BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//cyber-valley.de//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:2521@cyber-valley.de
DTSTAMP:20261027T135806Z
DTSTART:20230124T130000Z
DTEND:20230124T140000Z
SUMMARY:Research Talk: Semantic Probabilistic Layers for Neuro-Symbolic Lea
 rning
DESCRIPTION:Extending current deep learning architectures to correctly conf
 orm to prior knowledge and capture symbolic constraints while guaranteeing
  their satisfaction is a big open problem. Doing so would benefit many str
 uctured-output prediction (SOP) tasks in machine learning such as predicti
 ng rankings\, hierarchies and other structured objects. In this talk\, I w
 ill discuss how we can design
END:VEVENT
END:VCALENDAR