Markov models on graphs represent a model class widely applied in many areas of computer science, such as computer networks, data security, robotics and pattern recognition. The first part of the course covers inference and learning for Markov models on chains and trees. All these tasks including structure learning can be solved by efficient algorithms. The second part addresses graphical models on general graphs. Here on the contrary, practically all inference and learning tasks are NP-complete. The focus is therefore on efficient approximative algorithms.
18.01.12 Written exam is corrected
06.12.11 Exam date: Thursday, January 12, 9:15-10:45, room G205
15.11.11 Seminar on Wednesday 16.11. is moved to 9:15-10.45, G205
Prerequisites: Basics of probability theory, graphs and graph algorithms
Time and Location: lectures: Mon, 14:30, E-127, seminars: Wed, 16:15, E-128
Course format: (2/1)
Lectures: See
here for the syllabus
Seminars: Exercises/Assignments will be provided
here prior to every seminar. Students are expected to work on them and try to solve them before the seminar. Solutions will be discussed at the seminar.
Grading/Credits:
Textbooks and References:
Michail I. Schlesinger, Vaclav Hlavač, Ten Lectures on Statistical and Structural Pattern Recognition [
Schlesinger-TLPR2002]
Stan Z. Li, Markov Random Field Modeling in Image Analysis [
Li-MRFIA2009]
Daphne Koller, Nir Friedman, Probabilistic Graphical Models Principles and Techniques [
Koller-PGM2009]
Christopher M. Bishop, Pattern Recognition and Machine Learning (for additional reading) [
Bishop-PRML2006]
Gerhard Winkler, Image Analysis, Random Fields and Markov Chain Monte Carlo Methods: A Mathematical Introduction (for additional reading) [
Winkler-IARF2006]