Winter Semester 2023

Foundations of Deep Learning

Course type: Lecture + Exercise
Time: Lecture: Monday, 14:15 - 15:45; Optional exercises: Friday, 10:00 - 12:00
Location: The course will be in-person:
- Weekly flipped classroom sessions will be held on Monday in HS 00 026 µ - SAAL (G.-Köhler-Allee 101)
- Optional exercise sessions will take place on Friday in HS 00 006 (G.-Köhler-Allee 082)
Organizers: Frank Hutter , Abhinav Valada , André Biedenkapp , Mahmoud Safari , Rhea Sukthanker
Web page: ILIAS (please make sure to also register for all elements of this course module in HISinOne: Lecture + Exercise )

Foundations of Deep Learning

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.

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 (Mondays 14:15 - 15:45)
  • an attendance optional exercise session (Fridays)

At the end, there will be a written exam (likely an 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.

Course Material: 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 and with our tutors during weekly attendance optional in-class exercise sessions.

Exam: The exam will likely be a test you complete on ILIAS. In-person presence may be required (TBA).

Course Schedule

The following are the dates for the flipped classroom sessions:

16.10.23 - Kickoff: Info Course Organisation / Team Formation
23.10.23 - ChatGPT Panel Discussion
30.10.23 - Week 1: Intro to Deep Learning
06.11.23 - Week 2: From Logistic Regression to MLPs
13.11.23 - Week 3: Backpropagation
20.11.23 - Week 4: Optimization
27.11.23 - Week 5: Regularization
04.12.23 - Week 6: Convolutional Neural Networks (CNNs)
11.12.23 - Week 7: Recurrent Neural Networks (RNNs)
18.12.23 - Week 8: Practical Methodology
08.01.24 - Week 9: Attention & Transformers
15.01.24 - Week 10: Auto - Encoders, Variational Auto - Encoders, GANs
22.01.24 - Week 11: Uncertainty in Deep Learning
29.01.24 - Week 12: AutoML for DL
05.02.24 - Round - up / Exam Q & A

In the first session (on 16.10.22) 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 will be held on 05.02.23.


If you have a question, please post it in the ILIAS forum (so everyone can benefit from the answer).

Lab Course Automated Machine Learning

Course Type: Lab Course
Time & Location: 24.11.23; MST Pool, Building 74, 14:00-15:00 Introduction to Lab
27.11.23 - 30.11.23; MST Pool, Building 74, 09:00-17:30 participation in the AutoML Fall School
During the semester : A supervised projected related to AutoML;
Themes relating to ensembling and capabilities of AutoML systems
07.02.24; Room 13, Building 74, 14:00-16:00 : Poster presentation
Organizers: Eddie Bergman , Lennart Purucker , Frank Hutter
Web Page: HISinOne , Local Page