BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://techplay.jp//JP
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALDESC:Talk by Prof. Hsuan-Tien Lin : Label Space Dimension Reduction
  for Multi-label Classification
X-WR-CALNAME:Talk by Prof. Hsuan-Tien Lin : Label Space Dimension Reduction
  for Multi-label Classification
X-WR-TIMEZONE:Asia/Tokyo
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
BEGIN:STANDARD
DTSTART:19700101T000000
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:747659@techplay.jp
SUMMARY:Talk by Prof. Hsuan-Tien Lin : Label Space Dimension Reduction for 
 Multi-label Classification
DTSTART;TZID=Asia/Tokyo:20190830T100000
DTEND;TZID=Asia/Tokyo:20190830T110000
DTSTAMP:20260516T125148Z
CREATED:20190827T060031Z
DESCRIPTION:イベント詳細はこちら\nhttps://techplay.jp/event/74765
 9?utm_medium=referral&utm_source=ics&utm_campaign=ics\n\nTalk title: Labe
 l Space Dimension Reduction for Multi-label Classification\n\nTalk abstra
 ct:\nMulti-label classification is an extension of multi-class classifica
 tion---the former allows a set of labels to be associated with an instanc
 e while the latter allows only one. For instance\, a document may belong 
 to both he "politics" and "health" class if it is about the National Heal
 th Insurance. Many other similar applications arise in domains like text 
 mining\, vision\, or bio-informatics. In this talk\, we discuss a coding 
 view about the output (label) space of multi-label classification. The vi
 ew represents each set of possible labels as a (fixed-length) binary stri
 ng. We then discuss two research directions based on the connection: info
 rmation-preserving compression and cost-sensitive compression. The direct
 ions lead to two algorithms that systematically compresses the label spac
 e for more efficient and effective computation.\n\nShort Bio:\nProf. Hsua
 n-Tien Lin received a B.S. in Computer Science and Information Engineerin
 g from National Taiwan University in 2001\, an M.S. and a Ph.D. in Comput
 er Science from California Institute of Technology in 2005 and 2008\, res
 pectively. He joined the Department of Computer Science and Information E
 ngineering at National Taiwan University as an assistant professor in 200
 8\, and was promoted to an associate professor in 2012\, and has been a p
 rofessor since August 2017. Between 2016 and 2019\, he worked as the Chie
 f Data Scientist of Appier\, a startup company that specializes in making
  AI easier in various domains\, such as digital marketing and business in
 telligence. Currently\, he keeps growing with Appier as its Chief Data Sc
 ience Consultant.\n\nFrom the university\, Prof. Lin received the Disting
 uished Teaching Award in 2011\, the Outstanding Mentoring Award in 2013\,
  and the Outstanding Teaching Award in 2016\, 2017 and 2018. He co-author
 ed the introductory machine learning textbook Learning from Data and offe
 red two popular Mandarin-teaching MOOCs Machine Learning Foundations and 
 Machine Learning Techniques based on the textbook. His research interests
  include mathematical foundations of machine learning\, studies on new le
 arning problems\, and improvements on learning algorithms. He received th
 e 2012 K.-T. Li Young Researcher Award from the ACM Taipei Chapter\, the 
 2013 D.-Y. Wu Memorial Award from National Science Council of Taiwan\, an
 d the 2017 Creative Young Scholar Award from Foundation for the Advanceme
 nt of Outstanding Scholarship in Taiwan. He co-led the teams that won the
  third place of KDDCup 2009 slow track\, the champion of KDDCup 2010\, th
 e double-champion of the two tracks in KDDCup 2011\, the champion of trac
 k 2 in KDDCup 2012\, and the double-champion of the two tracks in KDDCup 
 2013. He served as the Secretary General of Taiwanese Association for Art
 ificial Intelligence between 2013 and 2014.
LOCATION:RIKEN AIP Open Space Nihonbashi 1-chome Mitsui Building\, 15th flo
 or\, 1-4-1 Nihonbashi\, Chuo-ku\, Tokyo
URL:https://techplay.jp/event/747659?utm_medium=referral&utm_source=ics&utm
 _campaign=ics
END:VEVENT
END:VCALENDAR