> > (1): The other caveat is that any system/representation merge that isn't
> > exhaustive (i.e. summing to systems together in totality) will
> > necessarily lose a lot of pattern context that is probably relevant.  On
> > the upside, a fully merged system generally uses fewer resources than
> > the sum of the two independent systems that went into the merged system.
> >  Size has its advantages.
>
> If you're talking about knowledge exchange for complete systems, I
> agree that is nearly impossible. Knowledge can only be exchanged
> within instances of the same system. I'm only proposing KX for
> the sensory frontend. It looks like there's going to be a battle of
> "KX standards" among various AGIs... all the more reasons to think
> about this problem sooner.

Two issues

1) I don't think object recognition goes in the sensory front-end ... it's
at least partially cognitive

2) even among sensory-processing front ends, I don't think there can be the
kind of standardization you want.  For instance, Novamente will use a
probabilistic-combinatory-term-logic based representation for perceptual
patterns, whereas I also know how to build systems that use wavelet
expansion based representations for perceptual patterns.  Translating
wavelets into Novamente's repr. is awkward; doing the reverse is close to
impossible...

-- Ben G


-------
To unsubscribe, change your address, or temporarily deactivate your subscription, 
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]

Reply via email to