Hi Aniket, That's an interesting idea. It could be another type of adaptive encoding. If you have more ON bits for a particular range of numbers the spatial pooler might pay more attention to that range. It might also perhaps be less sensitive to small changes in that range. It could be interesting to play with variations of this scheme.
--Subutai On Tue, Feb 18, 2014 at 2:32 AM, Aniket Bhattacharya < [email protected]> wrote: > Chetan's talk about RDSE served to seed some additional ideas about data > encoding. Perhaps this has already been tried earlier, but I wanted to know > whether it makes sense to have a variable length data encoding scheme. > Using > the notations from slide 8 of Chetan's talk, what impact would a variable > 'n' have? For instance if given a w of 121, n is constrained to lie between > 15 and 21 such that more frequently occurring data is associated with a > lower value of n, and less frequently occurring data is associated with a > higher value of n. I am assuming that the statistics of the data is known > in > advance. What effect would this have, if any, on the spatial pooler? > > Aniket Bhattacharya, > CIMO fellow, > Department of Intelligent Automation, > Tampere University of Technology. > http://www.linkedin.com/in/aniketbhattacharya > > _______________________________________________ > 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
