Synopsis
/^^^^^^^^^\ Thinking with Subject-Verb-Object /^^^^^^^^^\ / visual \ _______ / auditory \ / memory \ / S-V-O \ / memory \ | channel | / English \ | channel | | | \ syntax /---|-------------\ | | /--------|--------\ \_______/ | | | | | recog-|nition | | | | | | ___|___ | ___V__ ___V_ | ________ | | | /image \ | / \ fex / \ rv | / \ | | | / percept \---|---/Psi EnX \-----/English\----|-/ audNode \| | | \ engrams /---|---\concepts/-----\lexicon/----|-\ phonemes / | | \_______/ | \______/ fin \_____/ utg | \________/ |diagrams.html shows a Theory of Mind.
There is in the AI Mind a Short Term Memory (STM) module but
not a Long Term Memory (LTM) module because the AI algorithm
is based on the idea that the only difference between STM and LTM
lies in how engrams are recalled and re-activated in a lifelong
memory channel (see diagram above) when the short term lapses
into the long term. Although in neuroscience the thalamus (q.v.)
may be regarded as the locus of a selective attention system
to process short term memory, Occam's Razor
("Entia non sunt multiplicanda praeter necessitatem.")
demands that we not design more mental machinery and more
systems of memory deposition than we need to get the
Cartesian "Cogito ergo sum" job done.
If anyone successfully demands that there be an LTM module in
the AI Mind to go along with the STM module, that long-term
memory module will not be a separate storage area for
long term memory (LTM) but will rather be special processing
mechanisms of the same data that were originally laid down
in what we by default call the short term memory (STM).
If a rudimentary AI Mind has only the sense of audition in
Short Term Memory but still manages to think purely in terms
of acoustic words and how they relate logically to one another,
then such an AI has very little real knowledge of the real world.
Therefore the Short Term Memory must be expanded into multiple
senses coordinated with associative tags linked into the
linguistic system of syntax for generating sentences of thought,
so that the AI Mind may not only have real knowledge in its
knowledge base (KB) but also be able to discuss its knowledge.
mindloop.html is a flowchart of Mind.
// audExam() is a method of audNode()
// and provides access both to pho(nemes)
// stored in audition and their tags/flags.
// 19sep2001 Mind.Forth order 0-5:
function audExam() {
aud0 = this.pho;
aud1 = this.act;
aud2 = this.pov;
aud3 = this.beg;
aud4 = this.ctu;
aud5 = this.utg;
}
// audNode() is called from Short Term Memory "STM()"
// and other functions which need to create, activate,
// or deactivate an auditory memory node ("audNode").
function audNode(pho,act,pov,beg,ctu,utg) {
this.pho = pho; // phoneme
this.act = act; // activation level
this.pov = pov; // point-of-view: internal/external
this.beg = beg; // beginning of a word?
this.ctu = ctu; // continuation of a word?
this.utg = utg; // ultimate-tag over to a concept
this.audExam = audExam;
}
// STM() is called from Audition() +/- CR()
// and stands for "Short Term Memory":
function STM() {
if (attn > 1) {
Comparator();
}
tult = (t - 1); // the time "t-ultimate".
// See if previous auditory node was blank:
audMemory[tult].audExam();
// possibly use from Usenet: parseInt(act)+8
// after any blank, beg(inning) is primed to be true:
if (aud0 == 0) beg = 1;
audMemory[t] = new audNode(pho,0,pov,beg,ctu,utg);
return;
}
\ STM is called from AUDITION
\ and stands for "Short Term Memory":
: STM
unk @ 32 > IF COMPARATOR THEN ( ASCII 32 = SPACE-bar )
t @ 1- 0 aud{ @ 0= IF 1 beg ! THEN
unk @ t @ 0 aud{ ! \ Store the unk phoneme at time t
0 t @ 1 aud{ ! \ Store no act(ivation) level.
pov @ t @ 2 aud{ ! \ point-of-view: internal #, external *
beg @ t @ 3 aud{ ! \ beg(inning)? 1 Yes or 0 No.
ctu @ t @ 4 aud{ ! \ continuation? 1=Y or 0 = No.
utg @ t @ 5 aud{ ! \ u(ltimate) t(a)g # to a concept.
unk @ 32 = IF t @ blankt ! THEN
; \ Return to AUDITION.
The code above stores auditory memory engrams in the acoustic
array aud by inserting an ASCII value for a phoneme ("unk")
along with various flags that achieve in software the wetware
functionality of synapses and associative tags in a human brain-mind.
The flags used in the STM code are perhaps too redundant and too
wasteful of RAM memory space, and so while getting the job done
they invite improvement.
In the AI Mind source code, unk ("unknown") is a general-purpose
variable for anything unknown before an operation proceeds in the
software. The "unk" variable is used mainly in the Audition module
to hold momentarily whatever the human user or the AI itself enters
into the input sensorium. The "unk" variable is also used in other
modules such as Noun-Phrase. So long as coders blank or zero out
any value riding on the "unk" horse, they may cavalierly use "unk"
over and over again for any purpose.
