RE: basic BayesCraft training?

From: Marc Geddes (marc_geddes@yahoo.co.nz)
Date: Thu Mar 17 2005 - 20:28:32 MST


--- Ben Goertzel <ben@goertzel.org> 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.

Right.

I also want to point to recent theoretical ideas from
physics (namely the Holographic Principle of G. 't
Hooft ) which seem to be starting to approach a proof
that all finite physical processes must consist of
finite number of computational steps. On the basis of
this it seems likely that 'computational
intractibility' should be regarded as a fundamental
law, not just a practical constraint. It's only a
small intuitive step from there to thinking that there
is something wrong with current probability theory as
applied to theoretical computational models, because
theoretical ideal models are failing to take into
account a fundamental property of nature (namely that
computational resources per unit space must be
finite).

Does this clarify?

---
THE BRAIN is wider than the sky,  
  For, put them side by side,  
The one the other will include  
  With ease, and you beside. 
-Emily Dickinson
'The brain is wider than the sky'
http://www.bartleby.com/113/1126.html
---
Please visit my web-site:
Mathematics, Mind and Matter
http://www.riemannai.org/
---
Find local movie times and trailers on Yahoo! Movies.
http://au.movies.yahoo.com


This archive was generated by hypermail 2.1.5 : Tue Feb 21 2006 - 04:22:55 MST