Machine Learning for Robotics and Computer Vision
SS 2013, TU München
Lecture
Location: Room 02.09.023
Date: Friday, starting at 26th April
Time: 9.15
Lecturer: Dr. Rudolph Triebel
ECTS: TBC
SWS: 3
Tutorial
Location: Room 02.09.023
Date: Friday, 3rd May, every other week
Time: 14.15
Lecturer: Jan Stühmer
The course will be held in English.
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. Also, in addition to the standard methods, the lecture will also cover some recent topics such as CRFs, Random Forests, and IVMs.
Schedule:
- Introduction
- Regression
- Probabilistic Graphical Models
- Boosting
- Kernel Methods
- Gaussian Processes
- Evaluation and Model Selection
- Sampling Methods
- Clustering
Lecture Slides
1. Introduction into Probabilistic Reasoning and Learning
2. Regression
3. Graphical Models I
4. Graphical Models II
5. Boosting
6. Kernel Methods
7. Gaussian Processes
8. Mixture Models and EM
9. Variational Inference
10. Sampling Methods
11. MCMC and Evaluation Methods
12. Clustering
Exercises
03.05.2013. Assignment sheet 1
24.05.2013 Assignment sheet 2 Code
07.06.2013 Assignment sheet 3 Code
05.07.2013 Assignment sheet 4 Code