BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Paris BEGIN:DAYLIGHT DTSTART:20230326T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20231029T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20231007T090835Z UID:474D3F3F-0E3E-4843-BBB0-55F1F41033F9 DTSTART;TZID=Europe/Paris:20230407T150000 DTEND;TZID=Europe/Paris:20230407T163000 DESCRIPTION:Human-Centered AI: How Can We Support End-Users to Interact wit h AI?\n\nDespite the long history of work on explanations in the Machine L earning\, AI and Recommender Systems literature\, current efforts face unp recedented difficulties: contemporary models are more complex and less int erpretable than ever. As such models are used in many day-to-day applicati ons\, justifying their decisions for non-expert users with little or no te chnical knowledge will only become more crucial. Although several explanat ion methods have been proposed\, little work has been done to evaluate whe ther the proposed methods indeed enhance human interpretability. Many exis ting methods also require significant expertise and are static. Several re searchers have voiced the need for interaction with explanations as a core requirement to support understanding. In this talk\, I will present our w ork on explanation methods that are tailored to the needs of non-expert us ers in AI. In addition\, I will present the results of several user studie s that investigate how such explanations interact with different personal characteristics\, such as expertise\, need for cognition and visual workin g memory.\n\nCo-sponsored by: Séminaires LFI\, LIP6\, TRAIL\n\nSpeaker(s) : Katrien Verbert\, \n\nRoom: Salle de conférences SCAI\, Bldg: bâtiment Esclangon\, 1er étage\, Sorbonne Université\, 4 place Jussieu\, Paris\, Ile-de-France\, France\, 75005\, Virtual: https://events.vtools.ieee.org/ m/377393 LOCATION:Room: Salle de conférences SCAI\, Bldg: bâtiment Esclangon\, 1er étage\, Sorbonne Université\, 4 place Jussieu\, Paris\, Ile-de-France\, France\, 75005\, Virtual: https://events.vtools.ieee.org/m/377393 ORGANIZER:bernadette.bouchon-meunier@lip6.fr SEQUENCE:48 SUMMARY:Seminar: Human-Centered AI: How Can We Support End-Users to Interac t with AI?\, by Katrien Verbert URL;VALUE=URI:https://events.vtools.ieee.org/m/377393 X-ALT-DESC:Description: <br /><p><em>Human-Centered AI: How Can We Support End-Users to Interact with AI?&nbsp\;</em></p>\n<p>Despite the long histor y of work on explanations in the Machine Learning\, AI and Recommender Sys tems literature\, current efforts face unprecedented difficulties: contemp orary models are more complex and less interpretable than ever. As such mo dels are used in many day-to-day applications\, justifying their decisions for non-expert users with little or no technical knowledge will only beco me more crucial. Although several explanation methods have been proposed\, little work has been done to evaluate whether the proposed methods indeed enhance human interpretability. Many existing methods also require signif icant expertise and are static. Several researchers have voiced the need f or interaction with explanations as a core requirement to support understa nding. In this talk\, I will present our work on explanation methods that are tailored to the needs of non-expert users in AI. In addition\, I will present the results of several user studies that investigate how such expl anations interact with different personal characteristics\, such as expert ise\, need for cognition and visual working memory.</p> END:VEVENT END:VCALENDAR