I've noticed that whenever Jeff or another representative of Numenta gives a 
talk, they first revisit their definitions of terms used. Because a lot of 
these terms are "overloaded" by their context in everyday usage, it's probably 
important not to skip this step; especially because our goal brings with it 
conceptual hurdles as well as investigative. 

I have a feeling this will become crucial when we start tackling "Attention" 
and awareness.

Please forgive me if I'm stating the obvious?  :-)

David

Sent from my iPhone

> On Jul 11, 2014, at 7:12 AM, David Ray <[email protected]> wrote:
> 
> Close.
> 
> Using your "scale" analogy...
> 
> Resolution = unit of measure of the most granular increment of change. (i.e 
> .01g)
> 
> Capacity = count of distinct inputs possible at said resolution (i.e if scale 
> range is 0 to 10, then 1000)
> 
> Accuracy = how "well" does the scale perform it's task of measuring weight 
> (i.e how often is it correct?)
> 
> I don't know if resolution can be measured with the spacial pooler?
> 
> David
> 
> Sent from my iPhone
> 
>> On Jul 11, 2014, at 6:48 AM, Rik <[email protected]> wrote:
>> 
>>>> Sorry what value can be 1 billion? You keep bringing up that number. No 
>>>> spatial pooler of any sane dimensions has a capacity of 1 billion. Not for 
>>>> any reasonable definition of "capacity".
>>> 
>>> In this case we are just trying to discriminate between a fixed set of 
>>> patterns. By "discriminate" we mean the SDR output should be unique with 
>>> respect to the other patterns by at least one winning column.  Since there 
>>> are 1024 columns, of which 64 are on at a time, the total number of 
>>> patterns that can be discriminated is 1024 choose 64 > 10^102. In reality 
>>> it will be less than that, but if two inputs differ by more than a few 
>>> bits, we will have at least one column that is different. As such, there is 
>>> quite a bit of room here.
>> The SP output can possibly produce 1 billion+ different patterns but that is 
>> what I would consider its "resolution", not its "capacity" or "accuracy" 
>> which is what we're after in this thread and what is the desirable property 
>> that one seeks to evaluate and optimize. A completely unlearned SP will also 
>> produce 1 billion+ different output patterns so that can't possibly be an 
>> interesting property.
>> 
>> A real-world analogy: The local jeweler weighs precious metals with scales 
>> boasting a resolution of .01g but in the interest of getting a fair deal on 
>> my silver I'd rather know their accuracy. Scales with a resolution of .01g 
>> can still be off by 5g and usually will be so straight off the assembly line 
>> so they have to be calibrated, a primitive material world version of 
>> "learning".
>> 
>> Or your digital SLR camera + computer monitor boast a 24bit color depth 
>> allowing for 4 million+ colors but that's saying nothing about how 
>> faithfully they reproduce the exact shade of red of a flower that you 
>> photographed and there's a calibration/"learning" process too that involves 
>> photographing known colors off a pantone sheet.
>> 
>> A good definition of SP capacity or accuracy would IMHO involve a     
>> correlation between inputs and ouputs, along the lines of how well     
>> clusters in the input vector space correlate to clusters in the output 
>> vector space. Just thinking out loud here.
>> 
>> -- Rik
>> 
>> _______________________________________________
>> 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

Reply via email to