You are here: Home Teaching SS 2023 Laboratory: Deep Learning Lab

Laboratory: Deep Learning Lab

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

Welcome to the Deep Learning Lab a joint teaching effort of the Robotics (R)9, Robot Learning (RL)10, Neurorobotics (NR)11, Computer Vision (CV)11, and Machine Learning (ML)12 Labs. Deep learning has brought a revolution to AI research. A good understanding of the principles of deep networks and experience in training them has become one of the main assets for successful research and development of new technology in machine learning, computer vision, and robotics. In this course, we will teach students the practical knowledge that is needed to do research with deep learning, imitation learning, and reinforcement learning. This course consists of a mixture of lectures, exercises and group projects. The course is divided into five tracks that focus on different aspects of deep learning research. Please register for only one of the tracks mentioned below:


Track 1: Robotics (11LE13P-7302)
Track 2: Robot Learning (11LE13P-7321)
Track 3: Neurorobotics (11LE13P-7320)
Track 4: Computer Vision (11LE13P-7305)
Track 5: Automated Machine Learning (11LE13P-7312)

Please fill in this form with your information if you enroll in this course.



Lecture/Exercises: Wednesday, 16.00 c.t. -18.00 (Beginning Apr 19, 2023)
Room: Building 082, HS00-006.

Requirements: Fundamental programming skills in Python. Basic knowledge of deep learning, equivalent with having passed the Fundamentals of Deep Learning course. Some experience with the Linux toolchain (text editor, compiler, linker, debugger) is recommended.

Lectures, Assignments & Forum: ILIAS course

Remarks: The lab is organized as an in-person event.

Grades: Students need passing grades in all exercises. Final grades are 50% the average exercise grade and 50% the project grade.


    Phase I: Lectures
  • 19.04.2023: Course Overview
           Lecture 1: Deep Imitation and Reinforcement Learning
           Hand out Exercise 1
  • 26.04.2023: Meeting to solve open questions
  • 03.05.2023: Lecture 2: Deep Learning for Computer Vision
           Exercise 1 submission due
           Hand out Exercise 2
  • 10.05.2023: Meeting to solve open questions
  • 17.05.2023: Lecture 3: Automated Machine Learning
           Exercise 2 submission due
           Hand out Exercise 3

  • Phase II: Project
  • 24.05.2023: Meeting to solve open questions
           Presentation of topics for final project

    Please fill this form with your project selection.
  • 04.06.2023: Final project selection due
  • 07.06.2023: Project progress discussion
           Final project distribution announcement
           Exercise 3 submission due
  • 14.06.2023: Project milestone 1
  • 21.06.2023: Project progress discussion
  • 28.06.2023: Project milestone 2
  • 05.07.2023: Project progress discussion
  • 12.07.2023: Project milestone 3
  • 19.07.2023: Project progress discussion
  • 26.07.2023: Submission Final Project (Code + Poster/Presentation)
  • 01.08.2023: Poster presentations



Support for this course was generously provided by the Google Cloud Platform Education Grant.