mfpj0827

MindForth Programming Journal (MFPJ)
The MindForth Programming Journal (MFPJ) is both a tool in developing MindForth open-source artificial general intelligence (AGI) and an archival record of the history of how the AGI Forthmind evolved over time.

Sat.27.AUG.2016 -- Creating the MindGrid trough of inhibition

In agi00031.F we are trying to figure out why we have lost the functionality of ending human input with a 13=CR and still getting a recognition of the final word of the input. We compare the current AudMem code with the agi00026.F version, and there does not seem to be any difference. Therefore the problem must probably lie in the major revisions made recently to the AudInput module.

From the diagnostic report messages that appear when we run the agi00031.F, it looks as though the 13=CR carriage return is not getting through from the AudInput module to the AudMem module. When we briefly insert a revealing diagnostic into the agi00026.F AudMem start, we see from "g AudMem: pho= 71" and "o AudMem: pho= 79" and "d AudMem: pho= 68" and "AudMem: pho= 13" that the carriage-return is indeed getting through. Therefore in AudInput we need to find a way of sending the final 13=CR into AudMem. Upshot: It turns out that in AudInput we only had to restore "pho @ 31 > pho @ 13 = OR IF \ 2016aug27: CR, SPACE or alphabetic letter" as a line of code that would let 13=CR be one of the conditions required for calling the AudMem module.

Next in the InStantiate module we need to remove a test that only lets words with a positive "rv" recall-vector get instantiated, because we must set "rv" to zero for personal pronouns being re-interpreted as "you" or "I" during communication with a human user. Apparently the Perlmind just ignores the engrams with a zero "rv" and finds the correct forms with a search based on parameters.

Now we would like to see how close we are to fulfilling all the conditions for a proper "trough" of inhibition in the AI MindGrid. When we run the ghost175.pl Perl AI and we enter "You know God," we see negative activations in thepresent-most trough of both the input and the concepts of "I HELP KIDS" as the output. In the Forth AGI, we wonder why do not see any negative activations in the present-most trough. Oh, we were not yet bothering to store the "act" activation-level in the Forth InStantiate module. We insert the missing necessary code, and we begin to see the trough of inhibition in both the recent-most input and the present-most output.

may30jsai

The JavaScript artificial intelligence (JSAI) is a client-side AiApp whose natural habitat is a desktop computer, a laptop or a smartphone.

1 Mon.30.MAY.2011 -- Searching the AI Knowledge Base.

The JavaScript artificial intelligence (JSAI) is now being updated with new code from the MindForth AI, which on 29 May 2011 gained the ability to search its knowledge base (KB) twice in response to a single query and provide different but valid answers by means of the neural inhibition of the first answer in order to arrive next at the second answer. In other words, the JSAI will be able to discuss a subject exhaustively in terms of what it knows about the subject -- a major step in our achievement of the MileStone of self-referential thought on the RoadMap to artificial general intelligence. The AI source code has not yet been fine-tuned. We hope to achieve in JavaScript the basic functionality that has been created in MindForth.

Upshot: After we transferred mutatis mutandis all the pertinent code from MindForth into the AiMind.html program in JavaScript, the JSAI still did not work right. We had to hunt down and fix (by commenting out) some lines of obsolete code in the SpreadAct mind-module, where negative activation values were being reset to zero -- to the detriment of inhibition-values, which need to slowly PsiDecay upwards towards zero. We then achieved JSAI functionality on a par with MindForth. We entered new knowledge into the knowledge base (KB). We queried the KB twice with the same question, and the artificial AI Mind correctly gave us two different answers in complete agreement with the knowledge base.

may26mfpj

The MindForth Programming Journal (MFPJ) is both a tool in developing MindForth open-source artificial intelligence (AI) and an archival record of the history of how the AI Forthmind evolved over time.

