BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260707T112351Z
UID:e314da31-db63-4aa2-9e86-f2b51824e38b
DTSTART:20200310T090000Z
DTEND:20200313T175000Z
DESCRIPTION:Overview\n\nThe 4-day school will focus on providing the partic
 ipants with a concise introduction to key machine and deep learning (ML &a
 mp\; DL) concepts\, and their practical applications with relevant example
 s in the domain of molecular dynamics (MD)\, rare-event sampling and elect
 ronic structure calculations (ESC). ML is increasingly being used to make 
 sense of the enormous amount of data generated every day by MD and ESC sim
 ulations running on supercomputers. This can be used to obtain mechanistic
  understanding in terms of low-dimensional models that capture the crucial
  features of the processes under study\, or assist in the identification o
 f relevant order parameters that can be used in the context of rare-event 
 sampling. ML is also being used to train neural network based potentials f
 rom ESC which can then be used on MD engines such as LAMMPS allowing order
 s of magnitude increase in the dimensionality and time scales that can be 
 explored with ESC accuracy. So while the first half of this school will co
 ver the fundamentals of ML and DL\, the second half will be dedicated to r
 elevant examples of how these techniques are applied in the domains of MD 
 and ESC.\n\nLearning outcomes\n\nBy the end of the school\, participants a
 re expected to:\n\n\n	\n	Gain an understanding of the fundamental concepts
  of ML and DL\, including how neural networks function\, different types o
 f topologies\, common pitfalls\, etc.\n	\n	\n	Be able to implement basic d
 eep learning workflows using Python.\n	\n	\n	Leverage existing framework t
 o discover molecular mechanisms from MD simulations.\n	\n	Utilise the PANN
 A toolkit to create neural network models for atomistic systems and genera
 te results that can be integrated with MD packages.\n\n\nPrerequisites\n\n
 Participants are expected to have a working knowledge of Python (i.e. fami
 liar with the basic syntax and constructs\, have used Python before for at
  least a few months) and have a basic understanding of the fundamental phy
 sics behind molecular dynamics simulations and electronic structure calcul
 ations. All participants are expected to bring his/her own laptop to the s
 chool to conduct hands-on exercises.\n\nRegistration\n\nThere is no regist
 ration charge accepted participants. However\, all participants must regi
 ster and due to limited space\, in the event of high demand\, participants
  will be selected according to expressions of interest provided.\n\nNon-ac
 ademic participants are welcome to register to the school but should notif
 y the organisers in order to pre-empt issues with third party copyright 
 material that will be used for parts of the school.\nhttps://events.prace-
 ri.eu/event/995/
SUMMARY:PRACE & E-CAM Tutorial on Machine Learning and Simulations @ICHEC
URL;VALUE=URI:https://events.prace-ri.eu/event/995/
END:VEVENT
END:VCALENDAR