Hi, I think this video explains it quite nicely too: http://www.youtube.com/watch?v=z6r3ekreRzY
Gari On Mon, Oct 21, 2013 at 10:35 AM, Michael Ferrier <[email protected] > wrote: > Hi Jeff, > > That is what the spatial pooler does. See pages 21-22 of the white paper > for more details. Each column in an HTM region receives input from a unique > subset of input bits, so when the region receives a pattern of input bits, > regardless of what percentage of the input bits are on, some columns will > receive more excitation than others. Only the 2% of columns that receive > the highest amount of excitation will be activated. So regardless of what > proportion of input bits are active, the region will end up with a sparse > distributed representation of the input, with 2% of columns active. > > -Mike > > _____________ > Michael Ferrier > Department of Cognitive, Linguistic and Psychological Sciences, Brown > University > [email protected] > > > On Sun, Oct 20, 2013 at 9:40 PM, Jeff Fohl <[email protected]> wrote: > >> Hello - >> >> I hope this is not being posted to the wrong list. This is my first post >> here. Please let me know if there is a more appropriate place for this >> question. >> >> In preparation for learning NuPIC, I have read "On Intelligence", and I >> am now reading the HTM white paper put out by Numenta. >> >> Making my way through the white paper, I got stuck on one passage, which >> I can't really make sense of. Wondering if anyone can help me through this >> part. The passage in question is on pages 11-12 of the white paper PDF - >> specifically the second paragraph included below. >> >> *HTM regions also use sparse distributed representations. In fact, the >> memory mechanisms within an HTM region are dependent on using sparse >> distributed representations, and wouldn’t work otherwise. The input to an >> HTM region is always a distributed representation, but it may not be >> sparse, so the first thing an HTM region does is to convert its input into >> a sparse distributed representation.* >> >> *For example, a region might receive 20,000 input bits. The percentage >> of input bits that are “1” and “0” might vary significantly over time. One >> time there might be 5,000 “1” bits and another time there might be 9,000 >> “1” bits. The HTM region could convert this input into an internal >> representation of 10,000 bits of which 2%, or 200, are active at once, >> regardless of how many of the input bits are “1”. As the input to the HTM >> region varies over time, the internal representation also will change, but >> there always will be about 200 bits out of 10,000 active. * >> >> So, what exactly is going on here? How does a fluctuating input flow of >> 20,000 bits get converted into 200 bits? Obviously there is something >> important going on here, but I don't understand what it is. Any help >> illuminating this would be greatly appreciated! >> >> Many thanks, >> >> Jeff >> >> _______________________________________________ >> 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 > >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
