The case of Helen Keller can certainly shed some
light on the human processes of knowledge acquisition. Without the senses
of vision and hearing, how could she build up an internal model of the world and
her place in it?
I don't remember the exact number, but something
like 70% of the cerebral cortex is involved in visual processing. We use
internal visual-spatial maps to orient ourselves within the space around us
and navigate through it. With our eyes closed, we can pinpoint the
locations of objects in this internal model of space by the directions that
their sounds come from and by properties of the sounds. We can tell
without looking whether a car is driving toward or away from us by the
change in pitch of the sound--up or down. The auditory information gets
fed into the same central map that visual information gets fed into. The
sense of touch also gets fed into the same mapping system. That's how you
can build up a mental picture of a room in complete darkness by feeling your way
around.
Helen Keller, though without vision and hearing,
was not without a human brain and its visual-spatial modelling
capabilities. Using the sense of touch alone, she could build up maps of
her environment in the same way that non-blind people do in the dark. And
this is how she also acquired her knowledge of words and language--through the
sensory channel of touch (the story of her teacher finally getting her to
associate taps on her hands with the water coming out of a spigot). Her
language processing probably took place in the areas of the brain normally used
for language processing, such as Broca's and Wernick's areas, but
the symbols were grounded in and represented by patterns of incoming
touches and patterns of muscle movements for generating the same. Her
knowledge was built up out of sensory-motor patterns.
So your bot is an AGI project? I guess a
number of people on this list are actually working on real AGI systems.
I'm also developing one.
Like your system, my system also uses
ASCII inputs and outputs, but they are part of its formal interface
language, a computer language for communication between human and machine and
between machine and machine. The language is like SQL in the
sense that it is used for managing knowledge bases, inputting information, and
querying, but it has the universal expressability of languages like Prolog,
Lojban, or English. The other IO channels are vision and motor
outputs. If my system is to learn to use a natural language, it will do so
through these two channels, learning to recognize characters visually and
generate them through motor outputs, rather than using ASCII codes. I
think that this approach to handling natural language is essential for true AI,
which should be capable of learning any human language from Greek to Chinese to
hieroglyphics, regardless of the types of symbols used. To learn Chinese,
for example, a system should be able to learn to recognize and generate the
pictographic characters in their two-dimensional form instead of being tied
to numeric codes for the characters. Not easy, but necessary if you are to
say that a system has true general intelligence.
Higher intelligence requires the ability to use
language for communication and for encoding ideas in linguistic form. But
language is only a secondary form of knowledge representation. The primary
form, at least in the human brain, is spatial-temporal (and
probabilistic) models built up out of sensory-motor patterns.
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] |
- Re: [agi] Logic and Knowledge Representation John Scanlon
- Re: [agi] Logic and Knowledge Representation J Marlow
- RE: [agi] Logic and Knowledge Representation Gary Miller
- Re: [agi] Logic and Knowledge Representation J. Andrew Rogers
- RE: [agi] Logic and Knowledge Representation Gary Miller
- Re: [agi] Logic and Knowledge Representation sanjay padmane
- Re: [agi] Logic and Knowledge Representation J. Andrew Rogers
- Re: [agi] Logic and Knowledge Representation J. Andrew Rogers
- Re: [agi] Logic and Knowledge Representation James Ratcliff
- Re: [agi] Logic and Knowledge Representation James Ratcliff