On Wed, Jul 9, 2014 at 4:25 AM, Rik <[email protected]> wrote: > On 09/07/14 14:13, Subutai Ahmad wrote: > > Thanks, Jim. Yes, as long as the inputs are pretty distinct, I think > learning the training set should work perfectly for much larger data sets. > In theory the limit here should be extremely high (well over a billion > patterns). > > Sorry what value can be 1 billion? You keep bringing up that number. No > spatial pooler of any sane dimensions has a capacity of 1 billion. Not for > any reasonable definition of "capacity". >
In this case we are just trying to discriminate between a fixed set of patterns. By "discriminate" we mean the SDR output should be unique with respect to the other patterns by at least one winning column. Since there are 1024 columns, of which 64 are on at a time, the total number of patterns that can be discriminated is 1024 choose 64 > 10^102. In reality it will be less than that, but if two inputs differ by more than a few bits, we will have at least one column that is different. As such, there is quite a bit of room here. BTW another good opportunity to plug my quest for a quantitative model of > the CLA > <http://lists.numenta.org/pipermail/nupic-theory_lists.numenta.org/2014-March/000006.html>, > head over to nupic-theory everyone and continue the discussion there. > I think this is a great goal. I've been working on this a bit on the side since my Hackathon Deep dive last year and our email discussions. I've made some progress and hope to put together a talk on this soon. I'll definitely announce it on the theory list and maybe we can do a webcast version of the talk. --Subutai > > Regards > > Rik > > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
