BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Machine Learning for Scientific Discovery
DTSTART:20161125T100000
DTEND:20161125T110000
DTSTAMP:20260406T214515Z
UID:7ef020ff341f0b1060a4dc6b0d283d24b15d1f0c270799ca7ab75f83
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Cheng Soon Ong\nAssociate Professor\, Australian Nationa
 l University\nAdvances in algorithms and computation have allowed research
 ers to analyse ever larger quantities of data. This has resulted in an inc
 reasingly data driven approach to scientific research for which machine le
 arning turns out to be a popular paradigm. In recent years\, we have devel
 oped new optimisation methods for solving problems such as ranking\, learn
 ing from weak supervision and experimental design\, with the aim of solvin
 g scientific questions in collaboration with experts in other fields. The 
 long term research goal is to use active learning\, bandits\, and choice t
 heory for designing experiments.\n \nThis high level talk is about a pers
 onal journey of discovery in the sciences through the lens of machine lear
 ning. After introducing a few basic machine learning ideas\, I will highli
 ght collaborations with experts in genomics\, systems biology and astronom
 y that show how advances in data analysis have enabled scientific discover
 y. The focus will be on the practical challenges of interdisciplinary proj
 ects\, and strategies for using machine learning in data driven science.\n
  
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR