BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Machine Learning and Multi-scale Modeling
DTSTART:20181115T171500
DTEND:20181115T180000
DTSTAMP:20260406T204552Z
UID:9cbdbb8c7d62f13a28aa6d8c542a5cfd05cab8a627ab1dae7170f9fa
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Weinan E (Princeton\, USA)\nMulti-scale modeling is an a
 mbitious program that aims at unifying the different physical models at di
 fferent scales for the practical purpose of developing accurate models and
  simulation protocals for properties of interest. Although the concept of 
 multi-scale modeling is very powerful and very appealing\, practical succe
 ss on really challenging problems has been limited. One key difficulty has
  been our limited ability to represent complex models and complex function
 s.\nIn recent years\,  machine learning has emerged as a promising tool t
 o overcome the difficulty of representing complex functions and complex mo
 dels.  In this talk\, we will review some of the successes in applying ma
 chine learning to multi-scale modeling. These include molecular dynamics a
 nd model reduction for PDEs.\nAnother important issue is the mathematical 
 foundation of modern machine learning\, particularly in the over-parametri
 zed regime where most of the deep learning models lie. I will also discuss
  our current understanding on this important issue.
LOCATION:CM 1 4 https://plan.epfl.ch/?room==CM%201%204
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR