Powered by Indico
v3.1
The ORIGINS Data Science Lab (ODSL) is organizing two block courses on data science topics.
The courses, as well as the tutorials, will take place online. The tutorials will be organised through breakout rooms, each assigned to a tutor.
The block courses follow the schedule:
The course itself, as well as one tutorial will be recorded, the other tutorials not. If you have any objections to this, please contact us directly. We will make the recordings of the lectures available online.
All exercises will be made available before the courses and the deadline to hand in the report is October 31.
They should be sent to: l.heinrich [AT] tum.de
Zoom link: https://tum-conf.zoom.us/j/65666587594 (Passcode: 578388)
Also, the recordings of the lectures and tutorial sessions will be made available.
For students successfully completing both Block Courses, 5 (TUM) or 3 (LMU) ECTS points will be awarded. Formally this is a TUM event, but LMU students can hand in their certificates and it will be recognised.
Successful completion means turning in solutions to assigned problems by the end of October and getting a passing grade. The Courses are:
Lecturer: Philipp Eller
This course is focusing on methods for data processing, optimization and machine learning. First we will learn the basics of data decorrelation, reduction and optimization algorithms. Based on these new skills, we dive into machine learning topics, such as clustering, classification and regression with tree based algorithms and neural networks. In the last part deep learning models and different architectures will be introduced and explained.
Lecturer: Dr. Philipp Eller (philipp.eller@tum.de)
Prerequisites: Linear Algebra, basic Analysis, a programming language of choice
Skills acquired: basic data transformations, knowledge in various optimization algorithms, k-means clustering, decision trees, simple neural networks
Example solutions for the warm-up exercises can now be found under https://github.com/philippeller/teaching
Lecturer: Prof. Lukas Heinrich
In this course we will build on top of the prior week and discuss deep learning in depth starting from a short review of the nature of machine learning followed by a broad overview over popular deep learning architectures combined with hands-on experience in training basic deep networks
Prerequisites: basic probability theory, statistics, a programming language of choice
Skills acquired: basic statistical learning theory, overview over popular classes of deep neural networks, i.e. discriminative (MLP, CNN, RNN) and generative models (GANs, VAE) , density estimation (Normalizing Flows), training strategies deep neural networks
It is possible to get a Certification or ECTS points for participation in the Block Courses:
To get a Certificate of Participation (for either one of the two blocks or both), you will need to turn in solutions to the exercises that will be assigned during the course (tutoring session exercises) and get a passing grade. The certification will be done on a course-by-course basis, and will state that you have successfully completed the Block Course in the respective topic. Please register for the course in advance so we can estimate how much work will be involved in the evaluation of the reports.
To get the 5 (TUM) or 3 (LMU) ECTS points, you will need to turn in solutions to all exercises for both Block Courses (tutoring + homework exercises) that will be offered this year. The grade for the course will be based on the two sets of exercises, and there will not be an additional exam. The deadline to hand in the report is October 31. Please register for the courses in advance so we can estimate how much work will be involved in the evaluation of the reports.
TUM Students: If you would like to receive credits please register for course PH2309
Participants who do not want a certificate or points are not required to turn in solutions, but are allowed to.