From: Cliff Stabbert (cstabbert@the-beach.net)
Date: Wed Aug 20 2003 - 23:22:36 MDT
James Rogers wrote:
JR> Almost everyone who responded to my assertion did not grok it. That may
JR> have been a communication failure on my part or simply that I assumed the
JR> audience had sufficient contextual background to figure it out. Mixed with
JR> a bit of apparent reading non-comprehension. I've been meaning to get back
JR> to this but stepping through it from the primitives will be painfully
JR> lengthy so time is an issue. The reasoning behind my assertion is actually
JR> fairly elegant in a formal sense and you can prove it with the clever
JR> application of things we've already discussed on this list; I thought
JR> someone might put the pieces together.
James, could you give a yea/nay possibly with brief clarification to
the following (which did occur to me when you first made your
statements) as an approximation of your meaning/reasoning:
General Intelligence can be measured against e.g. AIXI, i.e.
degree of compression is the relevant factor here. Given finite
resources, there will be algorithms that approach "ideal
compressibility" (i.e. that degree achieved given infinite
resources i.e. AIXI) more or less closely; it follows from these
premises that there will be a best algorithm for this.
[Side note: from earlier hints, would this involve a network of
mutually-determining/converging Bayesian equations?]
[Also note that I do not necessarily agree with the statement-I'm-
interpreting-you-to-be-making above. Perhaps in a *very* general
sense of General Intelligence I would...]
-- Cliff cstabbert@the-beach.net
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:42 MDT