Edited wiki page InFerence through web user interface.

wiki/InFerence.wiki

@@ -1,196 +1,106 @@
#summary Creates new ideas by reasoning from old ideas
#labels module,logic,thinking

=== Diagram === 
MileStones SuperIntelligence ThInk
=== Theory === 

The Mentifex AI Minds began to incorporate *inference* in December of 2012, when it became clear that the AI could use two facts to create a third fact as a logical inference by replacing the subject of a general statement ("Birds have wings") with the subject of a specific statement ("An eagle is a bird") to create a silent inference: "Eagles have wings."

=== Algorithm === 

MindForth uses the input of a BeVerb statement ("Boys are kids") to trigger the calling of the InFerence module, which then changes the knowledge-base idea "Kids make robots" by replacing the general subject "Kids" with the specific subject "Boys" to infer, "Boys make robots." 

=== Code === 

{{{
   /^^^^^^^^^\  Reason infers semantic DarkMatter  /^^^^^^^^^\
  / visual    \  (inferred structures are below)  / auditory  \
 /  memory     \                                 /  memory     \
|   _______     |                               |               |
|  / image \----|--------- DarkMatter ----------|--- d          |
| /  of a   \   |                               |     o         |
| \  dog    /---|------- associative tag --+----|----- g        |
|  \_______/    |                          |    |               |
|               |    a|C|f|        | | + | |    |               |
|               |    b|O|i|        + | | | |    |               |
|               |    s|N|b|        | | | + |    |               |
|               |    t|C|e|        | + | | |    |               |
|               |    r|E|r|        + | | | |    |               |
|               |    a|P|s|        | | | | +    |               |
|   _______     |    c|T| |        | | + | |    |   ________    |
|  /new    \    |    t|_|_|_       |_|_|_|_|    |  /        \   |
| / percept \   |    /Psi   \-----/ English \---|-/ Auditory \  |
| \ engram  /---|---/concepts\---/  lexicon  \--|-\ phonemes /  |
|  \_______/    |   \________/   \___________/  |  \________/   |
: InFerence ( create silent triples for machine reasoning )
  CR ." InFer: subjnom prednom = " \ test; 18dec2012
  subjnom @ . prednom @ . CR \ test; 18dec2012
  midway @ t @ DO \ search IdeaPlex to infer facts; 18dec2012
    I 0 psi{ @ prednom @ = IF \ KB data? 18dec2012
      I 4 en{ @ 1 = IF \ nominative? 18dec2012
        seqverb @ 0 = IF \ only once; 18dec2012
          I 6 psi{ @ seqtqv ! \ transfer; 18dec2012
          I 7 psi{ @ seqverb ! \ transfer; 18dec2012
          seqverb @ seq ! \ test; 18dec2012
        THEN \ end of test for not-yet-declared; 18dec2012
        CR ." InFer: t psi seqverb = " \ test; 18dec2012
        I . prednom @ . seqverb @ . \ 18dec2012
      \ LEAVE \ at first make only one inference; 18dec2012
      THEN \ end of test for nominative; 18dec2012
    THEN \ end of test for finding prednom facts; 18dec2012
  -1 +LOOP \ end of backwards loop; 18dec2012
  1 t +! \ increment time "t" by one for a gap; 18dec2012
  1 t +! \ increment time to create an inference; 18dec2012
  subjnom @ t @ 0 psi{ ! \ subj of inference; 18dec2012
          5 t @ 5 psi{ ! \ pos=5 noun; 18dec2012
      \ 999 t @ 6 psi{ ! \ test; remove; 18dec2012
   t @ 1 + t @ 6 psi{ ! \ psi6=tqv; 18dec2012 
  CR ." InferB: storing seqverb = " seqverb @ . \ 18dec2012 
  seqverb @ t @ 7 psi{ ! \ seq is the verb; 18dec2012
  subjnom @ t @ 8 psi{ ! \ enx; 18dec2012
  1 t +! \ increment t for storage of verb; 18dec2012
  seqverb @ t @ 0 psi{ ! \ verb of inference; 18dec2012
  subjnom @ t @ 4 psi{ ! \ pre of verb; 18dec2012
          8 t @ 5 psi{ ! \ pos=8 verb; 18dec2012
        seqtqv @ 7 psi{ @ t @ 7 psi{ ! \ seq 18dec2012
  seqverb @ t @ 8 psi{ ! \ enx; 18dec2012 
  1 t +! \ increment t to store direct object; 18dec2012
  seqtqv @ 7 psi{ @ t @ 0 psi{ ! \ dir. obj 18dec2012
  seqtqv @ 7 psi{ @ t @ 8 psi{ ! \ enx 18dec2012 
  1 t +! \ increment time "t" for an ending gap; 18dec2012
  0 becon ! \ reset after use; 18dec2012
  0 prednom ! \ reset after use; 18dec2012
  0 seqtqv ! \ reset after use; 18dec2012
  0 subjnom ! \ reset after use; 18dec2012
\ QUIT \ test; remove; 18dec2012
; ( http://code.google.com/p/mindforth/wiki/InFerence )
}}}

=== Purpose === 

MindForth does not yet include an inference module, but the time 
is ripe to implement one. We illustrate the nature of an inference 
module by discussing a particular inference that once launched 
the very creation of MindForth as an artificial intelligence.

