3 September 2019
VŠB - Technical University Ostrava, IT4Innovations building
Europe/Prague timezone
Only for academia

Annotation

Explore the fundamentals of deep learning by training neural networks and using results to improve performance and capabilities.

During this day, you’ll learn the basics of deep learning by training and deploying neural networks. You’ll learn how to:

  • Implement common deep learning workflows, such as image classification and object detection,
  • Experiment with data, training parameters, network structure, and other strategies to increase performance and capability,
  • Deploy your neural networks to start solving real-world problems.

Upon completion, you’ll be able to start solving problems on your own with deep learning.

NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning.

This workshop contains lectures and hands-on exercises about fundamentals of Deep Learning for Computer Vision, to learn how to train and deploy a neural network to solve real-world problems.

The lectures are interleaved with many hands-on sessions using Jupyter Notebooks. The exercises will be done on a fully configured GPU-accelerated workstation in the cloud.

This training is organized by IT4Innovations National Supercomputing Center, which is a certified Nvidia DLI University Ambassador.

Target audience and Purpose of the course

Anyone interested in basics of deep learning. Upon completion, you’ll be able to start solving problems on your own with deep learning.

This course is only offered to academia (see details below in section Capacity and Fees).

About the tutor(s)

Georg Zitzlsberger is a research specialist for Machine and Deep Learning. He recently received his certification from Nvidia as a University Ambassador of the Nvidia Deep Learning Institute (DLI) program. This certification allows him to offer Nvidia DLI courses to academic users of IT4Innovations' HPC services.

NVIDIA Deep Learning Institute

The NVIDIA Deep Learning Institute delivers hands-on training for developers, data scientists, and engineers. The program is designed to help you get started with training, optimizing, and deploying neural networks to solve real-world problems across diverse industries such as self-driving cars, healthcare, online services, and robotics.

Acknowledgement

This course  is sponsored by Nvidia as part of the Nvidia Deep Learning Institute (DLI) University Ambassador program.

This work was also supported by The Ministry of Education, Youth and Sports from the Large Infrastructures for Research, Experimental Development and Innovations project ”IT4Innovations National Supercomputing Center – LM2015070”.

Starts
Ends
Europe/Prague
VŠB - Technical University Ostrava, IT4Innovations building
207
Studentská 6231/1B 708 33 Ostrava–Poruba Czech Republic

Practicalities

Prerequisities

Basics in Python will be helpful. Since Python 2.7 is used, the following tutorial can be used to learn the syntax: docs.python.org/2.7/tutorial/index.html

Bring your own laptop with eduroam properly configured. The recommended browser for the course is a recent version of Chrome. Please ensure your laptop will run smoothly by going to websocketstest.com. Make sure that WebSockets work for you by seeing under Environment, WebSockets is supported and Data Receive, Send and Echo Test all check Yes under WebSockets (Port 80). If there are issues with WebSockets, try updating your browser.

IMPORTANT: Before the workshop please create an account under http://courses.nvidia.com/join using the same email address as for event registration.

Capacity and Fees

Capacity 30 participants.

The workshop is free of charge for all academic participants and coffee breaks will be provided.

Note, that the workshop is exclusively for verifiable students, staff, and researchers from any academic institution (for industrial participants, contact NVIDIA for industrial specific training). Please bring your student/academia id.

Accommodation and transport recommendations

See this link