Loading Events
Sep 11

Deep Learning for Computer Vision

By EuroCC Austria
By EIT Manufacturing CLC East
By Vienna Scientific Cluster

Event Details

Level: intermediate

In this online course, participants will learn all about the basic concepts of neural networks, which have become widely applicable since the increase in available compute power. This includes activation functions, loss functions and optimisers. However, we will not just cover fully connected dense layers, but also work with convolutional layers, pooling layers, and dropout layers amongst others.

Since it is not necessary to train a model all by oneself, we will be looking into transfer learning, where we use pre-trained models and adapt them to our problem. Other than that, we will also talk about segmentation and object tracking and about what else can be done in deep learning (DL), apart from computer vision.

On the last day of this online training, we will introduce VSC-5, Austria’s fastest supercomputer, with all its capabilities. Should participants also want to train their models on VSC-5, Austria’s fastest supercomputer, they have to provide us with a valid mobile phone number to get past the 2-factor authentication.

This training is ideal for:

  • Professionals from all engineering disciplines with some programming experience
  • Professionals in QM and machine maintenance with programming experience

At the end of the online training, participants will be able to:

  • Understand the mathematics behind a neural network
  • Train your own neural network for different problems
  • Improve the performance with different architectures
  • Use existing models to cut training time and improve the outcome


1. Overview Deep Learning

Participants learn what Deep Learning is and which different forms there are and what the typical use-cases are.

2. Performance Metrics

Participants get to know how the performance of a neural network can be measured and what needs to be taken into account.

3. Basic Neural Networks

Participants will build their first neural networks with fully connected, dense layers to set a benchmark for further improvements. They will learn all about tensors, activation functions, loss functions and optimisers – in short, all about the mathematics behind neural networks.

4. Convolutional Layers

These are the backbone of computer vision. Participants will learn how and why they work and how to integrate them into a neural network.

5. Pooling and Dropout Layers

The complexity of a neural network often becomes unnecessarily large, leading to slow training and risk of overfitting. Pooling and dropout layers are some of the ways to alleviate this issue.

6. Different Architectures

A lot in deep learning is based on trial and error. Countless different architectures of neural networks have already been built by researchers around the world. We will have a look at some of the best performing ones and will try to adapt them to our problem.

7. Transfer Learning

Lack of data is one of the biggest challenges in building a well performing model for computer vision. Luckily, there are a lot of models that have already been trained on a vast amount of data. We will try to adapt theses fully trained models to meet our goals. This is called transfer learning.

8. Finetuning

Once we have leveraged the power of pre-trained models, we can finetune some hyperparameters to increase performance.

9. Segmentation

A major challenge in computer vision, is to not just classify a perfectly photographed object, but to detect it in the wider frame of a picture. This is called segmentation.

10. Working on a Supercomputer

There are many freely available computing resources out there. VSC-5 is Austria’s fastest supercomputer. It is not just a machine used by academia, but can also be utilized by SMEs. During the course we will have a look at how this can be done.

11. Outlook

In this final topic participants get a glimpse of what else can be done with deep learning. We are going to talk about RNNs, GANs and more media present topics such as ChatGPT.

Course format

The training will be held online on 11, 12, 13 September from 10:00 – 16:00 CEST with a 1-hour break at 12:00. The participation links will be provided after the purchase and before the training.


  • The participants are expected to have at least basic programming skills in Python.
  • The programming language of choice is Python with libraries such as Numpy, Pandas, Scikit-Learn, Matplotlib, Tensorflow and Keras.
  • The content is delivered with Jupyter notebooks on Google Colab, so participants should have a Google account in order to be able to participate fully.


Full price for the course with course documentation: € 360,00 (including VAT)


Upon completion of the online training, participants will receive a certificate of attendance.


Simeon Harrison (EuroCC Austria and VSC Research Center, TU Wien)


Rosina Preis (Competence and Knowledge Manager for EU Projects CLC East)

Simeon Harrison (Trainer and Coordinator Training for Industries, EuroCC Austria and VSC)

The When

September 11, 2023 | 10:00 am
September 13, 2023 | 4:00 pm

The Where


The Who

Hosted by EuroCC Austria

Publish Your Startup Events

The majority of the events listed on our site are community-generated. We invite you to add relevant events, whether ones you or your company hosts, or ones you simply wish to expose to our community. Publishing is quick and free!

Never miss an event

Join our newsletter and be the first to know of any new events taking place in your area. We will never spam or bother you, and 1-click opting-out takes 5 seconds!