Cenny Wenner wrote:
...
I hope my ignorance does not bother this list too much.
Regarding what or what may not be done through logical inference and
other expressive enough symbolic approaches; given unlimited resources
would it not be possible to implement an UTM with at most a finite
overhead which in turn yields that any algorithm running on an UTM
could also run on expressive enough symbolic systems, whether they
"learn" or not? I do not argue that it is not inefficient, both for
running and implementation speed. It's even so that the logical
inference in such a case may be reduced entirely and proven to be more
efficiently obviously, than to implement the system direcly on certain
systems. I do not think however that such a strict and not
well-formulated position is rationally justified since it's not clear
(at least not to me) that the logical inference may be efficiently
reduced for every algorithm expressed in the logical language. Just
rambling and unrelated but perhaps the brain's operations do not even
allow for UTMs since they are not so clear and there might not be
appropriate transformations and if assume the Turing-Church thesis we
might find that there are problems that artificial components may
solve that humans cannot even given unlimited resources. Perhaps not
very likely since we can simulate the process of an UTM by hand and
even the errors may be corrected given enough time.
...
It's true that a Universal Turing Machine can calculate anything
calculable. This doesn't mean it can do it with a reasonable
efficiency. It doesn't even mean that it might not require an "infinite
tape" to calculate something.
It's probably a bad idea to depend on either getting every part of your
design right to start with, or on calculating everything. So an AGI
starts from a place that isn't a blank slate, and learns from it's
environment. It needs to be able to learn from examples and
descriptions as well as from experiences, as some experiences are either
"fatal" or "permanently crippling". Beyond that there's lots of
disagreement as to the best way to proceed, but I think that everyone
would agree with that summary.
Note that AGIs are intended to exist in the "real world", not in some
abstract mathematical space, and therefore the presumption of infinite
resources of ANY kind cannot be allowed. (This is also true of many
mathematical spaces, of course, but the classic ones simplify things by
assuming that infinities are allowable.)
-----
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