Probabilistic Graphical Models

author: Sam Roweis
published: Feb. 25, 2007,   recorded: January 2005,   views: 154200


Related Open Educational Resources

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.

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 52:01
Watch Part 2
Part 2 38:47
Watch Part 3
Part 3 1:02:23
Watch Part 4
Part 4 40:03
Watch Part 5
Part 5 1:02:30
Watch Part 6
Part 6 42:32
Watch Part 7
Part 7 57:49
Watch Part 8
Part 8 42:57


My lectures will cover the basics of graphical models, also known as Bayes(ian) (Belief) Net(work)s. We will cover the basic motivations for using probabilities to represent and reason about uncertain knowledge in machine learning, and introduce graphical models as a qualitative and quantitative specification of large joint probability distributions. We will see how many common classification, regression and clustering models can be cast in this framework. We will cover the basic algorithm (called belief propagation) for inference in graphical model structures. We will also cover the major approaches to learning models from data (parameter estimation). The course will focus on directed models and the basic algorithms, but time and student desire permitting, I will also try to give some preliminary explanations of undirected models, approximate inference and learning, structure discovery and current applications.

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 Vinay, April 24, 2007 at 11:15 a.m.:

Mr. Sam Roweis lectures are very good.
he presents the theory in an interesting and a non-boring way.

Comment2 sreekanth vp, July 24, 2007 at 3:43 p.m.:

very useful

Comment3 dio, September 8, 2007 at 5:10 a.m.:

great...It open my eyes!

Comment4, November 18, 2007 at 2:35 p.m.:

for any case, i would like to thank you very much.
it is very interesting and helpful.

i would like to download the videos presentations about SVM but i couldn't, because i need them in my research.

can you help me to get them.

Comment5 Natasha26, November 20, 2007 at 6:28 p.m.:

so cool! thanks...

Comment6 Ibrahim El-Semman, November 23, 2007 at 1:36 p.m.:

It is a useful lectures, My best regards to Prof. Sam

Comment7 Abdul Rehman Abbasi, April 20, 2008 at 1:11 p.m.:

Lectures by Sam are really helpful for variety of audience doing either courses or research. His style is very very effective but some time I feel that he needs to repeat some point especially when it is really important one.


Comment8 Hasinur Rahaman Khan, May 10, 2008 at 1:52 p.m.:

His presentation is nice and I personally have been benefited from his lecture. Now things to me are quite easier than my previous feelings. Thanks

Comment9 Ahmed, June 29, 2008 at 5:10 p.m.:

He is a very good lecturer and its great tof ind these things on video lectures which usually we donot get in avrsities

Comment10 Maja, September 19, 2008 at 7:41 a.m.:

Sam Roweis lectures are well organized. They present the key challenges and ideas of machine learning and graphical models in a clear cut and concise manner. I love maths myself, but I believe that introductory lectures should focus on conveying new ideas in an easy to grasp way before journeying into the mathematical details -no matter how interesting these might be. In my opinion, Sam Roweis accomplish this in his lectures. I greatly appreciate that I have had the opportunity to follow these lectures online and recommend them to anyone with an interest in machine learning.

Comment11 Kevin, December 29, 2008 at 11:54 p.m.:

An excellent introduction. I have no real understanding of mathematics. However, the clear manner in which graphical models really help clarify the association of the learning strategies and their mathematical formulations.

Thanks professor Sam Roweis


Comment12 Doug, April 11, 2009 at 6:09 p.m.:

Holy Christ could you please use a standard video format that everyone's computer can play PLEASE?!?! Just use YouTube, jeez.

Comment13 Devin, January 14, 2010 at 1:43 p.m.:


Comment14 Mohammed, January 15, 2010 at 11:51 a.m.:

Poor guy. Killed himself just a couple of days ago. I know virtually nothing about computer science, but his CV is available on the web and its obvious he was severely intelligent. RIP.

Comment15 Sami, August 5, 2010 at 6:32 a.m.:

It's a great loss, he was a rare genius in machine learning. I could not believe when i heard the news about him. Its so painful. He was such a nice young person and I'll never be able to forget him. RIP

Comment16 Mahdi, September 2, 2010 at 2:13 p.m.:

His lecture was really Great. It was so sad that the world loosed such great scientist.

The NIPS Foundation has set up a Memorial Fund to support the care and well being of Prof. Roweis' family.

Comment17 Jeffrey Dubose, April 10, 2020 at 11:04 p.m.:

I need a rundown of each and every class you take for PC building ?

if you don't mind list all the maths and essential you have to take PC building for or the greatest number of as you can ?

Comment18 Angel Martin, April 10, 2020 at 11:06 p.m.:

That will depend on the university you go to. What you need to do is look up a particular university webpage and from there find the department of engineering. They usually have the curiculumn online. learn from here also

Comment19 KyleSnider, June 11, 2020 at 12:12 a.m.:

Comment20 Danielcraig, June 19, 2020 at 5:06 a.m.:

Graphical model lets the people know about the basic summary with less time rather than reading all the content manually.This website and the lecture helps the student to get motivation towards the graphical model for resenting the data.

Write your own review or comment:

make sure you have javascript enabled or clear this field: