Bayes Networks

General Information

This page contains information about the lecture "Bayes Networks" (in German "Bayes-Netze") that is held in winter term 2019/2020 by Prof. Dr. Rudolf Kruse. This page is updated during the course.


Announcement

 No exercises on 22.1.20, they are moved to 29.1.20

There will be no lecture on 30.1.2020. 

 The written exam will takes place at 11.02.20 , 11h-13h, room HS 5


Topics

  • Representation of uncertain information
  • Bayesian networks
  • Markov networks
  • Evidence propagation in probabilistic networks
  • Learning of probabilistic networks
  • Revision of probabilistic networks
  • Causal networks
  • Decision Graphs
  • Hidden Markov Models

 


Schedule and Rooms

  WeekdayTimeRoomBegin  
Lecture Thursday 11.15-12.45 G29-307 17.10.2019 english
Exercise    Wednesday 13.15-14.45 G29-K037 23.10.2019 english
Exercise Wednesday 15.15-16.45 G29-E037 23.10.2019 english

Every student who wants to participate in the exercise must register her-/himself via the FIN Registration Service for the exercise. If you have any trouble with verifying the SSL certificate Jens Elkner could help you. While doing the registration, we kindly ask you to give an e-mail address of which incoming e-mail you check regularly.

 


Lecturers

If you have questions regarding the lecture or exercise, please contact (via e-mail if possible) one of the persons named below.

 


Conditions for Certificates (Scheine) and Exams

Certificate (Übungsschein): There are assignment sheets published every week. Assignments the solutions of which you want to present in the next exercise lecture have to be ticked beforehand on a votation sheet that is handed our prior to every exercise lecture. If ticked, you may be asked to present your solution in front of class. The solutions need not necessarily be completely correct, however, it should become obvious that you treated the assignment thoroughly. You are granted the certificate (Schein), if (and only if) you

  • ticked at least two thirds of the assignments,
  • presented at least two times a solution during the exercise, and
  • pass the exam

Exam: If you intend to finish the course with an exam, your are required to meet the certificate conditions. There will be a written exam after the curse. You can use your own not graphical and not programmable calculator.

 


Prerequisites

You should have background knowledge on fundamentals of computer science such as algorithms, data structures etc. Also, insights into probability theory are highly recommended.

 


Slides

Note that the script may be subject to change (which will be stated in the news section above) during the course, i.e. page numbers may change.

 

# Topic    Files   Announcements and Changelog
  Administration PDF The lecture will start on October 17th, the first lecture will be held in G29-307
1 Rule-Based Systems PDF Updated on 17.10. added two business slides of up-to-date business cases
 2 Probability Foundations PDF Updated on 08.11., reformulations of some texts
3 Decomposition PDF  
4 Separation Concepts PDF  
5 Probabilistic Graphical Models PDF  Appended a few slides
6  Inference in Belief Trees PDF  
7  Clique Tree Representations PDF  removed a comma of slide 280
8  Propagation in Clique Trees PDF  
9  Manual Building of Bayes Networks PDF  
10  Building Bayes Networks: Parameter Learning PDF  
11  Learning Decision Trees PDF  
12  Building Bayes Networks: Structure Learning PDF  
13  Revision PDF  
14  Decision Graphs PDF  not relevant for exam
15  Hidden Markov Models PDF  not relevant for exam
16  Causal Networks PDF  not relevant for exam, will be updated

 


Assignment Sheets

The assignment sheets will be published weekly at this location.

Due dates may be adjusted according to the lectures progress.

 

 

ID Topic       Due Date      Exercise Sheet
      Wednesday   
1  Combinatorics, Certainty Factors, Probabilities 23.10. PDF
2  Conditional Probabilities, Independencies 06.11. PDF
3  Separation Concepts 13.11. PDF
4  Decomposition 20.11. PDF
5  Semi-Graphoid and Graphoid Axioms 04.12. PDF
6  Bayesian Networks and Propagation 04.12. PDF
7  Propagation and Construction of Clique Trees 11.12. PDF
8  Clique Tree Propagation 18.12. PDF
9  Learning from Data 08.01.  PDF
10  Properties of Undirected Graphs / Exam Prep 15.01. PDF

 

 


Additional Material

Feel free to check out the following supplementary material that augment the lecture and exercise.

 


Software

Here you find links to programs with for learning and using Bayesian networks.

 


References

  • Computational Intelligence - A Methodological Introduction
    Kruse, R., Borgelt, C., Braune, C., Mostaghim, S., Steinbrecher, M.
    Springer-Verlag London 2016
  • Graphical Models - Representations for Learning, Reasoning and Data Mining, 2nd Edition.
    C. Borgelt, M. Steinbrecher und R. Kruse.
    J. Wiley & Sons, Chichester, United Kingdom 2009
  • Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis
    Uffe B. Kjærulff, Anders L. Madsen
    Springer Science+Business Media New York 2013

 


Links

Last Modification: 22.01.2020 - Contact Person: Webmaster