The activation "act" variable is also used in the Spreadact module
to let activation "act" spread from one concept to related concepts.
The string-effect subroutine uses "act" to pass activation from
one character in a word to the next, so that the AI Mind may
recognize a series of characters as a word or as a morpheme.
The beginning "beg" variable is used in the Short Term Memory
module as a flag that tells whether an ASCII character being stored
is the beginning of a word in auditory memory. Although the
underlying AI algorithm must eventually be changed so that the
Mind may deal with subsets of words regardless of whether they
are at the beginning of a stored word, nevertheless the variable
"beg" has been useful to get the primitive AI program running.
The Audition module sets the "beg" (beginning) flag before STM
stores the datum as either a "1" or a zero "0", and the Comparaor
module uses the "beg" flag not explicitly but rather hidden as a
value found, and tested for, in a certain fixed position of the
"aud" array. If the Comparator finds that a stored and matching
character is a "beginning" item (i.e., "beg" = "1"), then the
Comparator initiates the string-effect process of pattern-recognition
by immediately increasing the activation "act" of the beginning item
by a value of eight (or whatever the coder chooses).
On the next pass-through of a subsequent comparand item,
the string-effect subroutine will pass activation down to the
next-in-line character. Temporarily now, the string-effect mechanism
relies on detecting the beginning of a stored auditory engram,
that is, a word, by means of the beginning-flag "beg".
However, this mechanism is too simple for the more advanced
recognitions that the evolving AI Mind needs to achieve,
and so the beginning-flag "beg" may eventually be replaced.
The continuation-flag "ctu" for "aud" array phonemes is set
(given a value) in the Audition module and is stored in the
Short Term Memory (STM). The "ctu" value stored by STM as "1"
or "0" in a panel of "aud" flags comes into play independently
in the Comparator and Speech modules. In the Comparator module,
the variable "ctu" is not explicitly stated but is hidden as
the value in a fixed position on the "aud" array flag-panel
and is tested for so as to find the end of a word stored in
auditory memory. If the "ctu" flag, by no longer holding true
at the end of a word, indicates that the end of a matching
and stored word has been found, then the Comparator module
seizes the ultimate-tag "utg" of the stored word and transfers
the numeric value of "utg" into the move-tag "mt" so that
a new instance of the word may be stored in auditory memory
with the correct "utg" leading to a concept. In the Speech
module, the role of the continuation-flag "ctu" is much simpler,
and once again the "ctu" flag is hidden and is expressed only
by the "1" or "0" value found in a test at a fixed position
of the "aud" panel, so that speech output may stop if the
continuation-flag "ctu", by changing in value from "1" to "0",
indicates that the character or phoneme now being spoken in
Speech is the final item that must be pronounced or displayed
in order to speak the given word.
The ultimate-tag "utg" is an integer number stored with
a quasi-phonemic word in the auditory memory channel array "aud"
and serving to associate or link the "ultimate" phoneme of each
stored word to the concept of the word in the "en(glish)" array.
After running Mind.Forth, one may finish a session by typing in:
.aud [RETURN] in order to see the ultimate-tag "utg" at the
end of each word-engram stored in the auditory memory channel.
The numeric tags are a way of simulating an associative nerve fiber.
The auditory ultimate-tag "utg" goes only inwards to the "En" fiber
"nen" and not vice-versa. The "En" array uses the recall-vector "rv"
to reverse direction, that is, from "En" to a word stored in "aud".
This arrangement is because, although an incoming word is recognized
by its ultimate "utg" sound, the same word, stored in auditory memory,
is reactivated by means of its onset sound "rv" as held onto by
synaptic nodes in the "En(glish)" lexical array.
The point-of-view "pov" flag is a marker in the Short Term Memory
(STM) as to whether a word came from the outside world or from
the mind itself. The Audition module sets the "pov" flag as either a
pound sign (ASCII 35 #) for "internal" or an asterisk (ASCII 42 *)
for an external point of view. In the AI stream of consciousness,
most thoughts will show an internal # sign which looks anyway like
the up-and-down concept fibers of the mindgrid (as described in
Mind/ Docs/ Theory of Mind/ Brain-Mind: Know Thyself!)
with orthogonal associative tags flowing left and right to integrate
the grid. The asterisks for external (*) input already suggest
by common usage that something external to the stated item
has a connection with the item, as in fact the external agent
entering the auditory input may be associated with the input.
In the Oldconcept module, the "pov" flag is used to route
the "fex" or "fin" branching of association from a word being stored
in the auditory memory channel, so that the proper deep mindcore
Psi concept may be tagged associatively to the phonemic word in
the auditory memory channel array aud. With personal
pronouns such as "you" and "I" or "me", it is important that
each pronoun in the mind be associated with the proper concept
from an internal (#) self or external (*) other point of view ("pov").
The "pov" flag has an effect upon self-awareness and consciousness.
[ ] Coordinate multisensory robot STM to flesh out semantic memory of concepts.
[ ] Devise a way to recycle the STM contents within a limited RAM space.
Short Term Memory Resources
Last updated: 13 November 2001
Return to the
top of this page; or to the
index.html Index page; or
sitemap.html Site Map.