Graphical Models and Variational Methods

author: Christopher Bishop, Microsoft Research
published: Feb. 25, 2007,   recorded: September 2004,   views: 79840
Categories

Slides

Related content

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.
Lecture popularity: You need to login to cast your vote.
  Delicious Bibliography

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 41:43
!NOW PLAYING
Watch Part 2
Part 2 56:56
!NOW PLAYING
Watch Part 3
Part 3 43:33
!NOW PLAYING
Watch Part 4
Part 4 1:00:13
!NOW PLAYING
Watch Part 5
Part 5 28:26
!NOW PLAYING
Watch Part 6
Part 6 42:57
!NOW PLAYING

Description

In this course I will discuss how exponential families, a standard tool in statistics, can be used with great success in machine learning to unify many existing algorithms and to invent novel ones quite effortlessly. In particular, I will show how they can be used in feature space to recover Gaussian Process classification for multiclass discrimination, sequence annotation (via Conditional Random Fields), and how they can lead to Gaussian Process Regression with heteroscedastic noise assumptions.

Link this page

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

Reviews and comments:

Comment1 David, March 13, 2007 at 10:46 p.m.:

a huge part of lecture 4 is not there. could some one please help fix it? thanks.


Comment2 Chang, July 25, 2007 at 12:38 a.m.:

There is a huge chunk of the video missing. After the third lecture, there should be video lecture for Junction trees but instead the fourth lecture jumps to latent variable view of EM


Comment3 mikaiel, September 20, 2007 at 9:44 a.m.:

I look through the video lecture and Part 4 and 5 are in reverse order. Also why is lecture 6 and 7 exactly the same? And why is lecture 8 not present?


Comment4 Francisco, March 15, 2008 at 6:35 p.m.:

Indeed, lecture 8 is missing, just when the lecture would get into variational methods. I wish someone could fix this. Given that the other commnents are from one year ago, I think these commnents are not getting they feedback they should.


Comment5 anon, July 21, 2008 at 1:11 p.m.:

early potion of part5 has no sound..


Comment6 Kayhan, August 20, 2008 at 4:17 a.m.:

lectures 6 and 7 are exactly the same and the most important part of the course (variational inference) is missing! Please add it.


Comment7 Ali, July 4, 2009 at 3:29 p.m.:

Camera is poorly managed. Professor is writting on the screen and the camera is focusing on his face (many occasions!). Please use professional camera man for recordings.


Comment8 Lukasz, May 7, 2010 at 5:04 a.m.:

Part 4, camera is sometimes pointed neither at the screen nor at the presenter, but at the ceiling.


Comment9 Uri, October 3, 2010 at 11:20 a.m.:

The cameraman is doing the stupidest filming ever. There is never a reason to film the lecturer (or the class) instead of the board. The lecturer can always be heard, but the board cannot be seen if it isn't filmed!


Comment10 Hani, February 13, 2012 at 6:42 a.m.:

It seems from the lecturer's talk and from the comments that there are missing parts. Please could any body help by uploading them. Thanks...


Comment11 Hani, February 13, 2012 at 6:42 a.m.:

It seems from the lecturer's talk and from the comments that there are missing parts. Please could any body help by uploading them. Thanks...


Comment12 Jyoti Ramakrishnan, December 30, 2014 at 2:23 p.m.:

Can you kindly share the lectures 7&8 as well? I don't see them listed. Thanks


Comment13 homepage, September 30, 2021 at 6:34 p.m.:

Thanks a lot to save my time. this Awesome site. It helped me a lot.

Write your own review or comment:

make sure you have javascript enabled or clear this field: