Mon.13.SEP.2010 -- Inhibition Revisited 

We need to go into the MindForth free AI source code and 
start removing inhibition code from verbs of being, because 
in clarifying our rules of activation, we have concluded that 
predicate nominatives should endure inhibition, but not the 
be-verbs that link to them. 

Tues.14.SEP.2010 -- Code, Test, Debug 

In our coding yesterday we switched many times back and forth 
between debug and test, debug and test. We were aided by our 
initial search for, and culling out, of current instances of 
neural inhibition implemented in the NounPhrase, BeVerb, 
VerbPhrase and EnCog mind-modules. Having formulated yesterday 
two rules -- that inhibition should occur in pairs, and that 
reasons for query-response variance should drive inhibition -- 
we are able now to focus more carefully now on where and why 
neural inhibition should occur in our open source code for 
artificial intelligence (AI). In the light of the new rules, 
we comment out the inhibition code in the EnCog thinking module, 
because we fear that it may interfere with our troubleshooting. 
Then we fire up the AI and we put the same question to the AI 
seven times, with the following results. 

Human: what are you
Robot:  I  AM  ANDRU

Human: what are you
Robot:  I  AM  ME

Human: what are you
Robot:  I  AM  ME

Human: what are you
Robot:  I  AM  ME

Human: what are you
Robot:  I  AM  ME

Human: what are you
Robot:  I  AM  ME

Human: what are you
Robot:   I  AM  ANDRU

We interpret the above exchange as showing that the 
response-idea "I AM ANDRU" was initially inhibited as a 
pair of two identical thoughts, one in the innate knowledge 
of the EnBoot English bootstrap, and one in the response 
made by the AI when asked, "What are you?" The inhibiition 
on the predicate nominative "ANDRU" lasts so long, that 
the "I AM ANDRU" KB-response is suppressed during five 
subsequent queries, until finally the inhibition of 
"ANDRU" has worn off and the AI can once again answer, 
"I AM ANDRU". It is up to the mind-designer and/or AI coder 
to decide how severely to inhibit ideas in the AI, under 
considerations such as just how much mind-control do we 
wish to engage in; what is the proper trade-off between 
time-duration of inhibited concepts and exhaustive KB-search; 
and so forth. Right now we are eager to have inhibition 
strong enough to aid our code-test-debug cycle, and we 
especially want to verify that each instance of inhibition 
is happening on the horns of an idea pair (old and new), so 
that no stray inhibitions are ruining a chain of AI thought. 

Uh-oh. We've got some good results. Let's upload the code.

Meanwhile, here is what happened. In our hovering, looming 
quest for self-referential thought, we were testing the AI 
not only by asking "what are you" but by first telling the 
AI "you are a program". Then we were getting "garbage out" 
in response to our "what are you" queries. But instead of 
dealing with the central issue (properly implementing 
inhibition), we tried removing the annoyance of seeing 
"I ARE ME" and "PROGRAM ARES ME" as some actual responses 
that the AI has issued today. So we went into the VerbPhrase 
module and inserted the following code. 

  motjuste @ 58 = IF BeVerb EXIT THEN  \ BE;  14sep2010
  motjuste @ 57 = IF BeVerb EXIT THEN  \ AM;  14sep2010
  motjuste @ 66 = IF BeVerb EXIT THEN  \ IS;  14sep2010  
  motjuste @ 67 = IF BeVerb EXIT THEN  \ ARE; 14sep2010

The above code forces the AI to treat "AM IS ARE" 
not as normal, regular verb-forms, but instead to let the 
BeVerb module enforce strict rules for the usage of forms 
of the "BE" verb. Immediately we obtained the following 
dialog which still has its problems but is on track. 

Transcript of AI Mind interview at 
6 31 38 o'clock on 14 September 2010.

Human: you are a program

Human: what are you

Human: what are you
Robot:  I  AM  PROGRAM

Further inspection of the activation-levels indicates that 
inhibition does not kick in until the AI states the idea, 
"I AM PROGRAM", leaving out the article "A" because the 
EnArticle module is not being called. 

It is an eerie feeling to see the above results, as if 
the AI Mind is awakening before our very eyes. 

RSS Feed:
Modify Your Subscription:
Powered by Listbox:

Reply via email to