The title of the talk is “Explainable AI and Uncertainty Quantification” and it will take place in room 1055N at 4PM on 26th June 2025.

Abstract

Despite the transformative potential of machine learning in critical areas such as healthcare, its integration is challenged by a lack of trust and acceptance. To overcome these challenges by ensuring reliant decision-making the interaction of users and the AI systems is crucial. Two research fields have the potential to improve human-AI collaboration: Explainable AI and Uncertainty Quantification. Explainable AI (XAI) aims to make AI predictions interpretable for humans. At the same time, Uncertainty Quantification (UQ) enables the estimation of confidence in predictions. Both areas have made important contributions to trustworthy AI, but to fully realize their potential they must be tailored to the needs of the end-users. In this presentation, we show what is needed to create a practical value in AI by highlighting novel XAI and UQ methods.