## Graphical models

author: Zoubin Ghahramani, Department of Engineering, University of Cambridge
published: Aug. 25, 2007,   recorded: August 2007,   views: 11247
Categories
You might be experiencing some problems with Your Video player.

# Slides

0:00 Slides Lecture 1: Introduction to Graphical Models Lecture 1: Introduction to Graphical Models Three main kinds of graphical models Why do we need graphical models? Conditional Independence Conditional and Marginal Independence (Examples) Factor Graphs Factor Graphs01 Proving Conditional Independence Undirected Graphical Models Undirected Graphical Models01 Comparing Undirected Graphs and Factor Graphs Problems with Undirected Graphs and Factor Graphs Directed Acyclic Graphical Models (Bayesian Networks) Directed Acyclic Graphical Models (Bayesian Networks)01 Examples of D-Separation in DAGs From Directed Trees to Undirected Trees Directed Graphs for Statistical Models: Plate Notation Expressive Power of Directed and Undirected Graphs Summary

# Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Part 1 53:13
!NOW PLAYING

Part 2 58:16

Part 3 1:18:43

Part 4 31:00

Part 5 1:05:18

Part 6 29:13

# Description

An introduction to directed and undirected probabilistic graphical models, including inference (belief propagation and the junction tree algorithm), parameter learning and structure learning, variational approximations, and approximate inference.
- Introduction to graphical models: (directed, undirected and factor graphs; conditional independence; d-separation; plate notation)
- Inference and propagation algorithms: (belief propagation; factor graph propagation; forward-backward and Kalman smoothing; the junction tree algorithm)
- Learning parameters and structure: maximum likelihood and Bayesian parameter learning for complete and incomplete data; EM; Dirichlet distributions; score-based structure learning; Bayesian structural EM; brief comments on causality and on learning undirected models)
- Approximate Inference: (Laplace approximation; BIC; variational Bayesian EM; variational message passing; VB for model selection)
- Bayesian information retrieval using sets of items: (Bayesian Sets; Applications)
- Foundations of Bayesian inference: (Cox Theorem; Dutch Book Theorem; Asymptotic consensus and certainty; choosing priors; limitations)

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

1 Roman, August 28, 2007 at 5:08 p.m.:

Will there be a version in Window Media Format?

2 Roman, August 28, 2007 at 6:24 p.m.:

Part 2 (file suffix 01) ends at about 32% (wmv). Do others have the same problem?

3 davor (staff), August 28, 2007 at 8:33 p.m.:

I have checked all the parameters and asked students from CMU if they have troubles with this video, but they dont seem to have this problem. Have you checked your players settings?

4 ss, September 6, 2007 at 2:58 a.m.:

Will the other parts of the tutorials be available soon?

5 yiqun, September 13, 2007 at 7:24 p.m.:

zhoubin's talk is very nice! But the third part about learning the parameters and structures of directed graphical model is missing! Can this part of talk be available?

6 Krishna, September 26, 2007 at 7:42 p.m.:

I am specifically looking for the part on learning the parameters and structures... Unfortunately this seems to be missing :(. Please let me know where I can find it!

7 cuty, October 23, 2007 at 5:39 a.m.:

Great talk! I find it very useful.

8 guest, April 28, 2008 at 2:52 a.m.:

Hi,

i was wondering where the first part of lecture 3 is?, could you please upload that,..Thanks,

9 amirhossein, May 25, 2008 at 2:01 a.m.:

Great comprehensive lecture.
Many thanks to prof. Ghahramani.

10 davor (staff), August 8, 2008 at 3:54 p.m.:

Hello everyone, we have added a new version of part 3 and 4 so enjoy them.

11 hassan, November 3, 2008 at 1:07 p.m.:

hello
thank you

12 rr, November 16, 2008 at 12:58 p.m.:

Hey,

WMV version of part 2 stops around 30% into the lecture.
Thanks

13 rr, November 16, 2008 at 11:12 p.m.:

The flash version of lec 2 stops after about 9 minutes

14 Sobhan, November 21, 2008 at 11:21 p.m.:

The third and forth lectures have problems in the middle.
I was proceeding along with the lectures sequence but the problem stopped me in the most challenging and informative part (learning the models)!

Thanks,
Sobhan

15 VG, February 5, 2009 at 8:59 a.m.:

Hi,
Would you please to fix the lecture 3 problem. It stops just after 44 minutes. I really would appreciate if you could help us. Thanks.

16 Sanghack Lee, March 1, 2009 at 4:28 a.m.:

I think you can solve the problem by launching a WMP instead of instead of using flash player

17 Mike, May 19, 2009 at 11:14 p.m.:

In slide 15 (@45:06 min), example 3 says the path is blocked by D. Doesn't he mean B?

18 Cyrill, June 30, 2009 at 1:12 p.m.:

Player (flash) blocks at 44:07. Any idea how to fix that?

19 Cauchy, July 26, 2009 at 1:30 p.m.:

I find the same problem that I cannot watch whole part2 and the video stopped at 89%.

20 jib, July 29, 2009 at 2:52 a.m.:

I cannot watch videos 1 and 4. An error messages popps up saying: "AJAX error: parsererror". Please fix it.

21 Hamid, June 6, 2011 at 7:42 a.m.:

They haven't still fixed the problem with the flash version of the lecture number 3. It seems that there is nobody to read these comments!!!!

22 Liangliang, June 28, 2011 at 4:26 a.m.: