Thank you, Scott san and Subutai san. I'm its watcher now. :)
2013/8/15 Scott Purdy <[email protected]> > Might take a few weeks depending on when Subutai can find time to put it > together. Follow along here: > https://issues.numenta.org/browse/NPC-310 > > > On Tue, Aug 13, 2013 at 10:32 AM, Hideaki Suzuki <[email protected]>wrote: > >> That would be great! Thank you very much. >> >> >> 2013/8/14 Scott Purdy <[email protected]> >> >>> I am going to try to engage Subutai and Jeff today and will follow up. >>> There was a lot of previous experimentation with vision so no point in >>> trying everything again. >>> >>> >>> On Tue, Aug 13, 2013 at 10:10 AM, Hideaki Suzuki <[email protected]>wrote: >>> >>>> Hi Scott san, >>>> >>>> Thank you for your comment and clarification. >>>> >>>> In that sense, would JIRA be the better place to gather pieces of >>>> information for discussion? >>>> >>>> I have a few more ideas of enhancement for 2D input; local inhibition, >>>> boosting,... ,etc. >>>> (from software perspective) >>>> >>>> Best Regards, >>>> >>>> 2013/8/14 Scott Purdy <[email protected]> >>>> >>>>> You are correct that a separate scalar encoder for each pixel would >>>>> not be a good method. You would want to create a vision-specific encoder >>>>> which may do a number of preprocessing techniques to capture the semantics >>>>> of the data. You would also want to use topology in the SP (currently the >>>>> default is global inhibition). And I believe that hierarchy is somewhat >>>>> important to vision problems, although may not be necessary for some >>>>> problems (I don't really know). >>>>> >>>>> This is a pretty big task in general. We have been talking about >>>>> putting up details around some domains like vision and NLP to help guide >>>>> research so we will follow up if we can get something like that together >>>>> for vision. >>>>> >>>>> >>>>> On Tue, Aug 13, 2013 at 8:21 AM, Hideaki Suzuki <[email protected]>wrote: >>>>> >>>>>> Hello people, >>>>>> >>>>>> Today, I've got one idea in my mind. Do you have any opinion or >>>>>> interest for this? >>>>>> >>>>>> Nupic uses scalar encoder to feed numbers to SP, IIUC. >>>>>> >>>>>> If we want to feed an image to SP, each pixel has an integer value and >>>>>> the number of pixels are large. It sounds not so easy to me that we >>>>>> convert >>>>>> million pixel values through scalar encoder and feed them to SP. >>>>>> >>>>>> Can dithering work as the encoder? I mean this. >>>>>> http://en.wikipedia.org/wiki/Dither >>>>>> >>>>>> Our brain recognizes a black & white binary image as if it is a >>>>>> grayscale image >>>>>> after dithering. Does our retina convey the intensity of light in a >>>>>> similar way of >>>>>> dithering...? >>>>>> >>>>>> # I was a bit away from ML due to a business trip. I hope I can be >>>>>> more active now. :) >>>>>> >>>>>> Best Regards, >>>>>> Hideaki Suzuki. >>>>>> >>>>>> _______________________________________________ >>>>>> 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 > >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
