BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Collective Inference of Large-Scale Genealogical Networks
DTSTART:20170720T100000
DTEND:20170720T110000
DTSTAMP:20260917T150108Z
UID:aeb87c6ee61bb385d7f37eb18e6c0f83a16ec4653f533037b9f782d8
CATEGORIES:Conferences - Seminars
DESCRIPTION:Eric Malmi (Aalto University)\nGenealogical networks\, also kn
 own as family trees or population pedigrees\, are commonly studied by gene
 alogists wanting to discover their ancestors\, but they also provide a val
 uable resource for studies in social science\, genetics\, historical demog
 raphy\, etc. These networks are typically constructed by hand which is a v
 ery time-consuming process since it requires comparing a large number of h
 istorical records manually. I present two approaches for inferring genealo
 gical networks computationally: (1) linking historical vital records\, and
  (2) aligning existing genealogical networks. In my PhD\, I have developed
  novel probabilistic\, combinatorial optimization\, and active learning me
 thods for these two approaches. An experimental evaluation of the proposed
  methods shows that they allow accurately inferring genealogical networks 
 consisting of up to millions of individuals. Finally\, I discuss the oppor
 tunities these networks offer to the new field of computational social sci
 ence.\n\nEric Malmi is a doctoral student at Aalto University. His researc
 h interests include computational social science\, machine learning\, data
  mining\, and natural language processing. Previously\, he has done intern
 ships at Google Research (Zurich)\, Qatar Computing Research Institute\, I
 diap Research Institute\, and CERN. His works have been featured widely in
  the media and they have received one best paper award nomination and one 
 best paper award.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR