Summon the JavaScript AI Mind into your presence with MSIE.

Do-It-Yourself Artificial Intelligence
by A.T. Murray based on the AI4U
Theory of Cognitivity


1. Top-Level AI Algorithm: Code the Main Alife Program Loop
            ___________                    ___________           
           /           \                  /           \          
          /  Motorium   \                /  Security   \         
          \_____________/\    ______    /\_____________/
       __________         \  /      \  /          _________
      /          \         \/  main  \/          /         \
     (  Volition  )--------<   Alife  >---------( Sensorium )
      \__________/         /\  loop  /\          \_________/
           _____________  /  \______/  \  _____________
          /             \/              \/             \
          \    Think    /                \   Emotion   /
           \___________/                  \___________/

Code the Alife loop shown above in your chosen programming language.
Use either an actual loop with subroutine calls, or make a ringlet
of perhaps object-oriented module stubs, each calling the next stub.
Provide the ESCAPE key or other mechanisms for the user to stop the AI.
Spread your code around the Web and invite AI coders to expand on it.
Watch for a proliferation of unique AI Mind entities evolving rapidly
on the Web and competing genetically for the survival of the fittest.


2. Second-Tier AI Algorithm: Code the Sensorium Module

Now you have two modules, a main aLife module and a subordinate,
Sensorium module. But what should come next in evolution?
Now we need a reaction module, so that the organism may react
to its environment. Let's call the reaction-module "Think".


3. Second-Tier AI Algorithm: Code the Think Module

Now, of course, the simple organism is not truly thinking yet,
but we have stubbed in the Think module and we need to show it.
You should now be able to run your AI program, watch it wait (briefly)
for keyboard input ending with a press of the Enter key, and see
a message (in Tab-selected tutorial mode) that Think has been called.
You have a partly functional AI program, but it has not yet quickened,
that is, it has not yet begun to think as a mind. But it should run
indefinitely (until you press the Escape key to terminate it), looping
forever through the brief wait for human entry either during the action
of the Sensorium module, or upon the event-driven recognition of a key-press.
If you do not have this organic functionality, your organism is not viable,
and you must go back and reengineer your stem cells, as it were, of AI.

With the proper looping functionality, you now have a stimulus-response
organism. There is no knowledge being accumulated, because the animal
has no memory. Therefore our next step is to create an Audition module
that will feed into auditory short term memory (audSTM).


4. Third-Tier AI Algorithm: Code the Audition Module

Drop the [ESCAPE] mechanism down by one tier, into the Audition
module, but do not eliminate or bypass the quite essential
Sensorium module, because another programmer may wish to specialize
in implementing some elaborate sensory modality among your
Sensorium stubs. Code the Audition module initially to deal
with ASCII keyboard input. If you are an expert at speech
recognition, extrapolate backwards from the storage requirements
(space and format) of the acoustic input of real phonemes in
your Audition system, so that the emerging robot Mind may be
ready in advance for the switch from hearing by keyboard to
hearing by microphone or artificial ear. Anticipate evolution.


5. The Listen Module

Stub in a new module and call it the Listen module.
Have the Audition module call the Listen module as a
separation of the state of readiness to hear, or listening,
from the actual act of hearing, or audition. By having
separate Listen and Audition modules that distinguish the two
functions, you could have an AI Mind that listened throughout
an entire building, or the Pacific Ocean, or a SETI galaxy.

6. Auditory Short Term Memory (audSTM) Module

Code an auditory Short Term Memory (audSTM) array.

7. audDamp Module

8. English Vocabulary (enVocab) Module

9. English Lexicon Damping (enDamp) Module

10. The Instantiate module

11. The psiDamp module plays a key role in
artificial consciousness by damping down the activation of each
concept immediately after it has been thought as part of an idea,
so that consciousness may ride a moving wave of active concepts
to flit from thought to thought in the stream of consciousness.

12. The Troubleshoot Module

13. Auditory Recognition (audRecog) Module

14. Second-Tier AI Algorithm: The English Bootstrap (enBoot) Module

15. oldConcept Module

16. newConcept Module

17. The Parser Module

18. The Activate Module

19. The Spreading Activation (spreadAct) Module

20. The psiDecay module lets semi-activated subconscious concepts
sink towards oblivion slowly enough to remain briefly available to the
searchlight of attention and for the moving wave of activation to bring
the subconscious concepts back into the stream of consciousness.

21. Second-Tier AI Algorithm: Enhance the Think Module

22. The Reify Module

23. The Speech Module

24. The Reentry Module

25. nounPhrase Module

26. verbPhrase Module

27. The Subject-Verb-Object (SVO) Module

28. The Conjoin Module

Code the Conjoin module as a mechanism to select conjunctions.
Once the AI has learned to think or utter one simple SVO statement,
it requires the ability to select the right conjunction in order to
string meandering thoughts together in a stream of output that lasts
as long as the process of spreading activation gives rise to ideas.
In answer to input questions of "why", the Conjoin module may select
the conjunction "because" -- followed by a statement of associated
and possibly explanatory ideas, in a demonstration of AI reasoning.

29. Auxiliary Verb (auxVerb) Module

30. Negational Subject-Verb-Object (negSVO) Module

31. The Ask Module

32. wtAuxSDo Module

33. The Security Module

34. Human-Comouter Interaction (HCI) Module

35. The Rejuvenate Module

36. The Ego Self-Preservation Module


37. Algorithmic Troubleshooting
Troubleshooting of the AI Mind starts with the highest level
of the AI algorithm and proceeds down to the lowest levels.
Look for troubleshooting tips on each mind-module Web page.
Since the original AI4U Mind-1.1 code is provided as a functioning
example, any port into a new language or a new robot ought
first to achieve parity with the basic functionality of the
"teaching" AI and only then, after ensuring a basic
functionality, start to add new features or refinements --
a delicate process in software which may give the AI coder
a feeling akin to performing psychosurgery in wetware.


38. Commenting the Code

See the material on "Comments" at
http://mind.sourceforge.net/progman.html#comments


39. Structured Programming

39.1 Sequential Order of Function Calls

See the material on Structured Programming Sequence at
http://mind.sourceforge.net/progman.html#anatomy


40. Robot AI Mindmaking Resources



Return to top; or to the
sitemap.html Sitemap.