BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260708T214349Z
UID:5a692841-24b6-44eb-b4d0-c8cf433cc859
DTSTART:20190603T070000Z
DTEND:20190606T150000Z
DESCRIPTION:Overview\n\nLearn how to train and deploy a neural network to s
 olve real-world problems\, how to generate effective descriptions of conte
 nt within images and video clips\, how to effectively parallelize training
  of deep neural networks on Multi-GPUs and how to accelerate your applicat
 ions with CUDA C/C++ and OpenACC.\n\nThis new 4-days workshop offered for 
 the first time at LRZ combines lectures about fundamentals of Deep Learnin
 g for Multiple Data Types and Multi-GPUs with lectures about Accelerated C
 omputing with CUDA C/C++ and OpenACC.\n\nThe lectures are interleaved with
  many hands-on sessions using Jupyter Notebooks. The exercises will be don
 e on a fully configured GPU-accelerated workstation in the cloud.\n\nThe w
 orkshop is co-organized by LRZ and NVIDIA Deep Learning Institute (DLI) fo
 r the Partnership for Advanced Computing in Europe (PRACE). Since 2012 LRZ
  as part of GCS is one of currently 10 PRACE Training Centres which serve 
 as European hubs and key drivers of advanced high-quality training for res
 earchers working in the computational sciences.\n\nNVIDIA DLI offers hands
 -on training for developers\, data scientists\, and researchers looking to
  solve challenging problems with deep learning.\n\n All instructors are N
 VIDIA certified University Ambassadors.\n\nAgenda\n\n1st day: Fundamentals
  of Deep Learning for Multiple Data Types\n\nThis day explores how convolu
 tional and recurrent neural networks can be combined to generate effective
  descriptions of content within images and video clips.\n\nLearn how to tr
 ain a network using TensorFlow and the Microsoft Common Objects in Context
  (COCO) dataset to generate captions from images and video by:\n\n\n	Imple
 menting deep learning workflows like image segmentation and text generatio
 n\n	Comparing and contrasting data types\, workflows\, and frameworks\n	Co
 mbining computer vision and natural language processing\n\n\nUpon completi
 on\, you’ll be able to solve deep learning problems that require multipl
 e types of data inputs.\n\n2nd day: Fundamentals of Deep Learning for Mult
 i-GPUs\n\nThe computational requirements of deep neural networks used to e
 nable AI applications like self-driving cars are enormous. A single traini
 ng cycle can take weeks on a single GPU or even years for larger datasets 
 like those used in self-driving car research. Using multiple GPUs for deep
  learning can significantly shorten the time required to train lots of dat
 a\, making solving complex problems with deep learning feasible.\n\nOn the
  2nd day we will teach you how to use multiple GPUs to train neural networ
 ks. You'll learn:\n\n\n	\n	Approaches to multi-GPUs training\n	\n	\n	Algor
 ithmic and engineering challenges to large-scale training\n	\n	\n	Key tech
 niques used to overcome the challenges mentioned above\n	\n\n\nUpon comple
 tion\, you'll be able to effectively parallelize training of deep neural n
 etworks using TensorFlow.\n\n3rd day: Fundamentals of Accelerated Computin
 g with CUDA C/C++\n\nThe CUDA computing platform enables the acceleration 
 of CPU-only applications to run on the world’s fastest massively paralle
 l GPUs. On the 3rd day you experience C/C++ application acceleration by:\n
 \n\n	\n	Accelerating CPU-only applications to run their latent parallelism
  on GPUs\n	\n	\n	Utilizing essential CUDA memory management techniques to 
 optimize accelerated applications\n	\n	\n	Exposing accelerated application
  potential for concurrency and exploiting it with CUDA streams\n	\n	\n	Lev
 eraging command line and visual profiling to guide and check your work\n	\
 n\n\nUpon completion\, you’ll be able to accelerate and optimize existin
 g C/C++ CPU-only applications using the most essential CUDA tools and tech
 niques. You’ll understand an iterative style of CUDA development that wi
 ll allow you to ship accelerated applications fast.\n\n4th day: Fundamenta
 ls of Accelerated Computing with OpenACC\n\nOn the last day you learn the 
 basics of OpenACC\, a high-level programming language for programming on G
 PUs. Discover how to accelerate the performance of your applications beyon
 d the limits of CPU-only programming with simple pragmas. You’ll learn:\
 n\n\n	\n	How to profile and optimize your CPU-only applications to identif
 y hot spots for acceleration\n	\n	\n	How to use OpenACC directives to GPU 
 accelerate your codebase\n	\n	\n	How to optimize data movement between the
  CPU and GPU accelerator\n	\n\n\nUpon completion\, you'll be ready to use 
 OpenACC to GPU accelerate CPU-only applications.\n\nImportant information\
 n\nYou must bring your own laptop to this workshop!\n\nAfter you are accep
 ted\, please create an account under courses.nvidia.com/join .\n\nEnsure y
 our laptop will run smoothly by going to http://websocketstest.com/ Make s
 ure that WebSockets work for you by seeing under Environment\, WebSockets 
 is supported and Data Receive\, Send and Echo Test all check Yes under Web
 Sockets (Port 80).If there are issues with WebSockets\, try updating your 
 browser. If you have any questions\, please contact Marjut Dieringer at md
 ieringer"at"nvidia.com. \n\nPRACE Training and Education\n\nThe mission o
 f PRACE (Partnership for Advanced Computing in Europe) is to enable high-i
 mpact scientific discovery and engineering research and development across
  all disciplines to enhance European competitiveness for the benefit of so
 ciety.  PRACE has an extensive education and training effort through seas
 onal schools\, workshops and scientific and industrial seminars throughout
  Europe. Seasonal Schools target broad HPC audiences\, whereas workshops a
 re focused on particular technologies\, tools or disciplines or research a
 reas.\n\nNVIDIA Deep Learning Institute\n\nThe NVIDIA Deep Learning Instit
 ute delivers hands-on training for developers\, data scientists\, and engi
 neers. The program is designed to help you get started with training\, opt
 imizing\, and deploying neural networks to solve real-world problems acros
 s diverse industries such as self-driving cars\, healthcare\, online servi
 ces\, and robotics.\n\n\nhttps://events.prace-ri.eu/event/860/
SUMMARY:Deep Learning and GPU programming workshop @ LRZ
URL;VALUE=URI:https://events.prace-ri.eu/event/860/
END:VEVENT
END:VCALENDAR