BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.27360.field_data.0@www.u-gov-ricerca.uniroma1.it
DTSTAMP:20260405T115910Z
CREATED:20231018T073414Z
DESCRIPTION:AbstractInterpretable and neural symbolic AI share a common goa
 l: to enhance the currently opaque and brittle decision making process of 
 deep learning methods. To address this issue\, I will discuss the design o
 f novel interpretable deep learning methods endowed with reasoning capabil
 ities. I will then show how these methods could be applied in diverse real
 -world domains\, ranging from answering queries on knowledge graphs to for
 mulating conjectures in universal algebra.BioPietro Barbiero is Research A
 ssistant at the Università della Svizzera Italiana (Switzerland). My resea
 rch activity focuses on interpretable artificial intelligence\, and neural
 -symbolic models applied to precision medicine. My current projects are re
 lated to interpretable neural reasoning\, explainable AI theory\, and AI-a
 ssisted conjectures for abstract mathematics.
DTSTART;TZID=Europe/Paris:20231107T150000
DTEND;TZID=Europe/Paris:20231107T150000
LAST-MODIFIED:20231018T074428Z
LOCATION:Aula Magna @ DIAG
SUMMARY:Interpretable Neural Symbolic AI - Pietro Barbiero
URL;TYPE=URI:http://www.u-gov-ricerca.uniroma1.it/node/27360
END:VEVENT
END:VCALENDAR