Booking required
Booking deadline: Monday 10 June 2019

This full-day hands-on Deep Learning fundamentals workshop is part of NVIDIA’s Deep Learning Institute. This course is a follow up to the Fundamentals of Deep Learning for Computer Vision. It covers Image Segmentation, Natural Language Captioning, and the combination of CNN and RNN for composite tasks. Competence in Python, and beginner's level understanding of Deep Learning and CNNs are required.

The detailed agenda is:

Image Segmentation with TensorFlow
Natural Language Processing – Introducing RNNs
Combining CNNs and RNNs for Image Captioning
Challenge: Video Captioning

This course aims at the following learning targets:

Introduce TensorFlow
Compare Computer Vision Workflows
Introduce Natural Language Processing
Highlight the value of mid-network information
Increase the diversity of solvable problems with Deep Learning

All participants will receive access to the NVIDIA DLI cloud infrastructure as well as the official DLI training material for at least 3 months. Thus, you will be able to continue or revise the course on your own pace after the end of this workshop. Thus, anyone can attend and complete the workshop with even minimal prior experience. NVIDIA provides completion certificates after successful assessment of certain deliverables.

Every concept is delivered with an initial lecture, then demonstrated with hands-on exercises. During these exercises, participants are guided to implement the lectured techniques but are also free to experiment and expand using the NVIDIA computing cloud infrastructure.

Seating is limited to 40 and prior registration is required by NVIDIA to reserve sufficient hardware resources in their cloud. Please reserve your place by Monday, June 10. Lunch will not be provided.

The workshop will be given by Dr Georgios Varisteas, Research Associate in the SEDAN Research Group, and a certified NVIDIA DLI instructor.

Photography

Please note that a photographer will be present at this event. The images may be published by the University, e.g. on its social media, its website and in print products. If you do not wish to be photographed, please alert the organisers and the photographer.

Data processing policy

The Interdisciplinary Centre for Security, Reliability and Trust (hereafter “SnT”) collects and processes your personal data in the framework of your registration and your participation in this event and the communication of its future activities. SnT processes and keeps your personal information only to the extent necessary to fulfill the purpose stated.

During the registration process your personal data is being collected and processed on the Eventbrite website by Eventbrite Inc. located in the United States. This will involve the transfer of personal data to countries that do not offer the same level of protection as the European Union regarding data protection rules. Eventbrite Inc. participates in and complies with the EU-U.S. Privacy Shield framework as set forth by the US Department of Commerce regarding the collection, use and retention of personal data. Eventbrite may process your personal data as a controller for different purposes than the purposes of the University of Luxembourg. More information is provided on Eventbrite Inc.’s website in their EU-US Privacy Shield Notice, Privacy Notice and Terms of Services.

You can deregister from the event directly on the Eventbrite website and withdraw your consent for the processing of personal data by SnT for the purpose stated above. You have the right to access, rectify, and erase your personal data as well as further rights described on the University of Luxembourg's website. You can exercise your rights by following the procedure described on the website.

Workshop - NVIDIA DLI Fundamentals of Deep Learning for Multiple Data Types