Sketch of the AlexNet deep neural network. A pivotal model in the history of deep learning.


Deep Learning (CAS machine intelligence, 2026)

This course in deep learning focuses on practical aspects of deep learning. We therefore provide jupyter notebooks (complete overview of all notebooks used in the course).

For doing the hands-on part we recommend to use google colab. You will need an internet connection and may also need a google account. See the instructions how to use google colab.

If you want to do work locally (e.g. in order to avoid needing an internet connection) you can install anaconda (details and installation instruction). Please note that we are not experts in anaconda and thus can only give limited support. Some examples may require extra effort to run smoothly in a custom installation.

To easily follow the course please make sure that you are familiar with some basic math and python skills.

Info for the projects

Your Leistungsnachweis for this course is a project. You can join together in small groups and choose a topic for your DL project. You should prepare a poster and a spotlight talk (5 minutes) which you will present on the last course day. To get some hints on how to create a good poster you can check out the links that are provided below under “Guidelines for designing a good poster”.

If you need free GPU resources, we again refer you to the instructions how to use google colab.

Examples for projects from previous versions the DL course: 2020 2021 2022 2023 2024

Open Datasets:

Hints:

Fill in the Title and the Topic of your Projects until End of Week 4 here

Other resources

We took inspiration (and sometimes slides / figures) from the following resources.

Dates & Topics

The course is split in 8 sessions, each 4 lectures long. Topics might be adapted during the course

Day Date Time Topic
1 05.05.2026 09:00-12:30 Introduction to Deep Learning & Keras, Backpropagation, first NNs
2 12.05.2026 09:00-12:30 Loss, Optimization, Regression, Classification
3 19.05.2026 09:00-12:30 Computer vision, CNN-archictecture
4 26.05.2026 09:00-12:30 DL in practice, pretrained (foundation) models
5 02.06.2026 09:00-12:30 Model evaluation, baselines, xAI, troubleshooting
6 09.06.2026 09:00-12:30 Generative Models, Transformer-architecture
7 16.06.2026 09:00-12:30 Vision Transformer
8 23.06.2026 09:00-12:30 Projects; AI fairness, responsibility

Provided Material

Day 1

TODO: Update links

Guidelines for designing a good poster

  • https://projects.ncsu.edu/project/posters/
  • https://projects.ncsu.edu/project/posters/60second.html
  • https://projects.ncsu.edu/project/posters/documents/QuickReferenceV4.pdf
  • https://www.slideshare.net/hmftj/scientific-posters-hmftj
  • http://betterposters.blogspot.ch/

This site uses Just the Docs, a documentation theme for Jekyll.