In the early years of the Mentifex AI project, we could visualize 
a MindGrid of sensory memory channels such as vision holding 
image engrams and audition holding word-engrams. We could 
imagine a one-to-one, two-way correspondence between an image 
in the visual memory channel and a word to describe or name 
the image in the auditory memory channel. Thus, for instance, 
an image of a dog could associate to the word "dog" and vice 
versa. At the time, it was an OpenQuestion whether the 
sensory memory channels led to a Central Processing Unit (CPU) 
where thinking occurred, or whether something like a 
homunculus intervened to engender thinking about the 
perceptions streaming through the sensory memory channels. 

As we performed one GedankenExperiment after another to 
elaborate the design of an AiMind, we came to the question 
of how the perception of multiple images in the visual 
memory channel would cause the AiMind to activate the 
memory of a plural noun in the auditory memory channel. 
For instance, if an AI-equipped robot saw not one dog 
but two or three dogs in a field of vision, how would 
not simply the word "dog" but the plural word "dogs" 
come to mind? If there is a one-to-one association 
between each image of a dog and the word "dog", 
how do multiple associations from multiple dogs 
add the extra phoneme "s" to make the word "dogs"?

The old, pre-inference knowledge goes something like 
the following.

Each image of a dog activates the word "dog" in memory. 

Multiple dog-images can not directly activate the word "dogs".

Seeing multiple dogs activates something extra beyond "dog".

The extra activation for noun-plurals is the "s" phoneme.

Something extra is happening somewhere in the MindGrid. 

The most likely venue for extra processing is in the middle 
between the memory channels, not at a CPU destination.

Inference: There is something extra in the middle of the MindGrid, 
between the visual memory channel and the auditory memory chanel.

When we made the above inference, we were stymied for several 
months as to the implications of the inference and the 
nature of the semantic DarkMatter that we had yet to 
describe, but it was an unshakeable inference. 
We positively KNEW that an abstract memory channel 
was mediating the sensory memory channels, even 
though we were originally dumbfounded as to what 
was the nature of the abstract memory channel. 
It was truly the DarkMatter of the MindGrid. 
It had to be there, but it was invisible. 
Only Reason could tease out the nature of the DarkMatter. 

We switched from considering how multiple images 
would cause the activation of noun-plurals to the 
more compelling consideration of how the visual 
observation of motion would lead to the fetching 
of verbs of motion in the auditory memory channel.

Building upon the idea of nerve fibers holding 
traces of sensory memory, we developed the idea 
of abstract fibers holding abstract concepts 
apart from concrete sensory memories. We designed 
a linguistic SuperStructure emerging not physically, 
but logically, in the otherwise flat plane of 
the MindGrid. Eventually we started coding software 
to implement the artificial Mind resulting from 
the one crucial inference of MindGrid DarkMatter.

Eventually we put the software on Google Code 
where you are reading about it now. And in 
the immortal words of Martin Luther:
=== Report === 

{{{
 Hier stehe ich. 
 Ich kann nicht anders.
 Gott huelfe mir.
 [the innate knowledge base KB about kids:]
583 : 528 -7 2 0 0 5 588 835 528 to KIDS
588 : 835 15 2 0 72 8 595 571 835 to MAKE
595 : 571 23 2 0 835 5 0 0 571 to ROBOTS
602 : 571 0 2 0 0 5 473 74 571 to ROBOTS
607 : 849 0 2 0 571 8 610 701 849 to NEED
610 : 701 0 1 0 849 7 0 0 701 to ME
  [three words of human input come in:]
617 : 589 16 1 0 0 5 621 800 589 to BOYS
621 : 800 0 1 0 589 8 626 528 800 to ARE
626 : 528 -15 2 0 589 5 0 0 528 to KIDS
  [AI creates an inference about boys:]
628 : 589 6 0 0 0 5 629 835 589 to BOYS
629 : 835 15 0 0 589 8 0 571 835 to MAKE
630 : 571 12 0 0 0 0 0 0 571 to ROBOTS
636 : 528 -13 2 0 0 5 641 835 528 to
641 : 835 -31 0 0 528 8 649 571 835 to MAKE
649 : 571 -15 2 0 528 5 0 0 571 to ROBOTS
time: psi act num jux pre pos tqv seq enx
}}}

=== Entelechy === 
=== Logic === 

TBA 
Now that the InFerence module exists, it may be expanded to incorporate logical operations such as if-then conditions.

