On Thu, Aug 22, 2013 at 1:34 PM, Hideaki Suzuki <[email protected]> wrote:

>
> As I said in the last mail, I enjoyed to explore the beauty of SP.  I'm
> pretty much sure that
> you will have a good time, too.  I'm expecting to have even more enjoyable
> time
> when I play with TP, because TP is the very "unique feature" of CLA.
>

I think it's a very interesting project, and the concepts and design make a
lot of sense.

Specifically regarding the Spatial Pooler and Temporal Pooler, I
continually wonder if these are necessary concepts - a lot of the other
concepts have direct analogues with structures in the brain.  These two are
the "odd men out".  It seems to be where the algorithmic complexity landed,
but it seems more like an implementation detail - thing which mutates a
bunch of data structures - than a necessary component (the logic needs to
exist;  aggregating it and naming it that way seems like a design choice
for putting a bunch of procedural code somewhere).  Am I missing some key
aspect here?


> So, I guess my question is:  Does a *proximal* dendrite connect to more
>> than one bit?
>>
>
> I think so.
> To be more precise, one proximal dendrite segment has many synapses, and
> each synapse connects to one bit.
>

That's where I keep getting stuck:  Is there any guidance for how to map
input-bits:synapses:columns, and how to layout distal dendrites *before you
have seen any input* - i.e. you are starting from zero, new data, new
configuration.  You have to choose *some* initial layout/mapping for these
things.  It's easy to randomly generate a bunch of connections and hope the
result is useful.  But it seems like there ought to be some suggested
approach, not just randomly do stuff and see what comes out.

Perhaps this is where I should just go read more code, but even doing that
won't tell me the reasoning behind the approach.

So basically, when creating a new distal segment, just randomly pick some
>> cells "near" (in whatever topology) the cell it connects to?
>>
>
> For distal segment, I don't think we have concept of near or far.
> Candidates are all cells.  This is mentioned "Implementation details and
> terminology" on Page 42
> in the white paper.
>

Hrm, are we looking at the same thing?  In my copy of the white paper (is
there more than one?), page 42 is pseudocode for Phase 2 and Phase 3.

Thanks a lot for your feedback!

-Tim
_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

Reply via email to