Location: Room 02.13.010
Date: Friday
Time: 10.15 - 12.00
Lecturer: PD Dr. habil. Rudolph Triebel
ECTS: 4
SWS: 3

Location: Room 02.09.023
Date: every second Friday starting from 28.10.2016
Time: 14.00 - 16.00
Lecturer: John Chiotellis

There will be no more tutorials after January, 27th.

Location: 101, Interims Hörsaal 1 (5620.01.101)
Date: Friday, February 24th
Time: 16.00 - 17.30

No assisting material is allowed, like calculators, formula sheets, etc.
Please note that there will be no repeat exam, since the lecture is offered in every semester.

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
- Distance Metric Learning
- Boosting
- Neural Networks and Deep Learning
- Kernel Methods
- Gaussian Processes
- Evaluation and Model Selection
- Sampling Methods
- Clustering

1. and 2. Introduction and Probabilistic Reasoning
3. Regression
4. Kernel Methods and Gaussian Processes
5. Distance Metric Learning
6. k-means, EM and Spectral Clustering
7. Neural Networks and Deep Learning
8. Boosting and Bagging
9. Probabilistic Graphical Models
10. HMMs for Sequential Data
11. Repetition, Consolidation and Applications (mainly clustering and GPs)
12. Variational Inference I
13. Variational Inference II
14. Sampling Methods and MCMC
15. Clustering II with material from http://www.kamperh.com/notes/kamper_bayesgmm13.pdf
16. Online Learning

0. Linear Algebra Refresher Linear Algebra Exercises
1. Probabilistic Reasoning
2. Regression, Kernels, GPs train_data.txt
3. K-Means, EM, GMM clustering.zip
4. Deep Learning, Boosting banknote_auth.zip
5. Graphical Models, HMM
6. Sampling and Variational Inference