Brownbag Seminar: AI Safety and Data-Driven Health Care: Challenges and Opportunities

Francesco Quinzan, associate researcher at the University of Oxford, will discuss some of the main challenges in AI Safety, focusing on medical applications. He will argue that it is possible to design AI systems that are robust and capable of generalizing effectively, by uncovering the causal mechanisms of the underlying data generating process. Also, he will discuss how state-of-the-art generative models can be used on top of these techniques, to further enhance generalization performance. He will illustrate recent advancements in this field, and discuss possible future directions.