BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Memento EPFL// BEGIN:VEVENT SUMMARY:IEM Seminar Series: Panning for insights in medicine and beyond: N ew frontiers in machine learning interpretability DTSTART:20220906T100000 DTEND:20220906T110000 DTSTAMP:20260916T034722Z UID:47a284b75227cc2c2767d671a2fb1489b2e6e408d2021f7c16c0b521 CATEGORIES:Conferences - Seminars DESCRIPTION:Mihaela van der Schaar\,\nJohn Humphrey Plummer Professor of M achine Learning\, AI\, and Medicine\,\nUniversity of Cambridge\nAbstract\n Medicine has the potential to be transformed by machine learning (ML) by a ddressing core challenges such as time-series forecasts\, clustering (phen otyping)\, and heterogeneous treatment effect estimation. However\, to be embraced by clinicians and patients\, ML approaches need to be interpretab le. So far though\, ML interpretability has been largely confined to expla ining static predictions.  \n \nIn this keynote\, I describe an extensi ve new framework for ML interpretability. This framework allows us to 1) i nterpret ML methods for time-series forecasting\, clustering (phenotyping) \, and heterogeneous treatment effect estimation using feature and example -based explanations\, 2) provide personalized explanations of ML methods w ith reference to a set of examples freely selected by the user\, and 3) un ravel the underlying governing equations of medicine from data\, enabling scientists to make new discoveries.\n \nBio\nMihaela van der Schaar is th e John Humphrey Plummer Professor of Machine Learning\, Artificial Intelli gence 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 Medic ine (CCAIM).\n \nMihaela was elected IEEE Fellow in 2009. She has receive d numerous awards\, including the Oon Prize on Preventative Medicine from the University of Cambridge (2018)\, a National Science Foundation CAREER Award (2004)\, 3 IBM Faculty Awards\, the IBM Exploratory Stream Analytics Innovation Award\, the Philips Make a Difference Award and several best p aper awards\, including the IEEE Darlington Award.\n \nMihaela is persona lly credited as inventor on 35 USA patents (the majority of which are list ed here)\, many of which are still frequently cited and adopted in standar ds. She has made over 45 contributions to international standards for whic h she received 3 ISO Awards. In 2019\, a Nesta report determined that Miha ela was the most-cited female AI researcher in the U.K.\n  LOCATION:ELA 1 https://plan.epfl.ch/?room==ELA%201 https://epfl.zoom.us/j/ 67369137525 STATUS:CONFIRMED END:VEVENT END:VCALENDAR