Foundations of Deep Learning
Prof. Dr. Abhinav Valada, Dr. Steven Adriaensen
Co-Organizers:
Imen Mahdi, Mahmoud Safari, Johannes Hog
Deep learning is one of the fastest growing and most exciting fields. This course will provide you with a clear understanding of the fundamentals of deep learning including the foundations to neural network architectures and learning techniques, and everything in between.
| Time: | Tuesday, 14:15 – 15:45 First meeting on October 14th 2025. |
| Location: | Weekly flipped classroom sessions will be held on Tuesday at HS 00 026 (G.-Köhler-Allee 101). Optional exercise sessions will take place on Friday 10:15-11:45 at HS 00 006 (G.-Köhler-Allee 082) |
| Learning Platform: | ILIAS |
Course Overview
The course will be taught in English and will follow a flipped classroom approach.
Every week there will be:
- a video lecture
- an exercise sheet
- a flipped classroom session (Tuesday 14:15-15:45)
- an attendance optional exercise session (Fridays 10:15 - 11:45)
At the end, there will be a written exam (ILIAS test).
Exercises must be completed in groups and must be submitted a week (+ 1 day) after their release. Your submissions will be graded, and you will receive weekly feedback. Your final grade will be solely based on a written examination, however, a passing grade for the exercises is a prerequisite for passing the course.
All material will be made available in ILIAS and course participation will not require in-person presence. That being said, we offer ample opportunity for direct interaction with the professors during live Q & A sessions (HS 00 026, G.-Köhler-Allee 101) and with our tutors during weekly attendance optional in-class exercise sessions (HS 00-006, G.-Köhler-Allee 082).
Exam: The exam will be a test you complete on ILIAS. In-person presence is required.
Course Schedule
The following are the dates for the flipped classroom sessions:
14.10.25 – Kickoff: Info Course Organisation / Team Formation
21.10.25 – Week 1: Intro to Deep Learning
28.10.25 – Week 2: From Logistic Regression to MLPs
04.11.25 – Week 3: Backpropagation
11.11.25 – Week 4: Optimization
18.11.25 – Week 5: Regularization
25.11.25 – Week 6: Convolutional Neural Networks (CNNs)
02.12.25 – Week 7: Recurrent Neural Networks (RNNs)
09.12.25 – Week 8: Attention & Transformers
16.12.25 – Week 9: Practical Methodology
13.01.26 – Week 10: Auto - Encoders, Variational Auto - Encoders, GANs
30.01.26 – Week 11: Uncertainty in Deep Learning
27.01.26 – Week 12: AutoML for DL
03.02.26 – Round-up / Exam Q & A
The course material (lecture video, slides, exercise sheet) for “Week N” will be made available a week before the flipped classroom session for “Week N”. For example, the material for Week 1 will be available on 14.10.25, and solutions to the exercises must be submitted by 29.10.25 at 23:59.
In the first session (on 14.10.25), you will get additional information about the course and get the opportunity to ask general questions (and form groups!) While there is no need to prepare for this first session, we encourage you to already think about forming teams. The last flipped classroom session is held on 27.01.26.
Questions?
If you have a question, please post it in the ILIAS forum (so everyone can benefit from the answer). Alternatively, you can also email dl-orga-ws25@cs.uni-freiburg.de