I think that the hardest part
to finding a solution to a difficult problem often lies in finding the
right way to
view the problem, in order words, the right representation.
Cheers
Shane
Yes ... but, what this means is that a critical task of AGI design is to be
sure
your AGI has, or has the capability to relatively easily learn, a good
**representation
for representing representations**.
Once it has a good meta-representation language like this, then indeed, it
can
aptly find the right representations to match with problems it is presented
with.
But learning the right meta-representation language is, I suspect, most of
what
happens on the way from Piaget's infantile stage to Piaget's formal stage.
I believe the human brain is "constructed" so as to grow a certain sort
of meta-representation language within itself, based on childhood neural
development in
conjunction with the experiences of a typical childhood.
Even though any general meta-representation language can be translated into
any
other one within O(1) [i.e. the length of the translation program is
constant with respect to the size of the representation beng expressed], in
practice the choice of meta-representation language is going to be critical
to the viability of the intelligent system...
-- Ben
-----
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=231415&user_secret=fabd7936
