BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260808T230118Z
UID:bd0c6c75-86e1-40e5-99bc-8e4ceb2834f0
DTSTART:20171130T090000Z
DTEND:20170112T000000Z
DESCRIPTION:This course part focuses on a recent machine learning method kn
 own as deep learning that emerged as a promising disruptive approach\, all
 owing knowledge discovery from large datasets in an unprecedented effectiv
 eness and efficiency. It is particularly relevant in research areas\, whic
 h are not accessible through modelling and simulation often performed in H
 PC. Traditional learning\, which was introduced in the 1950s and became a 
 data-driven paradigm in the 90s\, is 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 dat
 asets and research areas.\n This course provides an introduction into deep
  learning and its inherent ability to derive optimal and often quite gener
 ic problem representations from the data (aka ‘feature learning’). Con
 crete architectures such as Convolutional Neural Networks (CNNs) will be a
 pplied to real datasets of applications using known deep learning framewor
 ks such as Tensorflow\, Keras\, or Torch. As the learning process with CNN
 s is extremely computational-intensive the course will cover aspects of ho
 w parallel computing can be leveraged in order to speed-up the learning pr
 ocess using general purpose computing on graphics processing units (GPGPUs
 ). Hands-on exercises allow the participants to immediately turn the newly
  acquired skills into practice. After this course participants will have a
  general understanding for which problems CNN learning architectures are u
 seful and how parallel and scalable computing is facilitating the learning
  process when facing big datasets.\n About the lecturer: Prof. Dr. – Ing
 . Morris Riedel received his PhD from the Karlsruhe Institute of Technolog
 y (KIT) and he is the head of the ‘high productivity data processing’ 
 research group of the Juelich Supercomputing Centre (JSC) in Germany. As a
 n adjunct associated professor at the School of Natural Sciences and Engin
 eering of the University of Iceland he teaches ‘High Performance Computi
 ng’\, ‘Cloud Computing and Big Data’\, as well as ‘Statistical Dat
 a Mining’ and all of these courses are on the intersection of parallel c
 omputing and machine learning. He has given tutorials like the course abov
 e at numerous occasions like at the Barcelona Supercomputing Centre\, Smar
 t Data Innovation Conference\, or Prace Spring School in Cyprus. His resea
 rch interests are parallel and scalable machine learning and data science.
  (More info at http://www.morrisriedel.de )\n

LOCATION:Multimediaroom building S9 Campus De Sterre
SUMMARY:Deep Learning using a Convolutional Neural Network
URL;VALUE=URI:https://www.vscentrum.be/en/education-and-trainings/detail/sp
 ecialist-workshops-in-scientific-computing---swsc-30112017
END:VEVENT
END:VCALENDAR