Patrick, your image will be very useful for explaining the encoder. I only see one thing wrong - in the top half (current encoder) the top five rows have 6 cells active instead of 5.
But even if we choose the first range randomly in the implementation I think your image showing consecutive bits first makes it easier to understand. On Thu, Oct 31, 2013 at 3:24 PM, Jeff Hawkins <[email protected]> wrote: > Patrick, > Yes, I think you have the idea captured in these very nice images. > > As I understand the images, the x-axis is a list of encoding bits. The > y-axis shows encodings of successively increasing scalar input values. > > In my original email, at the end, I suggested that in hind sight we could > have just picked encoder bits randomly. As you say, this would be cleaner > and eliminate the strangeness of starting assigning coding bits one way and > then switching to a different, random, method. This would also reduce the > possibility of having some edge condition as we switch from the first > method > to the second. > > I don't see why this would increase the number of possible combinations. > Jeff > > -----Original Message----- > From: nupic [mailto:[email protected]] On Behalf Of Patrick > Higgins > Sent: Thursday, October 31, 2013 12:04 AM > To: NuPIC general mailing list. > Subject: Re: [nupic-dev] new encoder idea > > Jeff, > > Does this look correct? If so I'll expand on it to make it more clear. I > reduced it to 41 bits with 5 on bits for simplicity... > > Also, if this is correct, then why does the scaler encoder not just pick > random bits for each SDR if the bits in the buckets do not need to adjacent > to each other? Doing that would expand the number of possible combinations > substantially and give the overall system consistency. > > > > > Patrick > > > > _______________________________________________ > 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