1 Thurs.26.MAY.2011 -- Conditional Inhibition

In the recent Strong AI diaspora of MindForth and the tutorial AiMind.html program, we have implemented the neural inhibition of concepts immediately after they have been included in a generated thought. Now we would like to make inhibition occur when one or more responses must be made to a query involving nouns or a query involving verbs. The question "What do bears eat?" is a query of the what-do-X-verb variety involving one or more nouns as potentially valid answers as the direct object of the verb. If the noun of each single answer is immediately inhibited, the AI can respond with a different answer to a repeat of the question. Likewise, if we ask the AI, "What do robots do?", the query is of the what-do-X-do variety where potentially multiple verbs may need to be inhibited so as to give one valid answer after another, such as "Robots make tools" and "Robots sweep floors." If we are inhibiting the verbs, we do not want the direct-object nouns to be inhibited. We might need replies with different verbs but the same direct object, such as "Robots make tools" and "Robots use tools."

Inhibition may also play a role in calling the ConJoin module when a query elicits multiple thoughts which are the same sentence except for different nouns or different verbs. The responses, "Bears eat fish" and "Bears eat honey" could become "Bears eat fish and honey" if neural inhibition suppresses the repetition of subject and verb while calling the ConJoin module to insert the conjunction "AND" between the two answer nouns.

2 Thurs.26.MAY.2011 -- Problems With Determining Number

When we try to troubleshoot the Forthmind by entering "bears eat honey", a comedy of errors occurs. The AudRecog module contains a test to detect an "S" at the end of an English word and set the "num(ber)" value to two ("2") for plural. However, that test works only for recognized words, and not for a previously unknown word of new vocabulary. So the word "bears" gets tagged as singular by default, which causes the AI to issue erroneous output with "BEARS EATS HONEY", as if a singular subject is calling for "EATS" as a third person singular verb form.

The process of determining num(ber) ought to be more closely tied with the EnParser module, so that the parsing of a word as a noun should afford the AI a chance to declare plural number if the incoming noun ends with an "S".

Now we have inserted special code into the AudInput module to check for the input of nouns ending in "S", and to set the "num(ber)" variable to a plural value if a terminating "S" is found. For singular nouns like "bus" or "gas" that end in "S", we will have to devise techniques that override the default assumption of "S" meaning plural. We may use the article "A" or the verb "IS" as cues to declare a noun ending in "S" as singular.

Table of Contents

• 1 Thurs.26.MAY.2011 -- Conditional Inhibition

• 2 Thurs.26.MAY.2011 -- Problems With Determining Number

may7mfpj

The MindForth Programming Journal (MFPJ) is both a tool in developing MindForth open-source artificial intelligence (AI) and an archival record of the history of how the AI Forthmind evolved over time.

1 Sat.7.MAY.2011 -- Improving Neural Inhibition

Something is preventing neural inhibition from operating immediately when we ask the AI Mind a "who-are-you" question. The inhibition begins to occur only after a pause or delay, and we need to find out why. The problem may be that the "predflag" for predicate nominatives is not being set soon enough. The "predflag" is set towards the end of the BeVerb mind-module, and it governs the inhibiting of nouns as predicate nominatives in the NounPhrase module. We see through troubleshooting that the earlier engram in a pair of selected-noun engrams is being inhibited properly down to minus thirty-two points of conceptual activation, but apparently the present-time engram in the pair is only going down to zero activation. It looks as though calls to PsiClear from the EnCog (English cognition) module were interfering in the pairing of inhibitions shared by the old engram that won selection and the new engram being stored as the record of a generated thought. Then a further problem developed because the AI was not letting go of transitive verbs that served within an output thought. We inserted code to inhibit each transitive verb after thinking, and we began to obtain a variety of outputs from the AI in response to queries.

2 Sun.8.MAY.2011 -- Selecting New Inhibition Variables

Today we are creating two new inhibition variables, "tseln" for "time of selection of noun" in NounPhrase, and "tselv" for "time of selection of verb" in VerbPhrase. We need these variables to keep track of the selection-time of an "inhibend" concept to be inhibited after being thought, so that the AI Mind can avoid repeating the same knowledge-base retrieval over and over again. We stumbled upon neural inhibition for response-variety in our MFPJ work of 5 September 2010. We were so astonished by the implications that we issued a Singularity Alert (q.v.). Now we are ready to install a general mechanism of temporary inhibition throughout the AI MindGrid.

