Hi Francisco,
On Wed, Aug 7, 2013 at 5:22 PM, Francisco Webber <[email protected]> wrote: > Still concerning the pass-through encoder: > At various occasions I have noticed that the "pass through" functionality > corresponds to skipping the spacial pooler. > In my current understanding this would not be correct. > It is true that the output of the spatial pooler is in SDR format. But it > cannot be implied from there that the the spacial pooler actually SDRizes > the input. > If an SDR is feed in the SP that (randomly) subsamples it, the resulting > output will still be a valid SDR (through the noise resistance property of > the initial SDR). > If a non SDR bit pattern is subsampled the result will be looking like an > SDR while having lost the semantic context of the input data (lacking the > NR property. > Yes, I believe a SP "just creates" a SDR, like Fergal said, this happens "automatically" in neurons through inhibition. > > Another problem that I have on the conceptual level, when assuming that > SDR data doesn't need the SP stage is that in a hierarchy of layers the > output data of every layer would have the SDR format. If it would be fed > into the next higher level, one could skip the SP in all subsequent higher > levels , leaving the question why there is an SP at all. > Here is the second role of a SP, it subsamples/compresses the output. So for a hiearchy of regions, say 10 regions have output of 1000 bits each, now that makes 10000 for the new input to the higher region. SP can shrink those 10k bits to say 1000 and feed it the the next TP. As SP is trained, it also handles noice at the input. I believe this is the functionality the SP does at higher levels. Regards, Mark -- Marek Otahal :o)
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
