BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260608T084447Z
UID:AAEC8A61-95A4-46A8-B490-EA3E4B1B170A
DTSTART;TZID=Europe/Vienna:20260605T000000
DTEND;TZID=Europe/Vienna:20260605T133000
DESCRIPTION:Invited lecture by Prof. Satish Kumar Singh\n\nABSTRACT:\n\nThi
 s talk explores explainability techniques in signal\, image\, and language
  processing\, highlighting how complex AI models make decisions across div
 erse data modalities. It discusses methods for interpreting model behavior
 \, visualizing learned representations\, and identifying influential featu
 res. Real-world applications demonstrate how explainability improves trans
 parency\, trust\, and reliability in intelligent systems. The session also
  addresses current challenges and future directions for developing more in
 terpretable and accountable AI solutions.\n\nSpeaker(s): Satish\, \n\nRoom
 : P3\, Bldg: FRI building\, UL Faculty of Computer and Information Science
  \, Večna pot 113\, Ljubljana\, Slovenia\, Slovenia\, 1000
LOCATION:Room: P3\, Bldg: FRI building\, UL Faculty of Computer and Informa
 tion Science \, Večna pot 113\, Ljubljana\, Slovenia\, Slovenia\, 1000
ORGANIZER:anton.umek@fe.uni-lj.si
SEQUENCE:12
SUMMARY: Ante-hoc and Post-hoc Explainability in AI for Signal and Image P
 rocessing
URL;VALUE=URI:https://events.vtools.ieee.org/m/562053
X-ALT-DESC:Description: <br /><p>Invited lecture by Prof. Satish Kumar Sing
 h</p>\n<p>ABSTRACT:&nbsp\;</p>\n<p><span data-olk-copy-source="MessageBody
 ">This talk explores explainability techniques in signal\, image\, and lan
 guage processing\, highlighting how complex AI models make decisions acros
 s diverse data modalities. It discusses methods for interpreting model beh
 avior\, visualizing learned representations\, and identifying influential 
 features. Real-world applications demonstrate how explainability improves 
 transparency\, trust\, and reliability in intelligent systems. The session
  also addresses current challenges and future directions for developing mo
 re interpretable and accountable AI solutions.</span></p>
END:VEVENT
END:VCALENDAR