3 Sun.8.MAY.2011 -- Debugging Spurious Inflection

Although MindForth has suddenly become more intelligent than ever, the AI makes the grammatical mistake of saying "I HELPS KIDS". We need to track down why the SpeechAct module is adding an inflectional "S" to the verb "HELP".

The VerbPhrase module governs the sending of an "S" inflection into the SpeechAct module. The pertinent code was not fully checking for a verb in the third person singular, so we added an IF-THEN clause requiring that the prsn variable be set to three for an inflectional "S" to be added to a verb being spoken. The bugfix worked immediately.

Table of Contents

• 1 Sat.7.MAY.2011 -- Improving Neural Inhibition

• 2 Sun.8.MAY.2011 -- Selecting New Inhibition Variables

• 3 Sun.8.MAY.2011 -- Debugging Spurious Inflection

sep09mfpj

The MindForth Programming Journal (MFPJ) is both a tool in developing MindForth open-source artificial intelligence (AI) and an archival record of the history of how the AI Forthmind evolved over time.

1 Thurs.9.SEP.2010 -- Zeroing in on Inhibition
Let's get a few things straight about how the VerbPhrase "twin" (time of winning verb-selection) variable works. On 7sep2010, the variable was introduced into the 5sep10A.F MindForth in the following stretch of VerbPhrase code

I    1 en{ @  act @ > IF  ( if en1 is higher )
  I          twin !  \ retain time of motjuste; 7sep2010
  I  0 en{ @ motjuste !  ( store psi-tag of verb )

which keeps looking for a verb with a higher activation, until a winner is selected.
The "twin" win-time has perhaps changed while various verb-nodes were competing, but the final post-search-loop value of "twin" must necessarily be the time "t" of the winning verb-node, not only in the En(glish) array, but (importantly) also in the Psi concept array, where we postulate that thinking occurs.

Further down in the VerbPhrase module, just before the "main call from VerbPhrase to SpeechAct", "twin" is used as the indexing time to put a minus-fifteen inhibition on the verb-node that has just won selection into a sentence of thought. The inhibition prevents the utterance from being repeated again immediately.

We notice that the -15 inhibition does not persist long in our current 9sep10A.F code basically unchanged from 5sep10A.F. We tried to enter three sentences to see what would happen.

Human: boys make cars
Robot: CARS  WHAT ARE CARS

Human: boys make guns
Robot: GUNS  WHAT ARE GUNS

Human: boys make tools
Robot: TOOLS  WHAT ARE TOOLS

Human: boys 
Robot: THE  BOYS MAKE  THE  CARS

Human: boys
Robot: THE  BOYS MAKE  THE  TOOLS

Human: boys
Robot: THE  GUNS MAKE  THE  CARS

Not only does the inhibition not (yet) persist, but we can see
from the last line of output above that the residual activations are out of whack. We inspect the code and we see that after the first two query-inputs of the word "boys", "GUNS" and "CARS" are both left with an activation of 58, so they prevent the input-word "boys" from being the subject of thought. We do notice some persistence of inhibition, though, because one node on the verb "MAKE" is at -4 activation. So maybe the problem is that there is too much residual activation on "GUNS" and "CARS", which both have "58" while freshly entered "boys" has activation of only 52.

In SpreadAct there is some conditional code that limits an activation to a high value of 63. Let's see if we can try a lower limit in SpreadAct and see if it helps. When we lower the SpreadAct "seq" limit from 63 to 48, we no longer get a nonsense line as our final output. Instead, we get the problem of repetition as seen below.

Human: boys 
Robot: THE  BOYS MAKE  THE  CARS

Human: boys 
Robot: THE  BOYS MAKE  THE  TOOLS

Human: boys 
Robot: THE  BOYS MAKE  THE  TOOLS

Aha, the most recent "BOYS MAKE TOOLS" is inhibited, but an
older "BOYS MAKE TOOLS" has gone from -15 inhibition up to a more normal activation of 13 (or higher, since we can not see what the node's winning activation level was). Just as a test, let us try setting inhibition not at -15 but rather at -32.

