1.
Theory of
AI4U
Algorithm Steps: Code the Instantiate Mind-Module
/^^^^^^^^^\ Instantiate Associates Psi Concepts /^^^^^^^^^\ / EYE \ PSI _____ / EAR \ / \ MINDCORE /New- \ / \ | _______ | CONCEPTS _______ (Concept)-|-------------\ | | /old \ | | | | / Old- \ \_____/ | Audition | | | / image \---|----+ | ( Concept )---|------|----------\ | | | \ recog / | | | | \_______/----|------|-------\ | | | | \_______/ | a| | | | \ __|___ | c | | | | | | b|C| | ___V____ \/ POS \ | a | | | | | visual | s|O|f| / \ ( Parser ) | t | | | | | | t|N|i| ( Activate ) \______/ | s-/ | | | | memory | r|C|b| \________/ |noun? | | | | | | a|E|e| ___|_____ |verb? | e | | | | remembrance | c|P|r| / \ |adj.? | a | | | | | t|T|s| / spreadAct \ |adverb? | t-----/ | | | channel | |_|_| \___________/ |prep.? | | | | _______ | /Mind-\/ ___________|conj.? | f | | | /new \ |( Core ) /INSTANTIATE\ | a | | | / percept \---|-\"Psi"/-/ psi enx seq \ | u | | | \ engram / | \___/ ( act pos ) | n | | | \_______/ | \ jux pre / | a------/ | | | \___________/ | |http://mind.sourceforge.net/diagrams.html shows a Theory of Mind.
In the Robot AI Mind, a concept is the representation in
software of a long neuronal fiber branching out physically
into thousands of synapses and logically into a long chain
of associative nodes, each potentially connecting the
concept fiber by associative tag to another concept fiber
or to an engram in a sensorimotor memory channel.
In order to simulate synapses on nerve fibers, the Mind software
uses associative tags on elements in a semantic memory array.
2. Instantiate Creates Associative-Tag Nodes
Instantiate creates the software tags to represent synapses.
Each position in the synaptic tag-panel of a concept node may
contain a number to represent an associated concept, or a level
of activation, or the grammatical category of a concept-fiber.
As the advancing front of consciousness fills in the genetically
tabula rasa
mindgrid, the Instantiate module silently affixes
associative tags to each node or instance of a concept, so that
the concept remains active and recallable over time, and so that
machine learning may occur by virtue of the making and changing
of conceptual ideas in the knowledge base of the artificial Mind.
http://mind.sourceforge.net/ai4u_157.html
is an overview of Mind.
// psiExam() is a method of psiNode()
// for access to mindcore Psi concept nodes.
function psiExam() { // ATM 1aug2002; or your ID & date.
psi0 = this.psi;
psi1 = this.act;
psi2 = this.jux;
psi3 = this.pre;
psi4 = this.pos;
psi5 = this.seq;
psi6 = this.enx;
} // End of psiExam method of psiNode().
// psiNode() is called from Instantiate()
// to create or modify a Psi concept node:
function psiNode(psi,act,jux,pre,pos,seq,enx) {
this.psi = psi; // mindcore Psi concept;
this.act = act; // activation level;
this.jux = jux; // juxtaposed modifier;
this.pre = pre; // previous associand;
this.pos = pos; // part-of-speech;
this.seq = seq; // subsequent associand;
this.enx = enx; // transfer to En(glish)
this.psiExam = psiExam; // a method of this object.
} // End of psiNode; return to Instantiate().
// Instantiate() is called from the Parser
// module to create a new node of a concept.
function Instantiate() { // ATM 1aug2002; ID & date.
Psi[t] = new psiNode(psi,act,jux,pre,pos,seq,enx);
} // End of Instantiate; return to the Parser module.
\ INSTANTIATE is called from the PARSER
\ module to create a new node of a Psi concept.
: INSTANTIATE \ ATM 3aug2002; or your ID & date.
( concept fiber psi ) psi @ t @ 0 psi{ !
( Set "act" activation level. ) act @ t @ 1 psi{ +!
( Store JUXtaposition tags. ) jux @ t @ 2 psi{ !
( Store PREvious associand. ) pre @ t @ 3 psi{ !
( Store functional pos code. ) pos @ t @ 4 psi{ !
( Store the subSEQuent tag. ) seq @ t @ 5 psi{ !
( Store the EN-transfer tag. ) enx @ t @ 6 psi{ !
( Reset for safety. ) \ 0 seq ! 0 enx !
; \ End of INSTANTIATE; return to Parser module.
5. Analysis of the Modus Operandi
Instantiate gathers up the various flags for associative tags and
creates a new node at the freshest extremity of a concept fiber.
By virtue of new associations, a concept may shift over time and
the artificial Mind may learn and unlearn conceptual knowledge.
The same Psi concept may transfer activation to vocabulary words
in several human languages spoken by the artificial Mind. If the
AI Mind speaks three languages, say, German, English and Japanese,
then the deVocab() and enVocab() and jaVocab() modules will all
receive activation from any Psi concept that is to be expressed
as an element of thought in a particular human language.
AI programmers of a polyglot AI Mind need to determine whether
the transfer-to-English "enx" flag must be joined by additional
transfer-to-German "dex" flags and transfer-to-Japanese "jax"
flags in a mind with Deutsch(), English() and Japanese()
modules, or whether the "enx" flag, renamed or not, will work
with any number ad libitum of natural languages by dint of
transferring activation always to the appropriate vocabulary
module for the particular moment in time "t" at which the Psi
node was established in the first place. In such a felicitous
case, "enx" may simply become the lexical "lex" flag, because
there is no "le" language designation in between Latin "la" and
Lingala "ln" in the ISO 639 "Code for the representation of names
of languages" upon which deVocab() and jaVocab() are based.
Any person or nation wishing to code a monolingual AI Mind in one
of the ISO 639 natural human languages may simply replace the
English() module with a module for the new language and replace
enVocab() likewise with a vocabulary module for the new language.
Note however that the same unchanged auditory memory channel will
accommodate one and all natural human languages, just as we human
beings have only one auditory perception system in our sensorium --
which, by the way, need be expressed as only one Sensorium module
in the AI Mind, no matter how many languages the robot may speak.
To build an AI Mind that speaks two or more languages, AI coders
will probably devise an extra tag in the oldConcept() module to
recognize that a particular incoming word in the input stream
belongs to a particular human language, the syntax of which ought
now to be invoked if most of the incoming words are recognizably
elements of the vocabulary of the particular language. In other
words, speak German to the AI, and it will answer you in German.
Switch abruptly to Japanese, and the AI will use its Japanese()
syntax module and its jaVocab() lexicon module to reply to you.
6. Troubleshooting and Robotic Psychosurgery
The Instantiate module is so simple and straightforward that,
instead of malfunctioning itself, it is more likely to develop
problems caused by other modules such as newConcept and
oldConcept, which prepare the associative-tag data that will
be assigned during the operation of the Instantiate module.
Nevertheless, the overall functionality of an AI Mind may
develop bugs so mysteriously hidden and so difficult to
troubleshoot that a savvy Mind whisperer or AI coder
extraordinaire will know from expert experience that it
pays to troubleshoot the Instantiate module, which is probably
not malfunctioning, in order to track down elusive bugs
which drive bourgeois, clock-watching AI code maintainers to
distraction and despair. When management finally calls in the
True AI expert, the schadenfreudig hired hands will crowd
around the high-security superuser debugging console and hope
to watch the AI coding legend fail as miserably as they have.
Years later the stories will still be told about how the
obviously inept and overpaid AI guru wasted everybody's time
by troubleshooting the [fail-safe] Instantiate module and somehow
miraculously found the bug that nobody else could even describe
let alone pinpoint, thus fixing the unfixable and saving the
mission-critical stream of AI consciousness that was threatening
mayhem if not TEOTWAWKI -- the end of the world as we know it.
A guruvy way to troubleshoot Instantiate is to temporarily set
the AI software to come up already running in the "Diagnostic"
troubleshooting mode. In either Forth or JavaScript, the same
technique that starts the AI Mind in tutorial mode may be used
to start the AI in diagnostic mode. In JavaScript it may be
the judicious use of "CHECKED" in the control panel code,
and in Forth it may be the setting of a numeric mode-variable.
In Forth one may halt the AI and run the ".psi" diagnostic tool.
The overall Mind functionality bugs that can be tracked down
by troubleshooting Instantiate can be maddeningly difficult
to diagnose and tend to have an etiology rooted either in
the [spreading activation] subsystem or in the associative-tag
subsytem that comes to a head in the Instantiate mind-module.
AI code maintainers may be so accustomed to looking for thought-
bugs in the activation subsystem that they forget to consider
the associative subsystem on which all the activation-levels
are riding. It does no good to have perfectly tuned conceptual
activation parameters if the associative routing mechanisms
are out of whack.
A systemic Mind bug is evident when the AI fails to maintain
a meandering chain of thought or outputs spurious associations
instead of the true and logical associations that would reflect
accurately the knowledge base (KB) accumulating in the AI Mind.
One troubleshoots the associative Instantiate subsytem by
examining the contents of the conceptual Psi array as shown
in diagnostic mode. For every thought generated by the AI,
there must be a record of its mental construction archived
in the panel of associative tags for each constituent concept.
A proficient AI coder is able to examine the associative-tag
engrams and reconstruct the thought in natural human language.
An even savvier AI guru will check not only the immediate
area of a spurious thought for clues about what went wrong,
but will identify the designations of the concepts involved
and will search out nearby instances of the same concepts
to make sure that the appropriate associative tags are being
assigned properly by the Instantiate module in conjunction
with other mind-modules that prepare the tags for assignment.
It is definitely not the case that an AI Mind, once it is
functioning properly, will never again suffer systemic Mind bugs.
Adding any new functionality to a primitive AI Mind potentially
upsets the system as a whole and permits the [emergence] of
either conceptual activation bugs or associative
mindgrid bugs.
Porting an AI Mind from one programming language to another
is almost sure to cause systemic Mind bugs. Installing an AI
Mind in a robot embodiment may engender systemic Mind bugs.
Comes a Singularity, nothing can be done to keep a self-modifying
AI codebase from suicidal extinction by genetic trial and error.
7. Instantiate and Concept-Formation Resources for
Seed AI Evolution
