Re: [agi] AIXI (was: Mushed Up Decision Processes)

2008-11-30 Thread Ben Goertzel 
AIXI is a purely theoretic construct, requiring infinite computational resources

AIXItl is a version that could be implemented in principle, but not in
practice due to truly insane computational resource requirements

Whether the line of thinking and body of theory underlying these
things can be useful for inspiring more practical AGI designs, is a
matter of opinion and intuition, at this point...

-- Ben G

On Sun, Nov 30, 2008 at 10:58 AM, Philip Hunt [EMAIL PROTECTED] wrote:
 2008/11/29 Matt Mahoney [EMAIL PROTECTED]:

 The general problem of detecting overfitting is not computable. The 
 principle according to Occam's Razor, formalized and proven by Hutter's AIXI 
 model, is to choose the shortest program (simplest hypothesis) that 
 generates the data. Overfitting is the case of choosing a program that is 
 too large.


 Can someone explain AIXI to me? My understanding is that you've got
 some black-box process emitting output, and you generate all possible
 programs that emit the same output, then choose the shortest one. You
 then run this program and its subsequent output is what you predict
 the black-box process will do. This has the minor drawback, of course,
 that it requires infinite processing power and is therefore slightly
 impractical.

 I've read Hutter's paper Universal algorithmic intelligence, A
 mathematical top-down approach which amusingly describes itself as
 a gentle introduction to the AIXI model.

 Hutter also describes AIXItl of computation time Ord(t*2^L) where I
 assume L is the length of the program and I'm not sure what t is. Is
 AIXItl something that could be practically written or is it purely a
 theoretical construct?

 In short, is there something to AIXI or is it something I can safely ignore?

 --
 Philip Hunt, [EMAIL PROTECTED]
 Please avoid sending me Word or PowerPoint attachments.
 See http://www.gnu.org/philosophy/no-word-attachments.html


 ---
 agi
 Archives: https://www.listbox.com/member/archive/303/=now
 RSS Feed: https://www.listbox.com/member/archive/rss/303/
 Modify Your Subscription: https://www.listbox.com/member/?;
 Powered by Listbox: http://www.listbox.com




-- 
Ben Goertzel, PhD
CEO, Novamente LLC and Biomind LLC
Director of Research, SIAI
[EMAIL PROTECTED]

I intend to live forever, or die trying.
-- Groucho Marx


---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06
Powered by Listbox: http://www.listbox.com

Re: [agi] AIXI (was: Mushed Up Decision Processes)

2008-11-30 Thread Richard Loosemore 

Philip Hunt wrote:

2008/11/29 Matt Mahoney [EMAIL PROTECTED]:

The general problem of detecting overfitting is not computable. The
principle according to Occam's Razor, formalized and proven by
Hutter's AIXI model, is to choose the shortest program (simplest
hypothesis) that generates the data. Overfitting is the case of
choosing a program that is too large.



Can someone explain AIXI to me? My understanding is that you've got 
some black-box process emitting output, and you generate all possible

 programs that emit the same output, then choose the shortest one.
You then run this program and its subsequent output is what you
predict the black-box process will do. This has the minor drawback,
of course, that it requires infinite processing power and is
therefore slightly impractical.

I've read Hutter's paper Universal algorithmic intelligence, A 
mathematical top-down approach which amusingly describes itself as 
a gentle introduction to the AIXI model.


Hutter also describes AIXItl of computation time Ord(t*2^L) where I 
assume L is the length of the program and I'm not sure what t is. Is 
AIXItl something that could be practically written or is it purely a 
theoretical construct?


In short, is there something to AIXI or is it something I can safely
ignore?



It is something that, if you do not ignore it, will waste every second
of brain cpu time that you devote to it ;-).

Matt comes has a habit of repeating some version of the above statement 
... according to Occam's Razor, [which was] formalized and proven by 
Hutter's AIXI model... on a semi-periodic basis.  The first n times I 
took the trouble to explain why this statement is nonsense.  Now I don't 
bother.


AIXI is mathematical abstraction taken to the point of absurdity and 
beyond.  By introducing infinite numbers of copies of all possible 
universes into your formalism, and by implying that functions can be 
computed on such structures, and by redefining common terms like 
intelligence to be abstractions based on that formalism, you can prove 
anything under the sun.


That fact seems to escape some people.



Richard Loosemore


---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06
Powered by Listbox: http://www.listbox.com