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
