BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:606vabbivnjtf8s1pq4tnhm8c8@google.com
CATEGORIES:RTportal.ru
CREATED:20170606T092329
SUMMARY:Physics Informed Machine Learning
LOCATION: Кочновский проезд, дом 3, лекционный зал Декарт на 3 этаже
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:Physics Informed Machine Learning<br/><br/>Michael (Misha) Chertkov, Skolte
 ch - Adjunct Professor, on leave from Los Alamos National Laboratory)<br/><
 br/>Machine Learning (statistical engineering) capabilities are in a phase 
 of tremendous growth. Underlying these advances is a strong and deep connec
 tion to various aspects of statistical physics. There is also a great oppor
 tunity in pointing these tools toward physical modeling. In this colloquium
  I illustrate the two-way flow of ideas between physics and statistical eng
 ineering on three examples. First, I review the work on structure learning 
 and statistical estimation in power system distribution (thus physical) net
 works. Then I describe recent progress in constructive understanding of gra
 ph learning (on example of inverse Ising model) illustrating that the gener
 ic inverse task (of learning) is computationally easy in spite of the fact 
 that the direct problem (inference or sampling) is difficult. I conclude sp
 eculating how macro-scale models of physics (e.g. large eddy simulations of
  turbulence) can be learned from micro-scale simulations (e.g. of Navier-St
 ocks equations).<br/><br/><a href="https://cs.hse.ru/announcements/17917320
 8.html">https://cs.hse.ru/announcements/179173208.html</a><br/><br/>Регистр
 ация<br/><a href="https://docs.google.com/forms/d/1Z0SJ2hWn4zbzga0yYdX23RWT
 guQ-eIxzN8dQNKAZTZE/viewform">https://docs.google.com/forms/d/1Z0SJ2hWn4zbz
 ga0yYdX23RWTguQ-eIxzN8dQNKAZTZE/viewform</a> This event was imported from: 
 https://rtportal.ru/index.php/kalendar-sobytij/eventdetail/212/-/physics-in
 formed-machine-learning?tmpl=component
DTSTAMP:20260812T205021Z
DTSTART;TZID=Europe/Moscow:20160412T181000
DTEND;TZID=Europe/Moscow:20160412T194000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR