Location: Room 02.09.023
Date: Friday, starting at 22nd April
Time: 9.15
Lecturer: PD Dr. habil. Rudolph Triebel
ECTS: 4
SWS: 3

Location: Room 02.09.023
Date: every second Friday, starting at 29th April
Time: 15.00
Lecturer: John Chiotellis

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.

Tentative Schedule:
- Introduction
- Regression
- Probabilistic Graphical Models
- Boosting
- Neural Networks and Deep Learning
- Kernel Methods
- Gaussian Processes
- Evaluation and Model Selection
- Sampling Methods
- Clustering

1. Introduction
2. Regression
3. Graphical Models
4. Neural Networks and CNNs
5. Hidden Markov Models
6. Boosting
7. Mixture Models and Expectation Maximization
8. Kernel Methods
9. Gaussian Processes
10. Variational Inference
11. Sampling Methods I
12. Sampling Methods II
13. Clustering

0. Linear Algebra Refresher
1. Linear Algebra and Probabilistic Reasoning
2. Regression and Probabilistic Graphical Models
3. Neural Networks and Hidden Markov Models
4. Boosting and Expectation-Maximization banknote_auth.zip fisher-iris.zip
5. Kernel methods - Gaussian Processes
6. Sampling methods and Variational Inference

To prepare for the exam you can be helped by studying the questions here.