Look, humans are not consistent !!!
An AGI with modest resources and the same environment as a human can
still be a lot more consistent than a human, but not thoroughly
consistent
Consistency is a virtue but not the only one; creativity e.g. is
another virtue and given limited resources it is often contradictory
to consistency...
To see why consistency is out of reach for practical AI systems you
just need to look at
http://en.wikipedia.org/wiki/Cox's_theorem
which phrases Cox's third assumption revealingly as
"
Suppose [A & B] is equivalent to [C & D]. If we acquire new
information A and then acquire further new information B, and update
all probabilities each time, the updated probabilities will be the
same as if we had first acquired new information C and then acquired
further new information D. I
"
This is just not gonna happen for any computationally feasible
cognitive system.
-- Ben
On Feb 6, 2007, at 5:08 PM, gts wrote:
On Tue, 06 Feb 2007 16:27:22 -0500, Jef Allbright
<[EMAIL PROTECTED]> wrote:
You would have to assume that statement 2 is *entirely* contingent on
statement 1.
I don't believe so. If statement S is only partially contingent on
some other statement, or contingent on any number of other
statements, then simple coherency demands only that we assign the p
of S to be less than the p of any of those other statements on
which S is contingent. It makes no difference for the sake of
coherency how many of those other statements are known or in
memory, nor does it matter whether our assigned probabilities match
"reality".
I think coherency is probably a necessary but not a sufficient
condition for intelligence. I hope it is not really outside the
range of what is possible in AI.
-gts
-----
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/?list_id=303
-----
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/?list_id=303
