Of
course there is no way to get rid of recursion, that's very
silly!!!
In the
language of Gregory Bateson (see his book "Mind and Nature"), you're suggesting
to do away with "learning how to learn" --- which is not at all a workable idea
for AGI.
--
Ben
-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]On Behalf Of Yan King Yin
Sent: Thursday, September 08, 2005 7:20 PM
To: [email protected]
Subject: Re: [agi] Representing ThoughtsRegarding "how to select the appropriate reasoning rules to apply" --- in Novamente this occurs on two levels:1) some simple heuristics applied as a default2) based on probabilistic rules that are learned based on experience (via the system's experience carrying out reasoning)Note that there is some recursiveness here, because these probabilistic rules regarding which inference rules to apply in which context, may also be learned via INFERENCE. But this leads potentially to an infinite-depth recursion of inference guided by rules learned by inference guided by rules learned by inference ... which is why one needs some simple heuristics at the bottom to end the recursion after a finite number of steps.What if we allow the easy generation of rules (via inductive generalization) so that there will be a lot of rules, but entirely do away with recursion (ie rules will not further modify other rules)? That seems to simply things a lot. Unless you can show a case where a rule can only be derived from recursion but not directly from generalization of experience.
IMO We should keep the design of AGI to its bare minimum.yky
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
