The Alexandra Institute // Right Now // Events // 2018 // One-day hands-on course: Deep learning 2 (Aarhus)

One-day hands-on course: Deep learning 2 (Aarhus)



One-day hands-on course: Deep learning 2 (Aarhus)

Fundamentals of Deep Learning for Multiple Data Types

The Alexandra Institute and NVIDIA Deep Learning Institute offer this one-day course in deep learning with hands-on training.

This course explores how convolutional and recurrent neural networks can be combined to generate effective descriptions of content within images and video clips.

If you are new to deep learning, you might want to consider first attending Fundamentals of Deep Learning for Computer Vision.

What you will learn

You will learn how to train a network using TensorFlow and the MSCOCO dataset to generate captions from images and video by:

  • Implementing deep learning workflows like image segmentation and text generation.
  • Comparing and contrasting data types, workflows and frameworks.
  • Combining computer vision and natural language processing.

Upon completion, you will be able to solve deep learning problems that require multiple types of data inputs.

How the course is conducted

The course focuses on being able to use the techniques and offers hands-on training under expert guidance. You can ask about everything from how to start to how to move on if you are stuck. And the best part is that the next day you will be able to continue using deep learning back at work.

Hardware and/or installation requirements

A laptop with Google Chrome, Firefox or Safari (no special hardware like GPUs required).
Create an account on the DLI Platform (instructions will be e-mailed a few days before the course).

What do former participants say?

The course provides an insight into what artificial intelligence and deep learning are. Both in terms of how complicated and how uncomplicated the area is. Now I can have a better dialogue with both colleagues and the companies we collaborate with in this area. It’s a good way to get a feel of it. As for an introduction, it has been really good and tool-based.

Mikael Knudsen, Development Manager, Aarhus University School of Engineering, Electrical and Computer Engineering

8 hours insight and hands-on training with deep learning


9:00 Deep Learning Demystified and Applied Deep Learning (lecture)
9:45 Break
10:00 Image Segmentation with TensorFlow (lab*)
12:00 Lunch break (lunch not included)
13:00 Word Generation with TensorFlow (lab*)
15:00 Break
15:15 Image and Video captioning by Combining CNNs and RNNs  (lab*)
17:15 Q&A and closing comments

Skills required

This workshop is meant for developers, data scientists and researchers with a basic understanding of deep learning concepts.

Prerequisites: Basic programming skills (C/C++, Python or similar)
Duration: 8 hours
Framework: TensorFlow
Language: English
*Please note that attendees MUST bring their own laptops.

If you have any questions, please send an e-mail to


We also offer a course in Computer Vision.


This workshop is brought to you by:

19 September from 09:00 to 17:30 May, date to be confirmed
Meeting room Nygaard-395, 3rd floor in the Nygaard building, Helsingforsgade 12, 8200 Aarhus N
Free of charge. To reserve your seat, you MUST register with a valid university e-mail address. So you must be either a student or employed at a university to attend.

Organised by NVIDIA Deep Learning Institute and the Alexandra Institute

Head of Visual Computing Lab, PhD
+45 22 59 77 38
Åbogade 34, 8200 Aarhus N
Nygaard building, 3rd floor room 305

Meet the instructors

Henrik Pedersen and Mads Thoudahl are our deep learning experts. They know all about the technologies and have helped many businesses use deep learning.

Henrik Pedersen is a Senior Computer Vision Engineer, PhD, at the Alexandra Institute and we have chosen him as educator. Over his career, Henrik has been in various academic positions, covering research and teaching in computer vision and deep learning. His interests lie in exploring deep learning techniques for object detection and recognition using photorealistic, synthetic images for training. Henrik is an experienced educator and has played a key role in building up the vibrant deep learning community at the Alexandra Institute.

Mads Thoudahl specialises in machine learning and has a Master’s degree in computer science from the University of Copenhagen. He has a broad-based profile that spans the field between data analysis, modelling, simulation and visualisation, including cluster architecture and parallel programming in simulation of physical systems.