BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:EPFL CIS – RIKEN AIP Seminar Series by Qibin Zhao
DTSTART:20220216T100000
DTEND:20220216T110000
DTSTAMP:20260924T131133Z
UID:ee053d9b31e24c9162a2670c814d61ce01c2826e7119960b20692b2f
CATEGORIES:Conferences - Seminars
DESCRIPTION:Qibin Zhao\nGet your Zoom link:https://c5dc59ed978213830355fc8
 978.doorkeeper.jp/events/130798\nDate and Time: February 16th 6:00pm – 7
 :00pm(JST)\n10:00am-11:00pm(CET)\n\nTitle: Efficient Machine Learning with
  Tensor Networks\nAbstract:\nModern ML methods have achieved the remarkabl
 e performance by dramatically increasing the DNN model size and the amount
  of high quality data samples. However\, how to learn information from dat
 a efficiently and train a parameter efficient model become important in pa
 rticular applications. Tensor Networks (TNs)\, which were studied in quant
 um physics and applied mathematics\, have been increasingly investigated a
 nd applied to machine learning and signal processing\, due to their advant
 ages in handling large-scale and high-dimensional problems\, model compres
 sion in DNNs\, and efficient computations for learning algorithms. This ta
 lk aims to present some recent progresses of TNs technology applied to mac
 hine learning from perspectives of basic principle and algorithms\, partic
 ularly in unsupervised learning\, data completion\, multi-model learning a
 nd various applications in deep learning modeling and etc. Finally\, we wi
 ll also present several potential research directions and new trends in th
 is area.\nBio:\nQibin Zhao received the Ph.D. degree in computer science f
 rom Shanghai Jiao Tong University\, China in 2009. He was a research scien
 tist at RIKEN Brain Science Institute from 2009 to 2017. Then\, he joined 
 RIKEN Center for Advanced Intelligence Project as a unit leader (2017 - 20
 19) and is currently a team leader for tensor learning team. He is also a 
 visiting professor in Tokyo University of Agriculture and Technology and S
 aitama Institute of Technology\, Japan. His research interests include mac
 hine learning\, tensor factorization and tensor networks\, and brain signa
 l processing. He has published more than 150 scientific papers\, and co-au
 thored two monographs on tensor networks. He serves as an editorial board 
 member for the journal “Science China: Technological Sciences”\, Area 
 Chair for top-tier ML conferences of NeurIPS\, ICML\, AISTATS\, AAAI\, IJC
 AI and ACML. He has (co)-organized several workshops on “tensor networks
  in machine learning” at NeurIPS 2020\, 2021 and IJCAI 2020.\n \n\n\n\n
  \n\n\nRIKEN Center for Advanced Intelligence Project (AIP) which houses 
 more than 40 research teams ranging from fundamentals of machine learning
  to analysis of ethics and social impact of artificial intelligence colla
 borate with the EPFL CIS on a monthly online seminar series around the top
 ics and applications of AI.\nRIKEN is Japan’s largest comprehensive rese
 arch institution renowned for high-quality research in a diverse range of
  scientific disciplines.\nRIKEN Center for Advanced Intelligence Project (
 AIP) houses more than 40 research teams ranging from fundamentals of mach
 ine learning and optimization\, applications in medicine\, materials\, and
  disaster\, to analysis of ethics and social impact of artificial intelli
 gence.\nEPFL is located in Switzerland and is one of the most vibrant and 
 cosmopolitan science and technology institutions. EPFL has both a Swiss a
 nd international vocation and focuses on three missions: teaching\, resea
 rch and innovation.\nThe Center for Intelligent Systems (CIS) at EPFL\, a 
 joint initiative of the schools ENAC\, IC\, SB\, STI and SV seeks to ad
 vance research and practice in the strategic field of intelligent systems.
 \n\nAll participants are required to agree with the AIP Seminar Series Cod
 e of Conduct.\nPlease see the URL below.\nhttps://aip.riken.jp/event-list/
 termsofparticipation/?lang=en\nRIKEN AIP will expect adherence to this cod
 e throughout the event. We expect cooperation from all participants to hel
 p ensure a safe environment for everybody.
LOCATION:By Zoom https://c5dc59ed978213830355fc8978.doorkeeper.jp/events/1
 30798
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR