
Detailed information 
Original study plan 
Master's programme Computer Science 2022W 
Objectives 
After this class, students will know and understand the basic concepts of a large and centrally important class of methods in modern Artificial Intelligence: Probabilistic Graphical Models, used for representing and reasoning about uncertain information and knowledge in complex realworld scenarios. All three aspects related to such models will be covered: model semantics, inference, and learning. Both basic concepts and specific algorithms will be taught, and all methods will be derived in a mathematically rigorous way. Students will understand how such models can be used for problem modeling and solving, and what their limitations are.

Subject 
Elementary Concepts:
 Probability Distributions
 Density Functions
 (conditional) independence
 Probabilistic Reasoning and Inference
Bayesian Networks:
 Representation
 Semantics
 Factorisation
Inference in Bayesian Networks:
Approximate Inference:
 Stochastic Sampling
 Markov Chain Monte Carlo (MCMC) Methods
Learning Bayesian Networks:
 Parameter Learning (maximum likelihood and Bayesian estimation)
 Structure Learning
 Generative vs. Discriminative Models
Special Types of Bayes Nets:
 Linear Gaussian Network Models
Modelling and Predicting Temporal Processes:
 Dynamic Bayes Networks
 Hidden Markov Models
 Kalman Filters
 Particle Filters
 Selected Applications of Probabilistic Graphical Models.

Criteria for evaluation 
Written exam at the end of the semester.

Methods 
Lecture series with written materials (presentation slides) provided regularly in electronic form.

Language 
English 
Study material 
Koller, Daphne, and Friedman, Nir (2009). Probabilistic Graphical Models. Principles and Techniques. Cambridge, MA: MIT Press.
Russell, Stuart J. and Norvig, P. (2010). Artificial Intelligence: A Modern Approach (3rd Edition). Upper Saddle River, NJ: Prentice Hall.

Changing subject? 
No 
