Mike,
 
Mike wrote:
>What kind of problems have you designed this to solve? Can you give some 
>examples?
 
Natural language understanding, path finding, game playing
 
Any problems that can be represented as a situation in the four component 
domain (value - role - relation -  feature models) can be 3-C (compared, 
contrast, combined) to give a resulting situation (frame pattern).  What is 
combined/compared/or contrast?:  only the regions under attention, including 
its focus detail level are examined.  What is placed and represented in the 
regions determines what component can be 3-C analyzed... as a general computing 
paradigm using 3-C (AND - OR - NOT).
 
 
Example:
Here's a pattern example you may not have seen before, but by 3C you discover 
the pattern and how to make an example:
 
As spoken aloud:
five and nine    [is]   fine
two and six     [is]   twix
five and seven  [is]   fiven
 
Take the "five and seven = fiven".
when the system compares the resultant of "fiven" to "five" ..the result is 
that "five" is at the start of the situation.
When it compares "fiven" and "seven"... the result is that "ven" is at the end 
position.
 
resulting situation PATTERN = 
[situation 1 ][ focus inward ] [ start-position ]    combined with 
[situation 2 ][ focus inward ] [ end position  ]
(Spatial and sequence positions are a key part of the representation system)
 
How was the correct (reasoning) method chosen?
This result was was by comparison; it could have been by contrasting.  All 
three Compare, Contrast and Combine happen symultaneously.  The winner is 
whichever resulting situation makes sense to the system has the most activation 
in the value area (some direct or indirect value from past experience or value 
given by the "authority system" in the value region: e.g. fearful or attractive 
spectrum).
 
How was the correct region and focus detail level chosen?
The attention region in the example was on the sound region, the focus detail 
was on the phoneme level (syllable), it could have looked for patterns in the 
number values or the emotions related to each word, or the letter patterns,  or 
hand motions, eye position when spoken, etc).  The regions are biased by the 
value system's current index (amygdala/septum analog): e.g. when you see "five" 
the quantity region will be given a lower threshold, and the focus level 
associated will give the content on the 1 - 10 scale. The index region weights 
are re-organized only by stronger reward/failure (authority system), 3-C 
results can on the index changing the content connections weights.
 
Now you compare apples to oranges for an encore; what do you get? a color, a 
taste, a mass, a new fruit..your attention determines te result
 
All regions are being matched for patterns in the 2 primary index modules 
(action selection, emotional value,..others can be integrated seamlessly).
 
Five and seven is not "fiven", it is twelve, but in this situation it makes 
sense to the circumstances.  Sense and meaning are contextual for the model, 
for humans.
 
 
Hope this sheds light. Detailed paper has been in the works.
Robert
 
--- On Sun, 12/28/08, Mike Tintner <[email protected]> wrote:

From: Mike Tintner <[email protected]>
Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] 
AGI Preschool: sketch of an evaluation framework for early stage AGI systems 
aimed at human-level, roughly humanlike AGI
To: [email protected]
Date: Sunday, December 28, 2008, 4:49 PM

Robert,
 
What kind of problems have you designed this to solve? Can you give some 
examples?
Robert:
 
A brief paper on an AGI system for human-level  ...had only 2 pages to fit in.
 
If you are working on a system, you probably hope it will one day help design a 
better world, better tools, better inventions.  The better is a subjective 
human value.  A place for or human-like representation of  at least rough, 
general human values  (bias, likes) in the AGI is essential.
 
The paper give a quick view of the Human-centric representation and behavioral 
systems approach for problem-solving, reasoning as giving meaning (human 
values) to stories and games...Indexing relations via spatially related 
registers is it's simulated substrate.
 
Happy Holidays,
Robert
 
...all the human values were biased, unlike the very objective AGI systems 
designed on the Mudfish's home planet; AGI systems that objectively knew that 
sticky mud is beautiful,  large oceans of gooey mud..how enchanting!  Pure 
clean water, now that's fishy!"
  

--------------------------------------------------------------------------------
agi | Archives  | Modify Your Subscription  


--- On Sun, 12/28/08, Mike Tintner <[email protected]> wrote:

From: Mike Tintner <[email protected]>
Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] 
AGI Preschool: sketch of an evaluation framework for early stage AGI systems 
aimed at human-level, roughly humanlike AGI
To: [email protected]
Date: Sunday, December 28, 2008, 4:49 PM





Robert,
 
What kind of problems have you designed this to solve? Can you give some 
examples?

Robert:





 
A brief paper on an AGI system for human-level  ...had only 2 pages to fit in.
 
If you are working on a system, you probably hope it will one day help design a 
better world, better tools, better inventions.  The better is a subjective 
human value.  A place for or human-like representation of  at least rough, 
general human values  (bias, likes) in the AGI is essential.
 
The paper give a quick view of the Human-centric representation and behavioral 
systems approach for problem-solving, reasoning as giving meaning (human 
values) to stories and games...Indexing relations via spatially related 
registers is it's simulated substrate.
 
Happy Holidays,
Robert
 
...all the human values were biased, unlike the very objective AGI systems 
designed on the Mudfish's home planet; AGI systems that objectively knew that 
sticky mud is beautiful,  large oceans of gooey mud..how enchanting!  Pure 
clean water, now that's fishy!"
 






agi | Archives  | Modify Your Subscription



-------------------------------------------
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b
Powered by Listbox: http://www.listbox.com

Reply via email to