[ml] jung, graph clustering

[Mike Schachter]

Hello everyone!

I haven't gotten anywhere with clustering via self-organizing
feature maps, but went off on a tangent after reading a section
of Duda's book on machine learning (which is a classic that you
should probably buy):

http://www.amazon.com/Pattern-Classification-2nd-Richard-Duda/dp/0471056693

In the chapter on clustering they talk briefly about clustering
using graph algorithms, which I think Erin mentioned at a meeting
a few weeks ago. I worked once with a pretty sweet graph modeling
tool call JUNG and am going to try and implement the approach to
create a visualizable cluster of the skill sets. Link to JUNG:

http://jung.sourceforge.net/

Tomorrow I'll go over the graphical approach real quick, along with
a neural network in the Duda/Hart book that can be used for dimensionality
reduction, which could be promising.

See you tomorrow! Looking forward to it,

   mike
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.noisebridge.net/pipermail/ml/attachments/20100601/7711e670/attachment-0002.html>