Hi all, My supervisor updated his page. You can get our papers here: http://www.ict.griffith.edu.au/~johnt/publications.html.
There is the most recent paper on sparse codes plus some of our other papers. On 16 March 2014 02:07, Traun Leyden <[email protected]> wrote: > Hi Adam, > > Yes I'd be interested in getting a copy. I'd prefer a README and a github > repo, but I'll take what I can get! > > > > On Thu, Mar 13, 2014 at 3:35 PM, Adam Kneller < > [email protected]> wrote: > >> Hi, >> >> My supervisor is the lead author on that paper. It uses the old version >> of the HTM, not the CLA. We have some more recent papers dealing with digit >> recognition that use the CLA, e.g. Evaluating Sparse Codes on Handwritten >> Digits (http://link.springer.com/chapter/10.1007/978-3-319-03680-9_40). >> >> Let me know if you don't have Springer access and I will hopefully be >> able to get yo a copy. >> >> Adam. >> >> >> On 13 March 2014 01:36, 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 >> >> > > _______________________________________________ > 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
