> From: Joseph Gentle [mailto:[EMAIL PROTECTED]
> 
> 
> There are two interesting points here.
> 
> The first is that (in my opinion) pattern matching must come first. I
> agree that understanding the patterns (the /why/) is important; but
> seeing (even unjustified) patterns is crucial. The benchmark I like to
> consider is an intelligent system being connected to a noisy camera
> for the first time. The noise may overwhelm the pattern matching at
> first, but over time it should automatically learn to filter out the
> noise regardless of whether or not it understands why the noise exists
> at all.
> 
> The second interesting point is music. It is my belief that one of the
> important properties of music is how it tickles our pattern matching
> ability. Imagine a sequence of notes fed into an intelligent system
> (perhaps, through speakers into a human mind). The intelligent system
> automatically tries to find patterns in the notes such that it can
> model the notes (and predict subsequent notes).
> 
> We can imagine another sequence of actions of the intelligent system
> as it parses subsequent notes in the music. These actions can indicate
> three things:
> - The note has been correctly predicted
> - The note has been incorrectly predicted and the system doesn't know
> why that note in particular was played
> - The note was incorrectly predicted, but it shows a new pattern which
> explains previously incorrectly predicted notes.
> 
> It is my opinion that beautiful music makes an intelligent mind
> trigger 'just the right amount' of these second two kinds of
> modelling.
> 


I would expand on this by conjecturing that human musical pattern
extrapolation fidelity is a sort of an averaging of the human minds full
capability of an astonishingly robust pattern recognizing ability. I'm
saying this because the development of the ability over evolutionary time,
looking at survival of a species in nature with natures dizzying complexity
of audial richness. The sounds of animals and insects and weather, etc. in
nature before civilization and the organisms requirements of survival
informational needs, for example - listening to insect and bird calls in a
jungle when a predator is on the other side of a hill subconsciously, not
direct sound since the hill is somewhat out of hearing range but the chain
reaction sounds effects that reach you. I feel that our modern audial
pattern recognition ability has been extremely dumbed down. Though some of
us may have had the experience of waking at night in that placid state and
being able to hear everything, and I mean to be able to see what is going on
though sounds far away, down the block or hear and mentally extrapolate
activity literally miles away. 

So I feel that much of our brain mass is there due to the natural richness
of nature, and there may be quite a bit of overkill compared to what would
be needed in software AGI.

John





-------------------------------------------
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
http://www.listbox.com/member/?member_id=8660244&id_secret=103754539-40ed26
Powered by Listbox: http://www.listbox.com

Reply via email to