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:20221030T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.24952.field_data.0@www.corsodrupal.uniroma1.it
DTSTAMP:20260403T195947Z
CREATED:20221214T202554Z
DESCRIPTION:Abstract: Medicine has the potential to be transformed by machi
 ne learning (ML) by addressing core challenges such as time-series forecas
 ts\, clustering (phenotyping)\, and heterogeneous treatment effect estimat
 ion. However\, to be embraced by clinicians and patients\, ML approaches n
 eed to be interpretable. So far though\, ML interpretability has been larg
 ely confined to explaining static predictions.In this keynote\, I describe
  an extensive new framework for ML interpretability. This framework allows
  us to 1) interpret ML methods for time-series forecasting\, clustering (p
 henotyping)\, and heterogeneous treatment effect estimation using feature 
 and example-based explanations\, 2) provide personalized explanations of M
 L methods with reference to a set of examples freely selected by the user\
 , and 3) unravel the underlying governing equations of medicine from data\
 , enabling scientists to make new discoveries.Bio:Mihaela van der Schaar i
 s the John Humphrey Plummer Professor of Machine Learning\, Artificial Int
 elligence and Medicine at the University of Cambridge and a Fellow at The 
 Alan Turing Institute in London. In addition to leading the van der Schaar
  Lab\, Mihaela is founder and director of the Cambridge Centre for AI in M
 edicine(CCAIM).Mihaela was elected IEEE Fellow in 2009. She has received n
 umerous awards\, including the Oon Prize on Preventative Medicine from the
  University of Cambridge (2018)\, a National Science Foundation CAREER Awa
 rd (2004)\, 3 IBM Faculty Awards\, the IBM Exploratory Stream Analytics In
 novation Award\, the Philips Make a Difference Award and several best pape
 r awards\, including the IEEE Darlington Award.Mihaela is personally credi
 ted as inventor on 35 USA patents (the majority of which are listed here)\
 , many of which are still frequently cited and adopted in standards. She h
 as made over 45 contributions to international standards for which she rec
 eived 3 ISO Awards. In 2019\, a Nesta report determined that Mihaela was t
 he most-cited female AI researcher in the U.K. 
DTSTART;TZID=Europe/Paris:20221219T100000
DTEND;TZID=Europe/Paris:20221219T100000
LAST-MODIFIED:20221214T202944Z
LOCATION:Aula Magna@DIAG
SUMMARY:Talk: Panning for insights in medicine and beyond: New frontiers in
  machine learning interpretability - Mihaela Van Der Schaar
URL;TYPE=URI:http://www.corsodrupal.uniroma1.it/node/24952
END:VEVENT
END:VCALENDAR