BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Biomedical Mathematics Group - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.ibs.re.kr/bimag
X-WR-CALDESC:Events for Biomedical Mathematics Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:20210101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20220805T130000
DTEND;TZID=Asia/Seoul:20220805T140000
DTSTAMP:20260425T032100
CREATED:20220804T190000Z
LAST-MODIFIED:20220729T014246Z
UID:6341-1659704400-1659708000@www.ibs.re.kr
SUMMARY:Neural Ordinary Differential Equations
DESCRIPTION:We will discuss about “Neural Ordinary Differential Equations”\, Chen\, Ricky TQ\, et al.\, Advances in neural information processing systems 31 (2018). \nAbstract: We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers\, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a blackbox differential equation solver. These continuous-depth models have constant memory cost\, adapt their evaluation strategy to each input\, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows\, a generative model that can train by maximum likelihood\, without partitioning or ordering the data dimensions. For training\, we show how to scalably backpropagate through any ODE solver\, without access to its internal operations. This allows end-to-end training of ODEs within larger models.
URL:https://www.ibs.re.kr/bimag/event/2022-08-05-jc/
LOCATION:B378 Seminar room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
END:VCALENDAR