Aase Feragen, a professor at the Technical University of Denmark (DTU), provided a keynote for the NLDL conference 2024 (10 Jan 2024).
Title: How do we ensure that Trustworthy AI remains trustworthy?
Abstract: "Trustworthy AI" encompasses a range of approaches designed to promote safe and responsible use of AI. Prominent subfields include algorithmic fairness, explainable AI (XAI), and uncertainty quantification. As new legislation increasingly enforces safe use of AI, we will also see an increased use of trustworthy AI tools to justify and promote AI products. But is "Trustworthy AI" always trustworthy? In this talk we will use technical cases from algorithmic fairness, XAI and uncertainty quantification to discuss potential pitfalls in the use of Trustworthy AI tools, potential safeguards, as well as (interesting!) open problems for our community as we move into an increasingly AI-powered future.
Aasa Feragen is a rogue mathematician who has worked at the intersection of machine learning and medical imaging since 2009. She is also a professor at the Technical University of Denmark. Her MSc and PhD in mathematics are both from the University of Helsinki, following which she held postdocs at the University of Copenhagen, and the MPI for Intelligent Systems in Tübingen.
While interpretability and explainability have been at the heart of Aasa's research from the start, her more recent interests include uncertainty modelling and algorithmic fairness. Her work ranges from quantification and communication of uncertainty in brain imaging, via mathematical modelling for algorithmic fairness in medicine, to developing explainable AI algorithms for clinical use.
13 сен 2024
