# Teaching

### Summer term 2022

Practical course on applying deep learning for image generation.

Alexander Ecker and Timo Lüddecke

Introduction to Machine Learning

Alexander Ecker

### Winter term 2021/2022

Seminar where recent deep learning papers are presented and discussed.

Alexander Ecker, Laura Pede, Richard Vogg and Timo Lüddecke

Introduction to Deep Learning with a focus on image recognition

Alexander Ecker, Max Burg, Laura Pede

### Winter term 2021/2022

Seminar where recent deep learning papers are presented and discussed.

Alexander Ecker, Laura Pede, Richard Vogg and Timo Lüddecke

Introduction to Deep Learning with a focus on image recognition

Alexander Ecker, Max Burg, Laura Pede

### Summer term 2021

Introduction to Machine Learning

Alexander Ecker

# Bachelor’s and Master’s theses

### General requirements

We expect prospective students to have substantial knowledge in machine learning, its mathematical foundations and Python programming. We therefore strongly recommend that students interested in doing their thesis in our lab should take our courses on Machine Learning, Deep Learning and took the Fachpraktikum Data Science. Exceptions are possible if well motivated.

Further recommended lectures are:

- B.Inf.1231: Infrastruktures for Data Science
- M.WIWI-QMW.0002: Advanced Statistical Inference (Likelihood & Bayes)
- B.Inf.1206: Datenbanken
- B.Mat.1300: Numerische lineare Algebra
- B.Mat.2310: Optimierung

Please note, our thesis supervision capacity is limited and we receive more thesis inquiries than we are able supervise. Therefore, we have to select candidates. If you are interested, please write an email with the subject “Master’s thesis” or “Bachelor’s thesis” containing one to three sentences about what you would like to work on and your study record to Alexander Ecker.

We will get back to you within a few days. Otherwise, do not hesitate to remind us :).

## Thesis offers

Apply deep learning methods to track honey bees in video recordings

Supervisor: Alexander Ecker + Bardia Hejazi (MPI-DS)

Use self-supervised learning as pre-training in specific domains

Supervisor: Timo Lüddecke

Multi-task learning for visual quality control

Supervisor: Alexander Ecker (industry collaboration with Layer7 AI)

Building a unified framework for object-centric representation learning models.

Supervisor: Marissa Weis

Panoptic segmentation of microscopic images of neuronal cell cultures

Supervisor: Rickard Sjögren (Sartorius AG), Fabian Sinz, Alexander Ecker

Apply deep learning methods to segment 3D point clouds

Supervisor: Alexander Ecker + Dominik Seidel

Learning generic features for remote sensing data, specifically forests

Supervisor: Timo Lüddecke and Nils Nölke

Apply techniques for novel view synthesis with contrastive self-supervised learning

Supervisor: Timo Lüddecke