BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards responsible deployment of robust and private AI models in 
 healthcare - Olivia Wiles\, DeepMind
DTSTART:20250128T160000Z
DTEND:20250128T170000Z
UID:TALK219385@talks.cam.ac.uk
CONTACT:Cecilia Mascolo
DESCRIPTION:Bio: Olivia Wiles is a Staff Research Scientist at DeepMind wo
 rking on robustness and evaluation of large models in machine learning\, f
 ocussing on application driven research ranging from medical applications 
 to large\, multimodal foundational models. Prior to this\, she was a PhD s
 tudent at Oxford with Andrew Zisserman studying self-supervised representa
 tions for 3D.\n\nAbstract: AI breakthroughs for medical applications are h
 appening at pace\, but it is important to consider how to ensure trustwort
 hiness of these solutions before adoption. While true for ML as a whole \,
  these questions are especially vital in the medical domain. I will discus
 s two angles of trustworthiness -- fairness/robustness and privacy -- and 
 how we can build solutions that aim to ensure these requirements are met f
 rom the ground up by leveraging generative models. While these approaches 
 show promising results\, they are not a panacea\, and a holistic approach 
 is required to identify and mitigate challenges for deploying AI solutions
  in medical applications.
LOCATION:Computer Lab\, FW26 and Online
END:VEVENT
END:VCALENDAR