**From:** Ben Goertzel (*ben@goertzel.org*)

**Date:** Fri Mar 18 2005 - 14:58:55 MST

**Next message:**Mikko Särelä: "Re: basic BayesCraft training?"**Previous message:**J. Andrew Rogers: "RE: basic BayesCraft training?"**In reply to:**J. Andrew Rogers: "RE: basic BayesCraft training?"**Next in thread:**Mikko Särelä: "Re: basic BayesCraft training?"**Reply:**Mikko Särelä: "Re: basic BayesCraft training?"**Messages sorted by:**[ date ] [ thread ] [ subject ] [ author ] [ attachment ]

Hi James,

I don't claim to have proven that Bayesian inference is not a

computationally feasible foundation for AGI. The probability that I'm

wrong is, IMO, significantly greater than zero. But nevertheless this is my

best guess.... I don't think this is an OBVIOUS conclusion; I have come to

this conclusion only after a lot of hard thinking about both probability

theory and AGI. And I realize that I haven't given an adequate

justification for the conclusion here; to do so in a reasonably brief email

would be quite hard....

As a teaser, though, I'll note that I did a fair amount of work with MAXENT

a while back. It's powerful but yet the maximum-entropy assumption about

priors isn't really good enough. Yet the Solomonoff-Levin prior is

intractable.... Is there a "middle ground" (not quite the right expression,

I know) that works for AGI yet is tractable? IMO this "middle ground" is

going to involve a heck of a lot of stuff that has nothing directly to do

with Bayes theorem but a lot to do with cognitive science..

-- Ben

----- Original Message -----

From: "J. Andrew Rogers" <andrew@ceruleansystems.com>

To: <sl4@sl4.org>

Sent: Friday, March 18, 2005 1:37 PM

Subject: RE: basic BayesCraft training?

*> Ben wrote:
*

*>> I believe what Marc really wants to say here is NOT
*

*>> that Bayes theorem is "broken" (clearly it's correct
*

*>> math), but rather that explicitly applying
*

*>> Bayesian inference is not a computationally feasible
*

*>> strategy in most cases. So it's the idea that
*

*>> "intelligence should be achieved primarily via
*

*>> explicit application of Bayes Theorem" that is broken.
*

*>
*

*>
*

*> Marc said what Marc said. If he wanted to say something else, then he
*

*> should be a little more thoughtful before pressing the "Send" button.
*

*>
*

*> Even if he had written exactly what you had written above, I would still
*

*> disagree with the reasoning. Just because some implementations of Bayes
*

*> may be intractable does not mean that it is *necessarily* intractable in
*

*> this domain. Even you use the "most cases" weasel words, which makes
*

*> the idea that "Bayes theorem is broken" a real stretch even if Marc
*

*> merely meant "infeasible".
*

*>
*

*>
*

*> It is not obvious to me that some fairly pervasive application of Bayes
*

*> is always going to be intractable for this application. It would seem
*

*> to me to be making some implicit assumptions in the design,
*

*> implementation, and problem space that are not warranted. I'll simply
*

*> make the observation that people don't implement mathematics on
*

*> computers, they implement finite approximations that often have
*

*> different properties than the pure math description would suggest. As
*

*> an obvious example, useful lossless data compression algorithms do a
*

*> pretty fine job on ordinary computers even though a perfect
*

*> mathematically pure implementation of data compression would be
*

*> generally intractable in this universe.
*

*>
*

*>
*

*> j. andrew rogers
*

*>
*

*>
*

*>
*

**Next message:**Mikko Särelä: "Re: basic BayesCraft training?"**Previous message:**J. Andrew Rogers: "RE: basic BayesCraft training?"**In reply to:**J. Andrew Rogers: "RE: basic BayesCraft training?"**Next in thread:**Mikko Särelä: "Re: basic BayesCraft training?"**Reply:**Mikko Särelä: "Re: basic BayesCraft training?"**Messages sorted by:**[ date ] [ thread ] [ subject ] [ author ] [ attachment ]

*
This archive was generated by hypermail 2.1.5
: Wed Jul 17 2013 - 04:00:50 MDT
*