Practical Course: Hands-on Deep Learning for Computer Vision and Biomedicine (10 ECTS)
Summer Semester 2021, TU München
This is the summer semester 2021 course. For the winter semester 2021/2022 course, see here.
Please send applications (including learning goals, programming skills description, code, grade transcripts - see preliminary meeting slides) to dlpractice[at]vision.in.tum.de
Organizers: Vladimir Golkov, Prof. Dr. Daniel Cremers
Preliminary meeting (not obligatory): 1 February 2021 at 4pm online: https://bbb.in.tum.de/vla-493-ke7
Slides from last semester's preliminary meeting are available here.
Sending an email to dlpractice[at]vision.in.tum.de with sufficient info about yourself (learning goals, programming skills description, code, all grade transcripts) within the next few days is crucial for matching success. 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.
Course Description
In this course, we will develop 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 instead of choosing from the projects that we will offer, please discuss with us before 16 February 2021.
Prerequisites
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.
Knowledge of deep learning is recommended/required. Knowledge of biomedicine is NOT required and can be acquired during this practical course. However, the requirements listed above (e.g. good programming skills, soft 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 strategically is an important rule of the practical course. Almost all difficulties experienced by students are due to not following these rules.
Course Structure
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 and individually on practical deep learning projects. At the end of the project, 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.
Course Schedule
There will be three lectures in the beginning of the semester.
Time: Thursdays 2-4pm
Online link (BBB): see email
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.
Literature
- Christopher M. Bishop. "Pattern Recognition and Machine Learning", Springer, 2006. (Skim the Chapters 1, 2, 5.)
- Good current papers