I like your example, and I would love to see a PR. Kevin is working on a PR [1] to add another SP example to NuPIC as well, so you might want to take a look at some of the feedback he's getting. Be sure to run pylint against your code and document everything as much as possible, because people will be reading your code to try to figure out how NuPIC is working! :)
[1] https://github.com/numenta/nupic/pull/722 Thanks so much for your effort! --------- Matt Taylor OS Community Flag-Bearer Numenta On Wed, Mar 12, 2014 at 8:36 AM, Traun Leyden <[email protected]> wrote: > > Yep, fair enough. It sounds like you would need more than just a spatial > pooler here. > > I've found this paper which seems to be trying to tackle the same problem: > http://www.ict.griffith.edu.au/~johnt/publications/AI2008.pdf > > but unfortunately don't know where the accompanying source code is (or if > it's available). > > Btw if you think this repo would be good to put in the examples directory, > I'd be happy to send a PR. > > > On Mon, Mar 10, 2014 at 8:33 AM, Matthew Taylor <[email protected]> wrote: >> >> To quote Subutai from another thread [1]: >> >> "You might not get an exact match unless the inputs are really really >> close. In particular, the spatial pooler won't do too well at learning >> general invariances (and it's not supposed to). For example, if you >> shift the image by one or two pixels you might get a very different >> output SDR." >> >> [1] http://markmail.org/message/dytllixwodm5bjcu >> --------- >> Matt Taylor >> OS Community Flag-Bearer >> Numenta >> >> >> On Sun, Mar 9, 2014 at 12:27 PM, Traun Leyden <[email protected]> >> wrote: >> > >> > I created a simple example to recognize digits using the spatial pooler, >> > it's available on github here: >> > >> > https://github.com/tleyden/nupic-digitrecognizer >> > >> > It was able to get exact matches with SDR's, and I didn't need to use >> > the >> > KNNClassifier. Having said that, the test data was relatively "easy", >> > in >> > that I just went through the training data and removed a few pixels. >> > >> > However when I tried to recognize a digit that's been entirely shifted >> > to >> > the right by a few pixels (original - shifted) it wasn't able to find a >> > match. >> > >> > What are some suggested approaches to add spatial invariance so it can >> > handle this? >> > >> > I did see this mailing list thread but so far no simple answer has >> > jumped >> > out at me. >> > >> > Also thanks to all the folks who responded to my questions, those were >> > useful pointers. >> > >> > >> > >> > _______________________________________________ >> > 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 > _______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
