Google TechTalks
Bay Area Discrete Math Day XII
April 15, 2006
Michael Jordan (UC Berkeley)
ABSTRACT
A Dirichlet process (DP) is a random probability measure that concentrates on discrete measures. It has interesting and well-explored connections to various topics in combinatorics and probability. It has also played an important role in nonparametric Bayesian statistics, via sampling algorithms that are based on its exchangeability properties. I define a hierarchical Dirichlet process (HDP), in which the base measure for each of a set of child DPs is itself distributed according to a DP. I discuss representations of HDPs in terms of stick-breaking processes and a generalization of the Chinese...
cs [dot] berkeley [dot] edu /~jordan/papers/xing-jordan-sharan [dot] pdf
pokerface12344321 2 years ago 2
This is a great video.
pokerface12344321 2 years ago
Awesome presentation.
europeso 3 years ago
unfuckingreadable
semiliteratedgod 4 years ago
The font size on the slide was too small.
michaeldeng1981 4 years ago
Google tech Talks is a great initiative. The benefits that we, engineers, could have are huge. Nevertheless Google has to make some improvements in order to make the videos more viewable. There are a lot of videos, if not all, that is almost impossible reading the slides. Google Engineers I know that you could solve this problem fast!!!!
keyuser88 4 years ago