Winter Semester 2024/25, TU Munich

Organizers Felix Wimbauer, Prof. Dr. Daniel Cremers

E-Mail: felix.wimbauer@tum.de (Use subject [BDL])

Course page from previous years for reference: BDL SS23

• Kick-off meeting: October 14th 2024, 2pm-4pm, 02.09.023
• The slides from the preliminary meeting are now available. For your application, please fill out this form and follow the instructions from the slides.

Deep learning models nowadays provide state of the art results and set a new standard for many applications, such as speech recognition, computer vision. As standard supervised deep learning has become more and more established, there has been great interest in more specialised topics.

This course will be focusing on advanced deep learning techniques. The topics will include:

• Diffusion Models / Normalizing Flows
• DINO - Student-teacher models for self-supervised representation learning
• CLIP - Representation Learning for Text and Images
• Multimodal Language Models
• Segment Anything and Follow-Ups
• Bayesian Deep Learning Models
• Datasets and Dataset Curation
• many more

We will be discussing state-of-the-art research and open issues in the scientific community. We are also open to students proposing their own topics before the start of the seminar.

Participants should already have a good understanding of basic machine learning and deep learning concepts and models. Especially, they are required to have taken at least one machine learning related course such as:

• Introduction to Deep Learning
• Machine Learning
• Advanced Deep Learning for Computer Vision / Robotics
• Generative Models
• etc.

Participants should be able to take initiatives to plan and maintain a continuous workflow and communicate with tutors efficiently.

As many projects consider theoretical aspects of learning theory, a solid basis as well as interest for mathematics is highly recommended.

Prior experiences with machine learning projects are also a plus.

Note: it is crucial for interested applicants to also send us an e-mail (felix.wimbauer@tum.de) demonstrating their interest and fulfillment of prerequisites. The details will be explained during the pre-course meeting and available on the course website.

Places will be assigned through the TUM matching system (http://matching.in.tum.de).

This course is directed towards master students and will be held as a block seminar.

• Kick-off meeting: October 14th 2024, 2pm-4pm, 02.09.023
• Preliminary meeting: July 11th 2024, 10am-11am, online

• Deep Learning, Goodfellow, Bengio, Courville, 2016, http://www.deeplearningbook.org/
• Machine learning: a probabilistic perspective, Murphy, 2012
• The Elements of Statistical Learning, Hastie, Tibshirani, Friedman 2001
• Relevant papers will be announced during the course.