machinedlearnings.com
Machined Learnings: November 2014
http://www.machinedlearnings.com/2014_11_01_archive.html
Cue Butlerian Jihad in 3, 2, 1, . Sunday, November 16, 2014. There's plenty of unlabeled data, so lately I've been spending more time with unsupervised methods. Nikos. And I have spent some time with CCA. Which is akin to SVD but assumes a bit of structure on the data. In particular, it assumes there are two (or more) views of the data, where a view is basically a set of features. A generative interpretation. Mathrm{subject to} ;& mathbf{X} a top mathbf{A} top mathbf{A} mathbf{X} a = n mathbf{I},. Basica...
machinedlearnings.com
Machined Learnings: February 2014
http://www.machinedlearnings.com/2014_02_01_archive.html
Cue Butlerian Jihad in 3, 2, 1, . Friday, February 21, 2014. Stranger in a Strange Land. I attended the SIAM PP 2014. The Data Must Flow. One of the first things I heard at the conference was that “map-reduce ignores data locality”. The speaker, Steve Plimpton, clearly understood map-reduce, having implemented MapReduce for MPI. This was a big clue that they mean something very different by data locality (i.e., they do not mean “move the code to the data”). Moderately distorted, is a good match for what ...