Machine Learning for Robotics and Computer Vision
WS 2015/2016, TU München
Lecture
Location: Room 02.09.023
Date: Friday, starting at 16th October
Time: 9.15
Lecturer: PD Dr. habil. Rudolph Triebel
ECTS: 4
SWS: 3
Tutorial
Location: Room 02.09.023
Date: every second Friday, starting at 6th November
Time: 14.00
Lecturer: John Chiotellis
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.
Tentative Schedule:
- Introduction
- Regression
- Probabilistic Graphical Models
- Boosting
- Neural Networks and Deep Learning
- 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. Hidden Markov Models
6. Mixture Models and Expectation Maximization
7. Neural Networks and Deep Learning
8. Boosting
9. Kernel Methods
10. Gaussian Processes
11. Sampling Methods I
12. Sampling Methods II, Variational Inference
13. Expectation Propagation
14. Clustering
Homework
1. Probabilistic Reasoning and Regression
2. Graphical Models
3. HMMs, GMMs and Deep Learning
fisher-iris.zip
4. Boosting and Kernels
banknote_auth.zip
5. SVMs and Gaussian Processes
6. Sampling and Variational Inference
Exam Preparation
To prepare for the exam you can be helped by studying the questions here.