1 Partha Ghosh, November 19, 2011 at 1:04 a.m.:

Extreme clarity in explaining the complex LDA concepts. What started as mythical, was clarified by the genius David Blei, an astounding teacher researcher. Simply superb!

2 Andrew Polar, November 23, 2011 at 5:44 p.m.:

Your concept is completely wrong. Topics are distributed differently, not as Dirichlet prior. The creator of document choose only 1 or 2 topics and rarely 3 topics when making document, while number of topics in collection could be a hundred. I can write document about environment and how U.S. Congress treats it, so it will be document on 2 topics. It may be more but with lower probability and it can't be 20 or 30.
The right model is 2 urns with colored balls. First urn has one ball of each color. User draw 1 or 2 balls from it. Then user use other urn with many balls of each color. User draw selected number of balls but ignores other than colors of selected from previous urn. Example: first urn has 1 red, 1 green, 1 blue, 1 yellow. I choose randomly red and green. The second urn has 1000 red, 1000 green, 1000 blue, 1000 yellow. I draw 10 ball but keep only red and green. Let say outcome is 7 red and 3 green, this is topic distribution. It is not Dirichlet process. This is how it works in real life.

3 Andrew Polar, November 23, 2011 at 5:58 p.m.:

I can also add that this model does not consider that some topics have no chances to be in one document. Show me the document speaking about marine mammals, linear algebra, crime rate in New York and tea ceremony in Japan at the same time. Two parameters, introduced in concept (alpha and beta) do not control topics to the required degree. Concept works and returns reasonable result because it is close to PLSA and PLSA is close to non-negative matrix factorization.

4 Suresh, December 8, 2011 at 6:32 a.m.:

How do I download these videos? These don't even buffer...

5 Saullo, July 21, 2012 at 12:50 a.m.:

This website has awesome lectures but I'm never able to check... They don't even buffer with me also...

6 George, March 13, 2013 at 11:13 a.m.:

Is there any chance that the whole slides from this presentation are somewhere available? Especially by the end of the second video, some really important parts are left out due to time constraint

7 George, March 13, 2013 at 11:15 a.m.:

Please ignore the comment above.. next time i will check before i post ^^

8 Muthu Kumar C, June 7, 2013 at 1:17 a.m.:

Listen it once, you are a little distracted by the jokes and the notations. Second time, it is obvious.

9 Nikos Daniilidis, June 16, 2014 at 9:40 p.m.:

Excellent presentation, very poor video streaming quality. Is there some way to download this?

10 Aditya Joshi, August 7, 2014 at 12:50 p.m.:

For those who have trouble viewing the lectures...

https://www.youtube.com/watch?v=DDq3O...

11 ghozan, August 19, 2014 at 2:04 p.m.:

is there any video in youtube for the second presentation?

12 ahmed mahad, March 26, 2016 at 1:16 p.m.:

Vede lectures related to econometrics

13 Skye Li, April 26, 2016 at 3:31 a.m.:

How did he get 0.33 at around 39 minutes? What does the n mean in Zd,n?

14 Anmol, November 21, 2016 at 8:25 a.m.:

Exactly! How did he git it as 0.33?

15 Neethu, December 29, 2016 at 8:07 a.m.:

To clarify the question asked for 0.33 at 39 minutes, he did not derive 0.33;he assumed the probability value in the graph for the example.