BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:djer0iebpgabskk3n400te5umo@google.com
CATEGORIES:RTportal.ru
CREATED:20170606T092329
SUMMARY:Семинар "Структурные модели и глубинное обучение": Physics Informed Machine Learning
LOCATION:аудитория 615 ИППИ РАН
DESCRIPTION;ENCODING=QUOTED-PRINTABLE: Michael Chertkov, Adjunct Professor at Center for Energy Systems, SkolTech
 ; Los Alamos National Laboratory<br/><br/>Physics Informed Machine Learning
 <br/><br/>Machine Learning (statistical engineering) capabilities are in a 
 phase of tremendous growth. Underlying these advances is a strong and deep 
 connection to various aspects of statistical physics. There is also a great
  opportunity in pointing these tools toward physical modeling. In this pres
 entation I illustrate the two-way flow of ideas between physics and statist
 ical engineering on three examples. First, I review the work on structure l
 earning and statistical estimation in power system distribution (thus physi
 cal) networks. Then I describe recent progress in constructive understandin
 g of graph learning (on example of inverse Ising model) illustrating that t
 he generic inverse task (of learning) is computationally easy in spite of t
 he fact that the direct problem (inference or sampling) is difficult. I con
 clude speculating how macro-scale models of physics (e.g. large eddy simula
 tions of turbulence) can be learned from micro-scale simulations (e.g. of N
 avier-Stocks equations). This event was imported from: https://rtportal.ru/
 index.php/kalendar-sobytij/eventdetail/138/-/seminar-strukturnye-modeli-i-g
 lubinnoe-obuchenie-physics-informed-machine-learning?tmpl=component
DTSTAMP:20260812T201352Z
DTSTART;TZID=Europe/Moscow:20160418T183000
DTEND;TZID=Europe/Moscow:20160418T200000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR