BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085753Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20190612T130000
DTEND;TZID=Europe/Stockholm:20190612T150000
UID:submissions.pasc-conference.org_PASC19_sess138@linklings.com
SUMMARY:MS05 - Parallel High-Dimensional Approximation: Uncertainty Quanti
fication and Machine Learning, Part I of II
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Chemi
stry and Materials, Physics, Engineering\n\nSparse HPC Opportunities in De
ep Neural Networks\n\nKoanantakool\n\nWith the wide adoption of deep learn
ing, there have been numerous efforts to accelerate deep neural networks,
one of which is to exploit sparsity. Many high-dimensional problems are sp
arse by nature, and researchers have come up with abundant ways to enforce
sparse connections. In this talk, we give...\n\n---------------------\nLe
arning Large-Scale Sparse Graphical Models: Theory, Algorithm, and Applica
tions\n\nSojoudi\n\nLearning models from data has a significant impact on
many disciplines, including computer vision, medical imaging, social netwo
rks and signal processing. In the network inference problem, one may model
the relationships between the network components through an underlying in
verse covariance matrix....\n\n---------------------\nScalable Multi-Fidel
ity Machine Learning\n\nZaspel\n\nThe solution of parametric partial diffe
rential equations or other parametric problems is the main component of ma
ny applications in scientific computing. To avoid the re-implementation of
scientific simulation codes, the use of snapshot-based (non-intrusive) te
chniques for the solution of parametri...\n\n---------------------\nHeAT -
A New Versatile Distributed-Parallel Machine Learning Toolkit\n\nKnechtge
s\n\nIn this talk we will present the Helmholtz Analytics Toolkit (HeAT),
a scientific big data analytics library for HPC systems. Big data analytic
s, and machine learning in particular, has gained a lot of traction recent
ly with applications ranging from neuroscience to aeronautics. At the hear
t of many...\n
END:VEVENT
END:VCALENDAR