BEGIN:VCALENDAR
VERSION:2.0
PRODID:www.dresden-science-calendar.de
METHOD:PUBLISH
CALSCALE:GREGORIAN
X-MICROSOFT-CALSCALE:GREGORIAN
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19810329T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:DSC-18281
DTSTART;TZID=Europe/Berlin:20211124T151500
SEQUENCE:1637604251
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20211124T164500
URL:https://www.dresden-science-calendar.de/calendar/en/detail/18281
LOCATION:Online\,   
SUMMARY:Dong: Towards Trustworthy AI through Neural-Symbolic Unification
CLASS:PUBLIC
DESCRIPTION:Speaker: Tiansi Dong \nInstitute of Speaker: University Bonn an
 d ML2R\nTopics:\n\n Location:\n  Name: Online (https://events.scads.ai/eve
 nt/4/)\n  Street:  \n  City:  \n  Phone: \n  Fax: \nDescription: Symbolic 
 reasoning is explainable\, rigor\, but brittle to noisy inputs. Deep learn
 ing overcomes these weaknesses at the cost of the explanability and the ri
 gor of symbolic approach. In this talk\, I show the possibility for a prec
 ise unification of symbolic structure and vector embedding. The unified re
 presentation inherits elegant features from both parent sides\, namely\, e
 xplanability\, rigor\, robust\, and trustworthy. This shapes a new style o
 f AI.
DTSTAMP:20260511T210926Z
CREATED:20211122T180411Z
LAST-MODIFIED:20211122T180411Z
END:VEVENT
END:VCALENDAR