Practical Course: Hands-on Deep Learning for Computer Vision and Biomedicine (10 ECTS)
Winter Semester 2018/2019, TU München
Please direct all questions regarding this practical course to golkov[at]in.tum.de
Please send applications (including learning goals, programming skills description, code, grade transcripts - see preliminary meeting slides) to
Caution: information on TUMonline was not up to date. See below.
The preliminary meeting (not obligatory) took place on Friday, 29 June 2018 at noon (and at 13:00 for those who hadn't seen the updated time) in room 5620.01.101 (Interims-Hörsaal 1). A summary of the preliminary meeting (with important information) can be downloaded here.
Registration through the TUM Matching system is done from 29 June until 4 July 2018. Details can be found here. Sending us an email with sufficient info about yourself until 6 July is crucial for matching success. Students who did not register or did not get matched can contact us directly.
In this course, we will develop and implement deep learning algorithms for concrete applications in the field of computer vision and biomedicine. The main purpose of this course is to gain practical experience with deep learning, and to learn when, why and how to apply it to concrete, relevant problems. The topics will include:
- Machine learning, neural networks, deep learning
- Standard and advanced network architectures
- Tasks beyond supervised learning
- Design of architectures, choice of loss functions, tuning of hyperparameters.
The projects will be geared towards developing novel solutions for real open problems. Projects with various interesting problems and data representations will be offered.
If you want to propose an own project rather than choosing from the projects that we will offer, please discuss with us before 6 July.
Good programming skills. Eagerness to acquire and deepen knowledge about how to solve complex problems with machine learning. Passion for mathematics. The course will be focused on practical projects, thus previous knowledge of Python and array programming in NumPy (or in Matlab or similar) is desired. Having also good soft skills (or the willingness to acquire them quickly) and using them is a prerequisite.
Choice among many different projects will be offered. Some of these projects will be based on previous knowledge about machine learning, or computer vision, or biomedicine; but many other projects will NOT require such previous knowledge. The students will acquire knowledge during this practical course. However, the requirements listed above (e.g. good programming skills) are mandatory.
Important soft skills include communication skills, the ability to identify what is unclear, to figure out what questions need to be asked to clarify it, to formulate the questions clearly, and to ask the tutor without hesitation. Communicating well and regularly is an important rule of the practical course. Almost all difficulties experienced by students are due to not following these rules.
In the first three weeks, there will be lectures every week, focusing on theoretical and practical concepts related to deep learning. During the semester, the students will work in groups on practical deep learning projects. Each group will consist of about 1-2 students, and will be supervised by one of the tutors. At the end of the semester, each 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 course schedule is detailed below.
There will be three lectures in the beginning of the semester.
Time: Tuesdays 2-4pm
16 October: Machine Learning; Artificial Neural Networks; Network Training; Convolutional Neural Networks
23 October: Recap; Network Architecture Design; Understanding and Visualizing
30 October: Recap; Programming; Evaluating
6 November: 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.