Graphs, Edges & Nodes: Untangling the Social Web

Joël Perras (29.Feb.2012 at 13:15)
Talk at ConFoo 2012 (English - UK)

Rating: 5 of 5

Facebook figures out people that you might already know, LinkedIn tells you how many degrees of separation there are between you and the CEO of Nokia, and LastFM suggests music based on your current listening habits. We’ll take a look at the basic theory behind how some of these features work (no comp. sci. degree required!), and show how you can implement some of these features in your application.

Who are you?

Claim talk

By clicking this button you are declaring that you are the speaker responsible for it and a claim request will be sent to the administrator of the event.

If the claim is approved you will be able to edit the information for this talk.

Are you sure?

Comments closed.


Rating: 5 of 5

29.Feb.2012 at 23:03 by Tom Thorogood (6 comments)

This was an awesome talk. It got me very interested in the algorithms that drive the social web, which I always thought were completely nebulous and intangible before. Well. They are still nebulous and intangible, but at least I know why now.

Rating: 5 of 5

01.Mar.2012 at 01:02 by Peter Meth (19 comments)

Nice job of explaining complex graph theory in terms that the average developer can understand.

Rating: 5 of 5

02.Mar.2012 at 06:26 by jbrisson (8 comments)

Awesome! Talented presenter (you're good at that man!). Eye/mind opening presentation. Went a little bit fast on Neural nets (forget about the neural label for a moment, those things delivered interesting stuff). Thanks again

Rating: 5 of 5

02.Mar.2012 at 10:21 by Igor (37 comments)

Excellent talk explaining basic graph theory concepts very well. You should consider going into more details on graph algorithms and their practical use, and extracting the machine learning part into a separate talk.

Speaker comment:

02.Mar.2012 at 11:08 by Joël Perras (9 comments)

Thanks for all the comments everyone! I'm glad to see that most people found the presentation useful and interesting. I'll be sure to try and expand on more ANN-specifics in the next iteration of this talk; I agree that I could be a bit less biased against them ;-).

Rating: 5 of 5

04.Mar.2012 at 13:36 by Guilherme Blanco (25 comments)

Great talk, deserves 5 stars for sure.
A good improvement point would be more real world examples and some known Graph navigation algorithms, like Dijkstra, Topological Sorting and AI pseudo codes for searching, mainly the used ones for recommendation, such as A*.

© 2015