We will follow some chapters of the book on Probabilistic
Graphical Models by Koller and Friedman (MIT
press 2009). The book has three parts and we will cover a few chapters from
each part. You may want to read the probabilistic background in chapter 2 which
we will skip.
Tentative
schedule
1. An introductory lecture
(Oct 20)
2. Chapter 3: The Bayesian Network Representation (Oct 27),
Omer Tabach, Omer's notes, Homework #1
3. Chapter 4: Undirected Graphical Models (Nov 3), Itzhak Taub, Presentation,
Homework
#2
4. Chapter 9: Exact Inference: Variable Elimination (Nov
10), Barak Sternberg and Shimi Salant, Presentation parts 1+3, Presentation part 2, Homework #3
5. Chapter 10: Exact Inference: Clique Trees (Nov 17), Jonathan
Shafer, Lecture notes, Handout, Homework #4
6. Chapter 11: Inference as Optimization (Nov 24), Daniel
Carmon, slides,
homework #5
7. Chapter 12: Particle-Based Approximate Inference (Dec
1), Dafna Sade and Uri Meir, presentation, homework #6
8. Chapter 13: MAP Inference (Dec 8), Alon Brutzkus, presentation, homework #7
9. Chapter 17: Parameter Estimation (Dec 15), Tomer Galanti, presentation, homework
#8
10. Chapter 18: Structure Learning in Bayesian Networks
(Dec 22), Guy Shalev, presentation, homework
#9
11. Chapter 19: Partially Observed Data (Dec 29), Tal Gerbi and Shay Kazaz, presentation1,
presentation2, homework
12. Chapter 20: Learning Undirected Models (Jan 5), Barak
Gross, Mark Berlin, presentation1,
presentation2
13. Application
(speech recognition?) (Jan 12), Amichy Painsky, presentation