NVIDIA Deep Learning Intermediate


Teaching You To Solve Problems With Deep Learning

Learn how to design, train, and deploy neural network-powered artificial intelligence in your applications.

NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning. DLI and IP EXPO Europe are excited to announce these one-day practical Deep Learning workshop on both days of IP EXPO Europe, Wednesday 4th and Thursday 5th October 2017 at ExCeL London.

Places come at a price of £385 per session.

There are two levels of workshop available, this page details the Intermediate course for those with a higher level of experience in Deep Learning, if you would like the Fundamentals course for beginners click here.

First Click REGISTER FREE for IP EXPO Europe and then select the NVIDIA Register & Training option to pay for the workshop after registration.



Data Scientists:
- Experts in collecting and analyzing data.
- May have experience with previous Machine Learning techniques.
- Needs to shift approach from hard-coded feature classifiers to data-driven deep neural networks.

Software Developers:
- Implements custom code for deep learning solutions.
- May also fill role of data scientist.
- Needs to learn how to integrate and optimize trained neural networks into apps/services for deployment.

System Architect:
- Domain expert in their field of study.
- May have experience with HPC / parallel computing.
- May also fill roles of data scientists and developer.
- Needs to learn how to apply deep learning in their field of study.


Wednesday 4th October & Thursday 5th October 2017
Location: Room SG15



Content level: Intermediate
Pre-Requisites: Nvidia’s Deep Learning Fundamentals Workshop OR a working understanding of Deep Learning Fundamentals such as:
- Training basic networks
- Searching hyperparameters to improve performance

Generating descriptions of scenes requires both computer vision and natural language processing. After an introduction to TensorFlow, learn to work with natural language and then to combine workflows and datatypes to generate captions for images and video. Building on concepts from Deep Learning Fundamentals, you will learn to:
-          Implement common deep learning workflows such as Image Segmentation and Text Generation.
-          Manipulate features of both networks and training to improve performance.
-          Compare image vs. text based data prep, data ingestion, and training workflows
-          Combine workflows to solve more complex, 'multi-sensory' problems.

Problem specific skills such as:
-          Extracting high level features from images
-          One-hot sentence encoding
-          Concatenating input data


9:00    Best Practices in Deep Learning (lecture)
9:45    Break
10:00  Image Segmentation with TensorFlow (lab)
12:00  Lunch
1:00   Text Generation with TensorFlow (lab)
3:00   Break
3:15   Image and Video Captioning by Combining CNNs and RNNs (lab)
5:15   Closing Comments & Questions
5:30   End
*Agenda timing is subject to instructor preference

DLI Workshop Attendee Instructions:

  • You must bring your own laptop to this workshop.
  • Create an account by going to https://nvlabs.qwiklab.com/ prior to getting to the workshop.
  • Make sure your laptop is set up prior to the workshop by following these steps:

- Ensure websockets runs smoothly on your laptop by going to http://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 or trying a different browser.  The labs will not run without WebSockets support
- Best browsers for the labs are Chrome, FireFox and Safari. The labs will run in IE but it is not an optimal experience.

IMPORTANT: Please remember to sign in to nvlabs.qwiklab.com using the same email address as for event registration, since class access is given based on the event registration list.

Jonas Loof
Jonas Loof

Deep Learning Solution Architect


View Speaker

Jonas Loof

Jonas Lööf is a Deep Learning Solution Architect at NVIDIA, where he helps guide customer decision making on both hardware and software in their deep learning projects.

Before joining NVIDIA, Jonas has worked in research and development, applying deep learning in the fields of speech recognition and natural language processing, both in a startup environment and the corporate world.

Jonas holds a doctoral degree in computer science from RWTH Aachen University, where he worked on acoustic model adaptation for speech recognition.

We look forward to seeing you at IP EXPO Europe for the NVIDIA Deep Learning Intermediate workshop.


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.