CSE 590ST - Statistical Methods in Computer Science - Spring 2004
 CSE Home About Us Search Contact Info

 Instructor: Pedro Domingos Office: Allen 648 Office hours: Wednesdays 3:00-3:50 and by appointment TA: Matt Richardson Office: Allen 216 Office hours: Mondays 3:00-3:50 and by appointment

Class meets:
Mondays and Wednesdays from 1:30 to 2:50 in MGH 231

Week 1: Chapter 2 of Koller & Friedman; review basic probability and statistics
Week 2: Chapters 3 and 4 of Koller & Friedman
Weeks 3 & 4: Chapters 7, 8, 9 and 10 of Koller & Friedman
Weeks 5 & 6: Chapter 15 of Koller & Friedman, Heckerman tutorial
Week 7: Section 20.3 of Russell & Norvig
Week 8: Chapter 5 of Koller and Friedman
Week 9: Chapter 15 of Russell & Norvig
Week 10: Chapters 16 and 17 of Russell & Norvig

## Lecture Notes

Week 1: Introduction, background
Weeks 5 & 6: Learning Bayesian networks
Week 7: The EM algorithm
Week 8: Markov networks
Week 9: Temporal models
Week 10: Decision theory, Markov decision processes

## Topics

The topics covered will have a non-null intersection with the following list:
• Bayesian networks
• Markov networks
• Markov chain Monte Carlo
• Belief propagation
• Mixture models
• Maximum likelihood and Bayesian estimation
• The EM algorithm
• Hidden Markov models
• Dynamic Bayesian networks
• Particle filters
• Relational models
• Decision theory
• Markov decision processes
• Information theory

## Evaluation

Class evaluation will be by means of four homeworks, each worth 15% of the final grade, and a final, worth 40%. The homeworks include programming. Homework assignments will be handed out on weeks 2, 4, 6 and 8, and will be due two weeks later. Late policy: penalty of 2 points (out of 15) per day, up to a maximum of one week.

Homework 1
Homework 2 (And here are the networks referenced in the homework: ab.bif, insurance.bif)
Homework 3 (And here are the files referenced in the homework: alarm.bif, atrain.names, atrain.data, atest.names, atest.data)
Homework 4

## Textbooks

• D. Koller & N. Friedman, Bayesian Networks and Beyond: Probabilistic Models for Learning and Reasoning, MIT Press. This book has not been published yet; copies of chapters will be handed out in class.
• S. Russell & P. Norvig, Artificial Intelligence: A Modern Approach (2nd ed.), Prentice Hall, 2003 (recommended).
• M. DeGroot & M. Schervish, Probability and Statistics (3rd ed.), Addison-Wesley, 2002 (recommended; 2nd ed. also OK).

## Anonymous Feedback

Comments can be sent to the instructor or TAs using this anonymous feedback form.

## Course Mailing List

To subscribe to the course mailing list, visit the mailing list home page. Alternatively, you can use the email interface to subscribe; send email to cse590st-request@cs with the word "help" in the subject to receive a list of email command options.

#### Mailing List Archive

 Department of Computer Science & Engineering University of Washington Box 352350 Seattle, WA  98195-2350 (206) 543-1695 voice, (206) 543-2969 FAX [comments to pedrod@cs.washington.edu]