=== Code === 
=== Superintelligence === 

http://code.google.com/p/mindforth/wiki/ForthMindTextFile will show the AI source code of the inference module when it has been implemented, and will permit operational inspection of the inference functionality when the AI software is running. First the http://www.winzip.com compression utility for Windows must be used to extract and auto-install the http://prdownloads.sourceforge.net/win32forth/W32FOR42_671.zip?download of the Win32Forth language into which the AI source code is loaded. See the UserManual for instructions. 


=== Operation === 

In the planning phase for an inference module, we envision that 
the module will originally operate by thinking up questions to ask. 
It is inherent in the current functionality of the AiMind that 
a question not answered by a human user defaults to the assumption 
that the AiMind itself will try to answer its own questions. 
Therefore posing a question is an early step in the reasoning 
process that may lead to an inference. Since the first steps at 
making inferences may be rather feeble and may involve such 
simple-minded questions that the answers are extremely obvious, 
it makes sense to have the AiMind throw out questions for human 
users to answer. In the public setting of a ScienceMuseum or 
other such venue, human visitors could take turns in answering 
the questions put out by the AiMind. If the AI were not turned off 
at night and could constantly add to its body of knowledge by 
quizzing human visitors, we can imagine quite a scenario of 
the gradual emergence of SuperIntelligence. 

Since the http://AIMind-i.com offspring of MindForth has the 
ability to go out and surf the Web, it could think up questions and 
seek the answers not directly from human users, but from webpages. 

At any rate, one method of formulating questions in automated reasoning 
would be to switch subjects, verbs and direct objects inside the "old" 
knowledge of the AI and try to find "new" knowledge by asking questions. 
For instance, from "Cats eat fish" the AI could ask a questions by 
switching from "cats" to "bears" and asking, "Do bears eat fish?" 
A human child in a ScienceMuseum might enjoy answering dozens of 
such questions, thus educating the AI trapped inside a computer. 

The inferential questions asked by an AiMind will be more sophisticated 
if the inference module software follows the "Is-a" pathways from 
one subject-noun or object-noun contained in "old" knowledge to 
candidate subject-nouns and object-nouns for the inference of 
"new" knowledge. For instance, if the AiMind knows that "cat" 
"Is-a" animal, the AI could substitute various other animals 
and ask questions to learn just how similar each other animal is 
to a cat. By sheer luck, a primitive AI might ask (and receive 
answers to) important questions that no sensible human being 
would even bother to ask (and stumble upon a valuable inference). 
As the AI becomes more sophisticated, pruning of the askable 
questions would occur as activation spreads more and more to 
the best questions to ask, and skips fruitless lines of inquiry. 
Since MindForth already has the mechanics of SpreadingActivation, 
MindForth is poised for the implementation of an inference module. 


=== Debug === 

TBA 

=== Links === 

http://www.agiri.org/wiki/Inference_Control 

http://www.mail-archive.com/agi@v2.listbox.com/msg09748.html 

http://groups.google.com/group/sci.logic 

*NARS (Non-Axiomatic Reasoning System)* 
  * http://www.agiri.org/wiki/NARS 
  * http://code.google.com/p/open-nars
Once the AI Minds like [http://www.scn.org/~mentifex/mindforth.txt MindForth] in English, [http://www.scn.org/~mentifex/DeKi.txt Wotan] in German, and [http://www.scn.org/~mentifex/Dushka.html Dushka] in Russian start to employ complex logic in the modules for inference, a speed-up and a smarten-up may begin to occur, culminating in SuperIntelligence.

=== Wikipedia === 
  * http://en.wikipedia.org/wiki/Automated_reasoning 
  * http://en.wikipedia.org/wiki/Inference_engine 
  * http://en.wikipedia.org/wiki/Is-a 
  * http://en.wikipedia.org/wiki/Logic 
  * http://en.wikipedia.org/wiki/Reasoning 
  * http://en.wikipedia.org/wiki/Syllogism 
  * http://en.wikipedia.org/wiki/Syllogism 

=== AI For You === 

Click to run 

[http://www.scn.org/~mentifex/AiMind.html http://farm1.static.flickr.com/51/179758367_f283f0d6e0_s.jpg] 

AI For You