Re: PAPER: Theory of Universal AI based on Algorithmic Complexity

From: Mitchell Porter (you_have_some_sort_of_bug@yahoo.com)
Date: Sun Apr 15 2001 - 18:07:57 MDT


An identical-looking paper by this author
(http://xxx.lanl.gov/abs/cs.AI/0004001;
click on his name to see others) inspired
the second of my "six theses on superintelligence"
(http://www.sysopmind.com/archive-sl4/0102/0013.html).
The main problem with his optimal AI is that
in its idealized form, it is noncomputable,
and even its resource-bounded form, it still
scales horribly (see second comment under
"Outlook"). This is because it's meant to
deal with every possible environment, so it
runs afoul of no-free-lunch theorems. What
interests me is whether these concepts can
illuminate 'specialized AI' that works with
domain-specific representations and algorithms.

--- James Rogers <jamesr@best.com> wrote:
[...]
> http://www.hutter1.de/ai/pkcunai.pdf

__________________________________________________
Do You Yahoo!?
Get email at your own domain with Yahoo! Mail.
http://personal.mail.yahoo.com/



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:36 MDT