BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Departamento de Computación - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Departamento de Computación
X-ORIGINAL-URL:https://www.dc.uba.ar
X-WR-CALDESC:Eventos para Departamento de Computación
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Sao_Paulo
BEGIN:STANDARD
TZOFFSETFROM:-0300
TZOFFSETTO:-0300
TZNAME:-03
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Sao_Paulo:20240214T140000
DTEND;TZID=America/Sao_Paulo:20240214T150000
DTSTAMP:20260411T165137
CREATED:20240208T115939Z
LAST-MODIFIED:20240208T115939Z
UID:8885-1707919200-1707922800@www.dc.uba.ar
SUMMARY:Charla de Joost Peter Katoen on Safe AI
DESCRIPTION:El miércoles 14\, a las 14hs va a dar una charla Joost Peter Katoen\, (https://en.wikipedia.org/wiki/Joost-Pieter_Katoen) y va a dar una charla que tal vez sea de su interés.\nSala 2103 a las 14 horas.\n\n\nFacing Uncertainty in AI – From Verification to Synthesis \nUncertainties occur in different forms: data may be noisy\, mechanisms may be inherently randomised\, the visibility (of e.g. a robot) may not be optimal\, and the environment in which a system needs to operate may behave in an unknown manner. \nThe central question that we will address is «Can we guarantee that AI systems are safe and dependable in the presence of such uncertainty?» We advocate using model-based\, formal verification and synthesis with a particular focus on automation. \nWe will present techniques to verify uncertainty aspects modeled as randomness and to use formal synthesis to complete partial designs. Several example AI systems will illustrate the capabilities of these approaches.
URL:https://www.dc.uba.ar/event/charla-de-joost-peter-katoen-on-safe-ai/
LOCATION:Sala 2103
CATEGORIES:Agenda
END:VEVENT
END:VCALENDAR