I'm sorry if this is quite sudden. To build more specialized BSP-based machine learning community and collaborate with existing ML project mahout, personally I think that ML package need to be separated from core Hama (IMHO).
On Tue, Mar 12, 2013 at 5:25 PM, Apache Wiki <[email protected]> wrote: > Dear Wiki user, > > You have subscribed to a wiki page or wiki category on "Hama Wiki" for change > notification. > > The "OnlineML" page has been changed by edwardyoon: > http://wiki.apache.org/hama/OnlineML?action=diff&rev1=4&rev2=5 > > * Online Recommendation > * ..., etc. > > - == Rationale and Algorithms == > - > - Work In Progress. I'm currently studying, and testing BSP applications that > aim to speed up the recommendation engine for social commerce service. > - > - === Relationships with Other Apache Projects? === > - > - Comparing to Mahout, this is different in the sense that it runs based on > Message-Passing paradigm and will have On-line processing features. > - > - === Initial Members === > - > - * ''Please feel free to add yourself here, if you are interest.'' > - * Edward J. Yoon, Oracle, <[email protected]> > - * Paul Gyuho Song, Oracle, <[email protected]> > - -- Best Regards, Edward J. Yoon @eddieyoon
