BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260706T022203Z
UID:0aa15e1d-813b-4e15-b33c-e261d1c96c74
DTSTART:20201021T110000Z
DTEND:20201023T143000Z
DESCRIPTION:This course has to be postponed to 2021.\n\nThis course focuses
  on a recent machine learning method known as deep learning that emerged a
 s a promising disruptive approach\, allowing knowledge discovery from larg
 e datasets in an unprecedented effectiveness and efficiency. It is particu
 larly relevant in research areas\, which are not accessible through modell
 ing and simulation often performed in HPC. Traditional learning\, which wa
 s introduced in the 1950s and became a data-driven paradigm in the 90s\, i
 s usually based on an iterative process of feature engineering\, learning\
 , and modelling. Although successful on many tasks\, the resulting models 
 are often hard to transfer to other datasets and research areas.\n\nThis c
 ourse provides an introduction into deep learning and its inherent ability
  to derive optimal and often quite generic problem representations from th
 e data (aka ‘feature learning’). Concrete architectures such as Convol
 utional Neural Networks (CNNs) will be applied to real datasets of applica
 tions using known deep learning frameworks such as Tensorflow\, Keras\, or
  Torch. As the learning process with CNNs is extremely computational-inten
 sive the course will cover aspects of how parallel computing can be levera
 ged in order to speed-up the learning process using general purpose comput
 ing on graphics processing units (GPGPUs). Hands-on exercises allow the pa
 rticipants to immediately turn the newly acquired skills into practice. Af
 ter this course participants will have a general understanding for which p
 roblems CNN learning architectures are useful and how parallel and scalabl
 e computing is facilitating the learning process when facing big datasets.
 \n\nPrerequisites: \nParticipants should be able to work on the Unix/Linux
  command line\, have a basic level of understanding of batch scripts requi
 red for HPC application submissions\, and have a minimal knowledge of prob
 ability\, statistics\, and linear algebra.\n\nParticipants should bring th
 eir own notebooks (with an ssh-client).\n\nApplication \nApplicants will b
 e notified one month before the course starts\, whether they are accepted 
 for participitation.\n\nInstructors: Prof. Dr. Morris Riedel\, Dr. Gabriel
 e Cavallaro\, Dr. Jenia Jitsev\, Jülich Supercomputing Centre\n\nContact 
 \nFor any questions concerning the course please send an e-mail to g.caval
 laro@fz-juelich.de.\nhttps://events.prace-ri.eu/event/983/
SUMMARY:[POSTPONED] Introduction to Deep Learning Models @ JSC
URL;VALUE=URI:https://events.prace-ri.eu/event/983/
END:VEVENT
END:VCALENDAR