Winter Semester 2022/2023, TU München

Organizers: Dr. Vladimir Golkov, Prof. Dr. Daniel Cremers

Preliminary meeting (not obligatory): 12 July 2022, 3pm online: https://bbb.in.tum.de/vla-493-ke7
Slides from an earlier semester's preliminary meeting are available here.

Good understanding of multiple top scientific papers. Good programming skills. Passion for complex problems. Passion for mathematics, good skills. Knowledge of array programming, Python, a deep learning framework (e.g. PyTorch, JAX, TensorFlow). Good SOFT SKILLS are absolutely necessary: take responsibility, be proactive, identify what is unclear, ask the tutor precisely and without hesitation, communicate proactively.

If you fulfill the aforementioned prerequisites, please send an email to create-dl[at]vision.in.tum.de or dlpractice[at]vision.in.tum.de (not both! one email is enough) with sufficient info about yourself (learning goals, code you wrote in any programming languages, all grade transcripts (small file size but don't hide PDF files inside ZIP files), details related to the aforementioned prerequisites such as a description of your programming experience) until 1 August 2022.

Details about the matching system can be found here and here.

If you ask for a spot after the matching phase, but do not hear from us soon, it means that we cannot offer you a spot.

Using deep learning to solve real problems often requires the creation of novel appropriate deep learning methods, rather than just out-of-the-box usage of existing architectures. In this practical course, students will choose real open problems and learn how to analyze them, how to identify the requirements that a deep learning method should fulfill, and how to create novel deep learning methods that fulfill these requirements.

Some of the projects that can be chosen also include the analysis of design principles of existing methods, and subsequent usage of these design principles to create new methods.

If you want to propose an own project instead of choosing from the projects that we will offer, please discuss with us before 26 July 2022. Use the email subject "PROJECT PROPOSAL" and the aforementioned email address.

The students will work individually and in groups on practical deep learning projects. At the end of the project, each student or group will present their project with a following Q&A session. There will be no additional written or oral exam. Both the theoretical and practical part of the project will be considered in the final grading.

The students will receive recordings of introductory lectures as early as they want.

Lecture 1: Machine Learning; Artificial Neural Networks; Convolutional Neural Networks; Q&A about Deep Learning
Lecture 2: Recap; Network Architecture Design; Q&A about Deep Learning
Lecture 3: Recap; Network Training; Understanding and Visualizing; Evaluating; Q&A about Deep Learning

Note: ECTS credits are the measure of workload. So-called semester weekly hours (Semesterwochenstunden, SWS) are NOT a measure of project work time, but merely of classroom time. You will receive remote access to GPUs and are free to work remotely.

• NumPy Advanced Array Indexing
• Goodfellow, Bengio, Courville: Deep Learning
• Christopher M. Bishop. "​Pattern Recognition and Machine Learning",​ Springer, 2006. (Skim the Chapters 1, 2, 5.)
• Ng: Machine Learning Yearning
• Good current papers