BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Recent advances in weakly-supervised learning and reliable learnin
 g by Prof. Masashi Sugiyama
DTSTART:20190528T110000
DTEND:20190528T120000
DTSTAMP:20260408T071109Z
UID:a1545ecf392dbad92553210f5d968521194d52ce2f3070f1d9e1df99
CATEGORIES:Public Science Events
DESCRIPTION:Prof. Masashi Sugiyama\, Director of RIKEN Center for Advanced
  Intelligence Project and Professor at the University of Tokyo http://www.
 ms.k.u-tokyo.ac.jp/sugi/  \nAbstract: \nIn this talk\, I will introduce o
 ur recent research on weakly-supervised learning and reliable learning.\nT
 he motivation for weakly-supervised learning is to accurately perform mach
 ine learning only from "weak" data that can be collected more easily/cheap
 ly than fully-labeled data. In the first half of this talk\, I give an ove
 rview of our recently developed empirical risk minimization framework for 
 weakly-supervised classification\, covering binary classification only fro
 m PU data\, PNU data\, Pconf data\, UU data\, SU data\, and Comp data (P:p
 ositive\, N:negative\, U:unlabeled\, Conf:confidence\, S:similar\, and Com
 p:complementary).\nFor reliable deployment of machine learning systems in 
 the real world\, various types of robustness is needed. In the latter half
  of this talk\, I will give an overview of our recent work on robust learn
 ing towards noisy training data\, changing environments\, and adversarial 
 test input.\nFinally\, I will briefly introduce our RIKEN Center for Advan
 ced Intelligence Project (AIP)\, which is a national AI project in Japan s
 tarted in 2016. AIP covers a wide range of topics from generic AI research
  (machine learning\, optimization\, applied math.\, etc.)\, goal-oriented 
 AI research (material\, disaster\, cancer\, etc.)\, and AI-in-society rese
 arch (ethics\, data circulation\, laws\, etc.).\nBiography:\nMasashi Sugiy
 ama received the PhD degree in Computer Science from Tokyo Institute of Te
 chnology\, Japan in 2001. He has been Professor at the University of Tokyo
  since 2014 and concurrently appointed as Director of RIKEN Center for Adv
 anced Intelligence Project in 2016. His research interests include theory\
 , algorithms\, and applications of machine learning. He (co)-authored seve
 ral books such as Density Ratio Estimation in Machine Learning (Cambridge 
 University Press\, 2012)\, Machine Learning in Non-Stationary Environments
  (MIT Press\, 2012)\, Statistical Reinforcement Learning (Chapman and Hall
 \, 2015)\, and Introduction to Statistical Machine Learning (Morgan Kaufma
 nn\, 2015). He served as a Program co-chair and General co-chair of the Ne
 ural Information Processing Systems conference in 2015 and 2016\, and as a
  Program co-chair for the AISTATS conference in 2019. Masashi Sugiyama rec
 eived the Japan Society for the Promotion of Science Award and the Japan A
 cademy Medal in 2017.
LOCATION:Webcast available on: https://portal.klewel.com/watch/webcast/rec
 ent-advances-in-weakly-supervised-learning-and-reliable-learning/
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR