Philosophical Foundations

[Nate Cull]

> Categorization is difficult to do (and is important to AI) because it
> can easily lead to intractability: an apple is a fruit, belong to the
> category of edible stuff, is part of the vegetal kingdom. But it is
> also an exemplar of round objects, solid objects, textured surfaces,
> rotting things, etc. I could find thousands of "irrelevant" categories
> in which an apple would fit. This "explosion" of categories, if not
> taken care properly, would fill the memory of an agent rapidly,
> exactly the opposite of what compression is supposed to do. 


But presumably a good compressor would only generate a "category" when
it was required in order to differentiate two otherwise similar
objects?  And it would only differentiate the objects when there was
some compelling environmental need to do so?  (Like, for example,
needing to learn the difference between a banana and a wasp.  They're
both yellowish, pointed things... but one stings and the other tastes
good.)

It seems to me that one of the main assumptions of CasC is that all
intelligence is remembering and predicting.  Is that correct?

Nate

-- 
----------------------------------------------------------------
Nate Cull * culln at xtra.co.nz * www.geocities.com/Athens/Forum/6748

"It is the stillest words that bring the storm.  
Thoughts that come with doves' footsteps guide the world."  
-- Friedreich Nietzsche, _Thus Spake Zarathrustra_

Free Mars * Open Source DNA *  Just Say No To Sentient AI
----------------------------------------------------------------