It did not work. The most recent "MAKE" node was inhibited down to -32, but somehow the older "MAKE" nodes were all at an activation level of 13. Something is overriding the inhibitions, and it ain't alcohol.

Mybe it is the VerbAct module, putting such a uniform activation on all nodes of a candidate verb. Upshot: Into VerbAct we put some code to skip inhibited nodes, but it did not solve the problem. Apparently, something is getting to the older verb-nodes before the VerbAct module operates on them. It could be PsiDamp.

Hey! Maybe the problem is in the SpreadAct module. From the noun to the verb, SpreadAct could be sending a "spike" of uniform activation of 13 points. We changed some code in the SpreadAct module, and things did work better.

Maybe, when the AI generates a sentence and inhibits the verb-node from which the knowledge for the sentence is retrieved, the new sentence itself should have its verb-node inhibited, so that the idea itself will tend towards inhibition for a short time.

Now we have a very interesting situation. If the inhibition does not fade quickly enough, then a valid idea will fail to get mentioned. The following report indicates such a situation.

390 : 96 13 2 0 0 5 73 96 to BOYS
395 : 73 -11 0 96 96 8 109 73 to MAKE
400 : 109 41 0 73 96 5 0 109 to CARS
405 : 109 41 2 109 0 5 54 109 to CARS
410 : 54 0 0 109 109 7 67 54 to WHAT
415 : 67 0 0 54 54 8 109 67 to ARE
421 : 109 41 2 67 54 5 0 109 to CARS
426 : 96 13 2 109 0 5 73 96 to BOYS
431 : 73 -4 0 96 96 8 110 73 to MAKE
436 : 110 42 0 73 96 5 0 110 to GUNS
441 : 110 42 2 110 0 5 54 110 to GUNS
446 : 54 0 0 110 110 7 67 54 to WHAT
451 : 67 0 0 54 54 8 110 67 to ARE
457 : 110 2 2 67 54 5 0 110 to GUNS
462 : 96 13 2 110 0 5 0 96 to BOYS
467 : 96 13 2 96 0 5 73 96 to BOYS
472 : 73 -6 0 96 96 8 109 73 to MAKE
478 : 109 41 2 73 96 5 0 109 to CARS
483 : 96 13 2 109 0 5 0 96 to BOYS
488 : 96 13 2 96 0 5 73 96 to BOYS
493 : 73 -13 0 96 96 8 109 73 to MAKE
499 : 109 36 2 73 96 5 0 109 to CARS
time: psi act num jux pre pos seq enx

2 Fri.10.SEP.2010 -- Positive Results

We finally obtained some positive results with our implementing of neural inhibition when we removed from the functional heart of VerbAct a line of code that we had once used as only a test. The code snippet below shows our practice of commenting out the offending line twice, once to disable the line of code and once again to record the event of our commenting out the line now, for later clean-up when at least one archival record has been recorded of the action taken.

          I  1 psi{ @  psi1 !
 \ 8 verbval +!  \ add to verbval; test; 25aug2010
 \ 8 verbval +!  \ Commenting out; 10sep2010
 CR ." VrbAct: t & verbval = " I . verbval @ . \ test;9sep2010

        I    1 psi{ @ -1 > IF \ avoid inhibited nodes; 9sep2010
 \ psi1 @ I  1 psi{ !
verbval @ I  1 psi{ !  \ test; 25aug2010
        THEN  \ end of test to skip inhibited nodes; 9sep2010

We may upload the 9sep10A.F MindForth to the Web now that we have
a stable version in which inhibition actually enables the AI Mind to retrieve a series of facts from the knowledge base.

Table of Contents (TOC)

• 1 Thurs.9.SEP.2010 -- Zeroing in on Inhibition

• 2 Fri.10.SEP.2010 -- Positive Results