SEDS 533
Probabilistic Reasoning
Graphical Probability Models. Bayesian Reasoning. Bayesian Networks. Learning in Bayesian Networks. Knowledge Engineering. Temporal Models. Inference in Dynamic Bayesian Networks. Markov Decision Processes.
Course Objectives
The challenges of modeling and reasoning under uncertainty is defined and solution approaches based on probabilistic reasoning are discussed in this course.
Recommended or Required Reading
Learning Bayesian Networks; Richard E. Neapolitan, Prentice Hall, 2003. ,Bayesian Artificial Intelligence; Kevin B. Korb, Ann E. Nicholson; Chapman & Hall/CRC, 2004. ,Probabilistic Reasoning in Intelligent Systems (2nd Edition); Judea Pearl; Morgan Kaufmann Publishers Inc., 1988.
Learning Outcomes
1. Teaching the concept of uncertainty
2. To teach graphical probabilistic models
3. Being able to understand reasoning and learning in Bayesian networks
4. Being able to design Bayesian network applications
| Week | Topics |
|---|---|
| 1 | Introduction |
| 2 | Graphical Probability Models |
| 3 | Representing Knowledge in an Uncertain World |
| 4 | Bayesian Reasoning |
| 5 | Inference in Bayesian Networks |
| 6 | Midterm |
| 7 | Learning in Bayesian Networks |
| 8 | Knowledge Engineering |
| 9 | Bayesian Network Applications |
| 10 | Temporal Models |
| 11 | Inference in Dynamic Bayesian Networks |
| 12 | Markov Decision Processes |
| 13 | Partially Observable Markov Decision Processes |
| 14 | Project Presentations |
Grading
Midterm: 40%
Homework: 10%
Final: 50%