This practical course will be held during the semester!

Please direct ALL questions regarding this practical course at mlpractice[at]vision.in.tum.de

Lecturer: Dr. Rudolph Triebel

Tutors: Philip Häusser, Lingni Ma, John Chiotellis, Caner Hazirbas, Vladimir Golkov

In this course, we will develop and implement machine learning algorithms for concrete applications in the field of computer vision. The main purpose of this course is to gain practical experience with the most common machine learning methods and to learn about their benefits and drawbacks when applied to concrete, relevant problems. The main focus will be on supervised learning methods for classification, such as Support Vector Machines, Boosting methods, Gaussian Process Classifiers and tree-based classifiers, as well as deep learning methods (e.g. deep convolutional neural networks) for representation learning.

Preliminary meeting will take place on 26th January 2016, Tuesday between 10:30am and 11:30am in room 02.05.014.

We have more than 50 students interested in this lab course. We wish best of luck to all candidates in the matching system. Thank you all for your interests!

Slides of the pre-meeting can be found here.

The course registration is done via the matching system. Please only register on TUMOnline if you are assigned the course.

Requirements: Knowledge in basic mathematics, in particular statistics and linear algebra. Furthermore, basic programming skills are required.

Number of participants: max. 20

Project registration is now open. Please register before April 28, 2016, 12:00 a.m. The project assignment will be announced by May 02, 2016.

The list of projects can be found here. Please choose 3 projects and rank them according to your preferences. Optionally, you can find your partner and specify them in your preferences. If not, we will form the groups by project preferences. One group can be of two or maximum three students. Register by mlpractice[at]vision.in.tum.de.

The course will start on 12th April 2016. In the first three weeks, there will be lectures and exercise sheets handed out every week, containing practical/theoretical problems. After that, the students will work in groups on practical machine learning problems in computer vision. Each group consists of 2-3 students, and will be supervised by one of the lecturer/tutors. During the remaining of the semester, the group meet weekly with their supervisor to discuss the project progress. At the end of the semester, each group will present their project with a following Q&A section. There will be no additional written or oral exam. Both theoretical and practical part will be considered in the final grading. The course schedule are detailed below.

• 12.04.2016 : Lecture 1, SVMs and tree-based classifiers. Slides 01 SVM background notes
• 19.04.2016 : Lecture 2, deep learning and convolutional neural networks. Slides 02
• 26.04.2016 : Lecture 3, GP classifiers and boosting methods. Introduction to projects.
• 02.05.2016 : Announce project assignment and project start.
• 15.07.2016 : Project result submission deadline.
• 19.07.2016 : Project presentation part 1. Room 02.07.023, 10.00 - 13.00
• 22.07.2016 : Project presentation part 1. Room 02.09.023, 13.00 - 16.00
• 03.08.2016 : Project presentation part 2. Room 02.09.023, 10.00 - 13.00

• Kevin Murphy. "Machine Learning: A Probabilistic Perspective", MIT Press, Cambridge, Massachusetts 2012,
• Christopher M. Bishop. "Pattern Recognition and Machine Learning", Springer, Berlin, New York, 2006.