2012/1/23 Gael Varoquaux <[email protected]>: > On Mon, Jan 23, 2012 at 10:08:45AM +0100, Olivier Grisel wrote: >> Once we have random projections (or even just efficient hashing API), >> LSH is quite simple to implement on top. > > I don't understand: they are quite orthogonal, aren't they?
You can implement LSH with random projections or hash functions: http://en.wikipedia.org/wiki/Locality-sensitive_hashing#Methods LSH is just using a binary thresholded random projections in 32 (or 64 or 128...) dim space. That leads to 32bit (or 64bit...) vectors castable as integers and doing Hamming radius queries instead of Euclidean queries in that boolean space. Also you can simulate random projections with a hash function too. This is what I have done in the `hashing_dot` function of my branch as an alternative to materializing the random matrix: https://github.com/ogrisel/scikit-learn/blob/random_projection/sklearn/random_projection.py#L209 -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ Try before you buy = See our experts in action! The most comprehensive online learning library for Microsoft developers is just $99.99! Visual Studio, SharePoint, SQL - plus HTML5, CSS3, MVC3, Metro Style Apps, more. Free future releases when you subscribe now! http://p.sf.net/sfu/learndevnow-dev2 _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
