BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Algorithmic Transparency Requirement - Adalbert Fono (LMU Muni
 ch)
DTSTART:20240411T130000Z
DTEND:20240411T140000Z
UID:TALK215530@talks.cam.ac.uk
CONTACT:Matthew Colbrook
DESCRIPTION:Deep learning still has drawbacks in terms of trustworthiness\
 , which describes a comprehensible\, fair\, safe\, and reliable method. To
  mitigate the potential risk of AI\, clear obligations associated to trust
 worthiness have been proposed via regulatory guidelines\, e.g.\, in the Eu
 ropean AI Act. Therefore\, a central question is to what extent trustworth
 y deep learning can be realized. Establishing the described properties con
 stituting trustworthiness requires that the factors influencing an algorit
 hmic computation can be retraced\, i.e.\, the algorithmic implementation i
 s transparent. We derive a mathematical framework which enables us to anal
 yze whether a transparent implementation in a computing model is feasible.
  Finally\, we exemplarily apply our trustworthiness framework to analyze d
 eep learning approaches for inverse problems in digital computing models r
 epresented by Turing machines.
LOCATION:Centre for Mathematical Sciences\, MR14
END:VEVENT
END:VCALENDAR