Deep Learning Course, Automated Algorithm Design Section

Dr. Frank Hutter and Dr. Ilya Loshchilov

Deep learning has become a method of choice when dealing with complex Machine Learning tasks and datasets. This deep learning course jointly organized by four machine learning groups will help you to develop practical skills necessary to do deep learning research, e.g., applied in robotics and computer vision. Our section on Automated Algorithm Design will specifically focus on some crucial practical aspects of deep learning such as automated hyperparameter tuning and algorithm design. The course starts with some introductory lectures, continues with first some smaller and then larger projects. You will work in teams of 2-3 persons. There will be a final presentation of your project results at the end of the semester.


Course type: Lecture + Exercise
Time: Friday, 14:00-16:00. Beginning: Friday, October 21, 2016
Location: Kinohörsaal, Building 082
ECTS Credits: 4 or 6
Requirements: Bachelor or Master students. Fundamental programming skills in Python are recommended.
Contact persons: Ilya Loshchilov For questions, please email ilya@informatik.uni-freiburg.de
Remarks: The short lectures will be in English. The course is open to both Bachelor students (for their Bachelor project) and Master students (for their lab course). To reflect the larger experience of Master students, they must finish more involved project tasks to pass. The final project also provides 4 and 6 ECTS variants of the Bachelor project.
To register: This course is registered as "Automated Algorithm Design" by Frank Hutter.
Exercises: Exercise #3, Exercise #4