Lecture: Machine Learning for Computer Vision (IN2357) (2h + 2h, 5ECTS)
SS 2020, TU München
Announcements
This semester, the lecture will be given partly online. This means that several topics will be made available from an earlier recording of the lecture. A detailed lecture plan will be given on this page.
You can use our library for the programming exercises: mlcv-tutorial
April, 24th: Link for piazza: https://piazza.com/tum.de/spring2020/in2357
FAQ
1. Attendance to the lecture is open for all.
2. If your pursuing degree is not in Computer Science and you want to take the exam, you should ask the administrative staff responsible for your degree whether that is possible (it most probably is).
3. If you are a LMU student and you want to take the exam, you should ask the administrative staff responsible for your degree whether that is possible (it most probably is).
4. There is no way to get extra points for your final grade, such as bonus exercises, etc.
Lecture
Location:
For now, the lecture will be online. Later in the semester, we will be in
5620.01.102 Interims Hörsaal 2
Date: Fridays
Time: 12.00 - 14.00
Lecturer: PD Dr. habil. Rudolph Triebel
SWS: 2
Tutorial
Location:
For now online, later in 620.01.102 Interims Hörsaal 2
Date: Thursdays, starting from May 7th
Time: 16.00 - 18.00
Lecturer: John Chiotellis, Maximilian Denninger, Martin Sundermeyer, Maximilian Durner
SWS: 2
Contents
In this lecture, the students will be introduced into the most frequently used machine learning methods in computer vision and robotics applications. The major aim of the lecture is to obtain a broad overview of existing methods, and to understand their motivations and main ideas in the context of computer vision and pattern recognition.
For material from previous semesters, please refer to, e.g.: WS2017
Prerequisites
Linear Algebra, Calculus and Probability Theory are essential building blocks to this course. The homework exercises do not have to be handed in. Solutions for the programming exercises will be provided in Python .
Tentative Schedule
Topic | Notes | Lecture Date | Tutorial Dates |
---|---|---|---|
Introduction / Probabilistic Reasoning | No lecture! Please find introductory slides here | 24.04. | 07.05. |
Regression | Online lecture. See video here. | 08.05. | 14.05. |
Graphical Models | Online lecture. See video here . | 15.05. | 21.05. |
Boosting | Online lecture. See video here . Note that there is a "-" sign missing in the derivation on the board. This is a mistake which is corrected later in the video. | 22.05. | 28.05. |
Kernel Methods | Online lecture. See video here . | 29.05. | 04.06. |
Gaussian Processes | Online lecture. See video here | 05.06. | 18.06. |
Metric Learning | 12.6 | 25.6. | Gaussian Mixture Models and EM (Clustering I) | 19.6. | 2.7 |
Clustering II | 26.6. | none | |
Deep Learning | 3.7. | 9.7. | |
Variational Inference I | 10.7. | 16.7. | |
Variational Inference II | 17.7. | 23.7. | Sampling Methods | 24.7. | none |