BEGIN:VCALENDAR
METHOD:REQUEST
PRODID:Microsoft Exchange Server 2010
VERSION:2.0
BEGIN:VTIMEZONE
TZID:GMT Standard Time
BEGIN:STANDARD
DTSTART:16010101T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=-1SU;BYMONTH=10
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:16010101T010000
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=-1SU;BYMONTH=3
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
ORGANIZER;CN=Daniele  Quercia:mailto:[email protected]
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=smartdater
 [email protected]:mailto:[email protected]
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=members@sm
 artdata.polito.it:mailto:[email protected]
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=MINDS:mail
 to:[email protected]
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=HCI:mailto
 :[email protected]
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=nexa@serve
 r-nexa.polito.it:mailto:[email protected]
DESCRIPTION;LANGUAGE=en-US:Title: BRIO: A Bias and Risk Assessment Tool for
  Fair ML Systems\nGiuseppe Primiero\, University of Milan\n\nJoin the meet
 ing <https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZWE1MDUyMWItM2
 Q2MC00OTA3LWE1YjktYjYyNmE2OGFlMTky%40thread.v2/0?context=%7b%22Tid%22%3a%2
 25d471751-9675-428d-917b-70f44f9630b0%22%2c%22Oid%22%3a%221e405340-2229-45
 54-b37f-b193c118d70e%22%7d>\n\n\nAbstract: Phenomena of bias by AI systems
  based on machine learning methods are well known\, and largely discussed 
 in the literature. A variety of tools are being developed to assess these 
 undesirable behaviours. In this talk I present BRIO\, a bias and risk asse
 ssment tool developed by MIRAI (https://mirai.systems). The tool is based 
 on a combination of formal and statistical methods and works on the I/O da
 ta of a ML system remaining agnostic on the model itself. The result of th
 e analysis is a set of all the features and combinations thereof that prod
 uce violations with respect to a given target distribution. These values c
 an be fed into a risk function which computes an overall value weighting t
 hem on parameters such as size of the population and number of features in
 volved\, mapping naturally into notions of group and individual fairness.\
 n\n<https://arxiv.org/abs/2407.02191>Bio:  Giuseppe Primiero is Professor 
 of Logic with the Logic\, Uncertainty\, Computation and Information Lab (l
 uci.unimi.it) in the Department of Philosophy at the University of Milan\,
  Italy. He acts as Scientific Director for PHILTECH\, Research Center for 
 The Philosophy of Technology (https://philtech.unimi.it/) and as Programme
  Leader for the Master's Degree in Human-Centered AI (https://hcai.cdl.uni
 mi.it/en). He is co-founder and Chief Research Officer of MIRAI (https://m
 irai.systems). Giuseppe works in the formal modeling and verification of m
 ulti-agent systems. His preferred tools are proof-systems\, modal and comp
 utational logics. Giuseppe's formal research is applied to AI systems and 
 their deployment for resolving issues of misinformation and disinformation
  online\, as well as computable approaches to the evaluation of trustworth
 iness of information sources\, bias and fairness. He is currently the Prin
 cipal Investigator of the Projects “BRIO: Bias\, Risk and Opacity in AI
 ” (https://sites.unimi.it/brio)\, and "SMARTEST: Simulation of probabili
 stic systems for the age of the digital twin" (https://sites.unimi.it/smar
 test/) both funded by the Italian Ministry of University and Research. Ful
 l CV at https://work.unimi.it/chiedove/cv/giuseppe_primiero.pdf.\n\nSubscr
 ibe to future talk announcements: Anyone outside Bell Labs can receive tal
 k announcements by subscribing to the mailing list. To subscribe\, send an
  empty email with the subject line "Subscribe RAI" to daniele.quercia@poli
 to.it<mailto:[email protected]>\n\n\n\n\n\n
UID:040000008200E00074C5B7101A82E008000000009A42AC4AF1EBDB01000000000000000
 0100000005E74BBFE92AF0844B57B86088926D2DF
SUMMARY;LANGUAGE=en-US:[Responsible AI] BRIO: A Bias and Risk Assessment To
 ol for Fair ML Systems
DTSTART;TZID=GMT Standard Time:20250714T153000
DTEND;TZID=GMT Standard Time:20250714T163000
CLASS:PUBLIC
PRIORITY:5
DTSTAMP:20250703T080726Z
TRANSP:OPAQUE
STATUS:CONFIRMED
SEQUENCE:0
X-MICROSOFT-CDO-APPT-SEQUENCE:0
X-MICROSOFT-CDO-OWNERAPPTID:2123833242
X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE
X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY
X-MICROSOFT-CDO-ALLDAYEVENT:FALSE
X-MICROSOFT-CDO-IMPORTANCE:1
X-MICROSOFT-CDO-INSTTYPE:0
X-MICROSOFT-DONOTFORWARDMEETING:FALSE
X-MICROSOFT-DISALLOW-COUNTER:FALSE
X-MICROSOFT-REQUESTEDATTENDANCEMODE:DEFAULT
X-MICROSOFT-ISRESPONSEREQUESTED:TRUE
BEGIN:VALARM
DESCRIPTION:REMINDER
TRIGGER;RELATED=START:-PT15M
ACTION:DISPLAY
END:VALARM
END:VEVENT
END:VCALENDAR

Reply via email to