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 
To easily follow the course please make sure that you are familiar with the some basic math and python skills.
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 how to create a good poster you can check out the links that are provided in poster_guidelines.pdf
If you need free GPU resources, we might want to follow the instructions how to use google colab.
Examples for projects from previous versions the DL course: 2018, 2019 2020 2021 2022 2023
Open Datasets: papers with code, kaggle
Hints: Upload data to colab , keras with your own images
Fill in the Title and the Topic of your Projects until End of Week 5 here
We took inspiration (and sometimes slides / figures) from the following resources.
-
Probabilistic Deep Learning (DL-Book) Probabilistic Deep Learning. This book is written by us the tensorchiefs and covers the increasingly popular probabilistic approach to deep learning.
-
Deep Learning Book (DL-Book) http://www.deeplearningbook.org/. This is a quite comprehensive book which goes far beyond the scope of this course.
-
Convolutional Neural Networks for Visual Recognition http://cs231n.stanford.edu/, has additional material and youtube videos of the lectures. While the focus is on computer vision, it also treats other topics such as optimization, backpropagation and RNNs. Lecture notes can be found at http://cs231n.github.io/.
-
More TensorFlow examples can be found at dl_tutorial
-
Math concept videos at 3blue1brown
The course is split in 8 sessions, each 4 lectures long.
| Day | Date | Time |
|---|---|---|
| 1 | 20.02.2024 | 13:30-17:00 |
| 2 | 27.02.2024 | 13:30-17:00 |
| 3 | 05.03.2024 | 13:30-17:00 |
| 4 | 12.03.2024 | 13:30-17:00 |
| 5 | 19.03.2024 | 13:30-17:00 |
| 6 | 26.03.2024 | 13:30-17:00 |
| 7 | 02.04.2024 | 13:30-17:00 |
| 8 | 09.04.2024 | 13:30-17:00 |
-
Day 1
- Topics: Introduction, Fully Connected Networks (fcNN)
- Slides: 01_Introduction
- Additional Material:
- Exercises and Homework:
- Solutions to Exercises:
-
Day 2
- Topics: Looking back at fcNN, convolutional neural networks (CNN)
- Slides: 02_fcNN_CNN
- Additional Material:
- Exercises and Homework:
- Solutions to Exercises:
-
Day 3
- Topics: Convolutional neural networks (CNN)
- Slides: 03_CNN
- Exercises and Homework:
-
Day 4
- Topics: Details Backpropagation in DL, MaxLike-Principle
- Slides: 04_Training_Details
- Exercises and Homework:
- Backprop. linear regression eager 10_linreg_tensorflow, colab
- Optional Backprop static graph 11_backpropagation, colab
- Simple Max Like 12_maxlike, colab
-
Day 5
- Topics: Probabilistic Prediction Models
- Slides: 05_Probabilistic_Models
- Exercises and Homework:
-
Numerical Stability 12_numerical,stability, colab
-
Max Like MNIST 12b_mnist_loglike, colab
-
Linear Regression with Tensorflow Probability 13_linreg_with_tfp, colab
-
- Solutions to Exercises:
-
Day 6
- Topics: Flexible CPDs
- Slides: 06_flexible_CPDs
- Exercises and Homework:
- Poisson Regression with Tensorflow Probability 14_poisreg_with_tfp, colab
- Regression with Tensorflow Probability on Images 15_faces_regression, colab
- Pretrained Network 16_elephant_in_the_room, colab
- Solutions to Exercises:
-
Day 7
- Topics: Ensembling and Bayes
- Slides: 07_ensembling_bayes
- Exercises and Homework:
- Classification with Ensembles and Bayes 17_cifar10_ensemble_bayes, colab
- Bayesian Model for Coin Toss 18_bayesian_coin_toss, colab
-
Day 8
- Topics: Bayes (continued), Projects
- Slides: 08_bayes_2024