On Tue, Dec 18, 2012 at 10:21 AM, A. T. Murray <[email protected]> wrote:
> Logan Streonj wrote:
> >
> >how about using kind of a cognitive net, similar to brain.
> >words are linked to other words.
> >i.e. eagles is a bird, links eagle to bird,
> >birds have wings, links birds to wings.
>
> The Mentifex AI Minds do something similar to the above.
>
> >
> >Ideally it could actually integrate grammar I guess.
> >where of is parent and for is child
> >bird for eagle crow has wings beak feathers
> >eagle of bird
> >
> >so eagle inherits all the has attributes of bird
> >therefore eagle has wings, beak, feathers
>
> The above seems to be the goal for inference :-)
> >
> >that's probably how i'd implement it in HSPL if I was that far along.
>
> Please tell us all what "HSPL" stands for.
>
Human Speakable Programming Language
though if I'm not mistaken such logical inferences already come standard in
logical languages like Prolog.
>
> Meanwhile, over the night I have coded about
> half of the InFerence module for MindForth:
>
> : 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
> CR ." InFer: t psi seq = " \ test; 18dec2012
> I . prednom @ . I 7 psi{ @ . \ 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
> 1 t +! \ increment time "t" for an ending gap; 18dec2012
> 0 becon ! \ reset after use; 18dec2012
> 0 prednom ! \ reset after use; 18dec2012
> 0 subjnom ! \ reset after use; 18dec2012
> ; ( http://code.google.com/p/mindforth/wiki/InFerence )
>
> ****
>
> Transcript of Forthmind 20121218 interview at 7 40 53 o'clock on 18
> December 2012.
> boys
> OldC: pov pos oldpsi subjnom prednom = 42 5 589 589 0 are
> OldC: pov pos oldpsi subjnom prednom = 42 8 800 589 0 kids
>
>
>
> OldC: pov pos oldpsi subjnom prednom = 42 5 528 589 528
> InFer: subjnom prednom = 589 528
>
> InFer: t psi seq = 626 528 0
> InFer: t psi seq = 583 528 835
> Robot: KIDS
> OldC: pov pos oldpsi subjnom prednom = 35 5 528 0 0 MAKE
> OldC: pov pos oldpsi subjnom prednom = 35 8 835 0 0 ROBOTS
> OldC: pov pos oldpsi subjnom prednom = 35 5 571 0 0
>
> Robot: KIDS MAKE 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
> 617 : 589 17 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
> 628 : 589 0 0 0 0 0 0 0 0 FIRST CREATION OF AN INFERENCE!
> 634 : 528 -14 2 0 0 5 639 835 528 to
> 639 : 835 -31 0 0 528 8 647 571 835 to MAKE
> 647 : 571 -15 2 0 528 5 0 0 571 to ROBOTS
> time: psi act num jux pre pos tqv seq enx
>
> ****
>
> The above report shows that at time point t=628
> an instance of the concept 589=BOYS was created,
> but with no other data fleshing out the inference.
> As the code grows to completion, one or more
> such "silent records" will constitute inference --
> new knowledge created by the AI itslef and not
> directly told to the AI by a human user.
>
> Mentifex (Arthur)
> --
> http://cyborg.blogspot.com
>
>
Hmmm one of the reasons I decided not to code in forth was that it lacked
case grammar, which is actually lacked by most if not all programming
languages, so is why I'm making HSPL as it does support these basic
Linguistic Universals.
>
> -------------------------------------------
> AGI
> Archives: https://www.listbox.com/member/archive/303/=now
> RSS Feed: https://www.listbox.com/member/archive/rss/303/5037279-a88c7a6d
> Modify Your Subscription:
> https://www.listbox.com/member/?&;
> Powered by Listbox: http://www.listbox.com
>
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription:
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com
