To practice with the course subjects, you are offered both practical assignments (which are graded, if submitted before the given deadlines), and self-assessment assignments (not graded). If you need any help or feedback, try your fellow students, e.g. in the discussion forum on Blackboard, or ask the instructor during the lecture breaks.

Practical assignments

The practical assignments consist of a number of questions and exercises. Some can be answered using only the theory discussed in class; others are to be answered using one of the freely available Bayesian network software tools (see below). Sometimes you are expected to search for your own information (online).

Deadlines and submission procedure for practical assignments

Part A should not be submitted, but is necessary for completing the other parts; do yourself a favour by nonetheless sticking to the given deadline. For each of the other parts you should hand in the associated question-answer form on paper, either during class or through the pigeon hole of Silja Renooij (Coffee room, BBG 513 NB currently the coffee room is being redecorated; pigeon holes can be found just outside in the hallway). Part E is a BONUS modelling assignment; its deadline is relevant only for those interested.
Deadlines are (note the times!):

These deadlines will be strictly enforced! Note that e-mail submissions are not acceptable!

Additional sources for practical assignments

For your convenience, the following additional sources are available:

Software for practical assignments

Numerous software packages have been developed for constructing and reasoning with Bayesian networks; most of them have a free downloadable (demo-) version. Install the one of your choice for the practical assignment. (SamIam or GeNIe are recommended, or if you prefer a commercial product: Hugin-Lite or Netica.)

Note that most software packages allow a choice between inference algorithms. Be sure to select an exact inference algorithm (e.g. Lauritzen/Spiegelhalter, Jensen, Hugin, Shenoy/Shafer, Pearl, Variable elimination) and not an approximate one (e.g. (Loopy) belief propagation, sampling, Monte Carlo simulation)!

The software may also help you to gain more insight in inference in (Chapter 4) and the construction of (Chapter 5) Bayesian networks.

The following two pages present an overview of existing software packages: Specific packages are listed here:

Self-assessment exercises

The syllabus contains various exercises for the subjects treated in the course, and provides hints or answers to most of them. For each lecture, the relevant exercises are listed in the class schedule. In addition, the studymanual lists questions per syllabus chapter to guide your selfstudies.

You are advised to make the exercises and try to answer the questions. Doing so will form a good preparation for the written test and allows you to assess your own advancement during the course.

The majority of the exercises in the syllabus are former exam questions and therefore representative of what you can expect for the written test. Examples of actual previous tests:

Further examples are available through A-Eskwadraat. Note that all exams include a question about Pearl's algorithm, so be sure to practice that!