Click here for a printable version of this page.
Colloquia
Colloquium
Friday, March 4, 2016
3:30 PM
Physics Building, Room 204

Michael Chertkov
[Host: Marija Vucelja]
LANL
"Physics Informed Machine Learning"

ABSTRACT:
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 colloquium I illustrate the twoway flow of ideas between physics and statistical engineering on three examples from our team LANL. First, I review the work on structure learning and statistical estimation in power system distribution (thus physical) networks. Then I describe recent progress in constructive understanding of graph learning (on example of inverse Ising model) illustrating that the generic inverse task (of learning) is computationally easy in spite of the fact that the direct problem (inference or sampling) is difficult. I conclude speculating how macroscale models of physics (e.g. large eddy simulations of turbulence) can be learned from microscale simulations (e.g. of NavierStocks equations).
https://sites.google.com/site/mchertkov/




To add a speaker, send an email to
physspeakers@Virginia.EDU.
Please include the seminar type (e.g. Colloquia), date, name of the speaker, title of talk, and an abstract (if available).
