BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:EPFL CIS – RIKEN AIP Seminar Series: Prof. Emtiyaz Khan "The Bay
 esian Learning Rule for Adaptive AI​​​​​​​"
DTSTART:20220413T100000
DTEND:20220413T110000
DTSTAMP:20260526T165557Z
UID:ff22589d31b51c4d0dedad8d3c7a30818f30b9956f40434fe34fa91a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Emtiyaz Khan\nGet your Zoom link: https://c5dc59ed978213
 830355fc8978.doorkeeper.jp/events/134720\nDate and Time: April 13th 6:00pm
  – 7:00pm(JST)\n10:00am-11:00pm(CEST)\n\n\nTitle: The Bayesian Learning 
 Rule for Adaptive AI\n\nAbstract:\nHumans and animals have a natural abili
 ty to autonomously learn and quickly adapt to their surroundings. How can 
 we design AI systems that do the same? In this talk\, I will present Bayes
 ian principles to bridge such gaps between humans and AI. I will show that
  a wide-variety of machine-learning algorithms are instances of a single l
 earning-rule called the Bayesian learning rule. The rule unravels a dual p
 erspective yielding new adaptive mechanisms for machine-learning based AI 
 systems. My hope is to convince the audience that Bayesian principles are 
 indispensable for an AI that learns as efficiently as we do.\nBio:\nEmtiya
 z Khan (also known as Emti) is a team leader at the RIKEN center for Advan
 ced Intelligence Project (AIP) in Tokyo where he leads the Approximate Bay
 esian Inference Team. He is also an external professor at the Okinawa Inst
 itute of Science and Technology (OIST). Previously\, he was a postdoc and 
 then a scientist at Ecole Polytechnique Fédérale de Lausanne (EPFL)\, wh
 ere he also taught two large machine learning courses and received a teach
 ing award. He finished his PhD in machine learning from University of Brit
 ish Columbia in 2012. The main goal of Emti’s research is to understand 
 the principles of learning from data and use them to develop algorithms th
 at can learn like living beings. For more than a decade\, his work has foc
 used on developing Bayesian methods that could lead to such fundamental pr
 inciples. The approximate Bayesian inference team now continues to use the
 se principles\, as well as derive new ones\, to solve real-world problems.
 \nAll participants are required to agree with the AIP Seminar Series Code 
 of Conduct.\nPlease see the URL below.\nhttps://aip.riken.jp/event-list/te
 rmsofparticipation/?lang=en\nRIKEN AIP will expect adherence to this code 
 throughout the event. We expect cooperation from all participants to help 
 ensure a safe environment for everybody.\n \n\n\n\n \n\n\nRIKEN Center f
 or Advanced Intelligence Project (AIP) which houses more than 40 research 
 teams ranging from fundamentals of machine learning to analysis of ethic
 s and social impact of artificial intelligence collaborate with the EPFL C
 IS on a monthly online seminar series around the topics and applications o
 f AI.\nRIKEN is Japan’s largest comprehensive research institution renow
 ned for high-quality research in a diverse range of scientific discipline
 s.\nRIKEN Center for Advanced Intelligence Project (AIP) houses more than 
 40 research teams ranging from fundamentals of machine learning and optim
 ization\, applications in medicine\, materials\, and disaster\, to analys
 is of ethics and social impact of artificial intelligence.\nEPFL is locate
 d in Switzerland and is one of the most vibrant and cosmopolitan science a
 nd technology institutions. EPFL has both a Swiss and international vocat
 ion and focuses on three missions: teaching\, research and innovation.\nT
 he Center for Intelligent Systems (CIS) at EPFL\, a joint initiative of th
 e schools ENAC\, IC\, SB\, STI and SV seeks to advance research and pra
 ctice in the strategic field of intelligent systems.\n\nAll participants a
 re required to agree with the AIP Seminar Series Code of Conduct.\nPlease 
 see the URL below.\nhttps://aip.riken.jp/event-list/termsofparticipation/?
 lang=en\nRIKEN AIP will expect adherence to this code throughout the event
 . We expect cooperation from all participants to help ensure a safe enviro
 nment for everybody.
LOCATION:By Zoom
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR