> Rather than introduce a new third method, it seems to me that we could simply 
> replace the spreading of importance from everything in the AF with the 
> spreading of importance K links out, where the value of K might be determined 
> from context.


I just worry that would result in the internal AF STI-spreading
happening too slowly, thus screwing up attractor-formation dynamics
inside the AF ...

After all, spreading 3 links out from X may take 100x or 1000x or 10Kx
more effort than spreading only from X, right?



>The “third method” really just seems to me to be a generalized version of AF 
>spreading rather than a new method. As Roman points out, the actual mechanics 
>of how to spread K links out also needs to be determined.
>
> —matt
>
>> On Sep 12, 2016, at 10:01 AM, Ben Goertzel <[email protected]> wrote:
>>
>> A somewhat interesting point came up in discussions w/ Misgana re ECAN 
>> today...
>>
>> So far we have been working on two methods of attention allocation:
>>
>> -- spreading importance from everything in the AttentionalFocus, frequently
>>
>> -- spreading importance from everything in the Atomspace, but more
>> slowly (by sampling Atoms from the Atomspace with probability
>> proportional to STI, and then spreading from each Atom as it's
>> sampled)
>>
>> But we have seen a need now for a third method
>>
>> -- iterating through every X in the AttentionalFocus, and spreading
>> importance K links out from X (where, say, K=2 or 3)
>>
>> The practical use-case that made this requirement clear was: rapidly
>> boosting the importance of question-answers, that contain words which
>> are in the AF....  The question-answers are ImplicationLinks, which
>> point to ListLinks, which point to words ... so to get STI to the
>> ImplicationLink, a word in the AF needs to send STI to the ListLink
>> which then needs to send STI to the ImplicationLink...
>>
>> But more generally one can view this as an importance-spreading agent
>> aimed at spreading activity from the AttentionalFocus to the "Fringe"
>> of consciousness -- those things that one can feel at the back of
>> one's mind, on the edge of one's consciousness ... one is aware they
>> are there but not quite aware of what they are, but one can generally
>> with effort pull them into one's awareness...
>>
>> Sometimes spreading enough STI into the Fringe will cause something in
>> the Fringe to get boosted into the AttentionalFocus ....
>>
>> -- Ben
>>
>> --
>> Ben Goertzel, PhD
>> http://goertzel.org
>>
>> Super-benevolent super-intelligence is the thought the Global Brain is
>> currently struggling to form...
>>
>> --
>> You received this message because you are subscribed to the Google Groups 
>> "opencog" group.
>> To unsubscribe from this group and stop receiving emails from it, send an 
>> email to [email protected].
>> To post to this group, send email to [email protected].
>> Visit this group at https://groups.google.com/group/opencog.
>> To view this discussion on the web visit 
>> https://groups.google.com/d/msgid/opencog/CACYTDBdGNipWfnguuZY%2ByyGtnCxAKoXfqoTiYMSsGcqj0rQ5Mw%40mail.gmail.com.
>> For more options, visit https://groups.google.com/d/optout.
>
> --
> You received this message because you are subscribed to the Google Groups 
> "opencog" group.
> To unsubscribe from this group and stop receiving emails from it, send an 
> email to [email protected].
> To post to this group, send email to [email protected].
> Visit this group at https://groups.google.com/group/opencog.
> To view this discussion on the web visit 
> https://groups.google.com/d/msgid/opencog/1F463D95-D0D5-4B95-9D4D-092C0EEFDDFC%40gmail.com.
> For more options, visit https://groups.google.com/d/optout.



-- 
Ben Goertzel, PhD
http://goertzel.org

Super-benevolent super-intelligence is the thought the Global Brain is
currently struggling to form...

-- 
You received this message because you are subscribed to the Google Groups 
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/opencog.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/opencog/CACYTDBepQVSPMh__wu%2BR2yUjQmCT6ofUr0enxcJttGM0Xbamzg%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to