--- Pei Wang <[EMAIL PROTECTED]> wrote:

> On Jan 20, 2008 10:17 PM, Ben Goertzel <[EMAIL PROTECTED]> wrote:
> > > So, people do have a practically useful way of cheating problems in NP
> > > now. Problem with AGI is, we don't know how to program it even given
> > > computers with infinite computational power.
> >
> > Well, that is wrong IMO....  AIXI and the Godel Machine are provably
> correct
> > ways to achieve AGI with infinite (or even huge finite) computational
> power.
> 
> Well, that is wrong IMO. ;-)
> 
> Given infinite (or even huge finite) computational power, AIXI and the
> Godel Machine will achieve their working definition of intelligence
> (i.e., Hutter's Universal Intelligence), but whether that definition
> captures all aspects of "AGI" is still an open question.
> 
> For example, "to predict what will happen in the environment" and "to
> predict the next input from the environment as a TM" are two very
> different problems, at least to me. For the former, the environment
> can be described by a hierarchy of concepts with different
> granularity, which for the latter, the environment is always described
> at the same level.
> 
> For some people in this list, I can predict their opinions on certain
> topics with high accuracy, though I have little idea on what letter
> will be the first letter of their next post. If I have to predict
> that, I'll have to depend on the the occurrence distribution of
> English letters, and my knowledge about their opinions play no role.
> 
> Pei

There is no difference.  The chain rule says that P(s) = PROD_i
P(s_i|s_1..i-1), that any probability distribution over string s can be
expressed as a product of conditional predictions of consecutive symbols in s.
 If you know that I am for or against X then you have one bit of knowledge.  A
data compressor knowing this can compress a message from me about X one bit
smaller than a compressor without this knowledge.


-- Matt Mahoney, [EMAIL PROTECTED]

-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=8660244&id_secret=88198902-ec54fb

Reply via email to