Hello,
I propose the following
Define
_a = (output - resource_usage) / resource_usage ; a measure of
effeciency
_b = d_a / dt ; i.e. the derivative of _a with respect to time
where output and resource_usage are appropriately calculated depending on
context (scarcity/need).
Example: for people in the past food (energy) has been scarce, so
historically a large component of resource_usage for people has been energy
usage, and a large component of output has been obtaining necessary food.
As such people are intelligent as _a is good and _b is positive. We learn to
do things more effeciently. We can think more and more things through,
rather than using the expensive trial and error way. We can do more and more
with less.
We could then consider an AGI as a system that given a series of function
definitions f(n) from a particular domain D and the ability to evaluate
these functions over a set of parameters _x to give an output _y,
is a system that improves its effeciency in calculating _x for a given _y
and f(n), both for n fixed and for related f(n). (i.e. an inverse problem)
i.e. _y = eval f(n) _x ; the application of a particular function f(n)
from D to _x.
With this framework, measuring resource usage is a necessary part of
measuring intelligence, as is measuring change in efficiency over time
(learning).
What existing work already exists in this direction?
It would seem to me that people, given the context are already very
intelligent by this measure. We can achieve a lot quickly using few joules.
Most of the hopes of a superhuman intelligence rely on us being able to use
megawatts as opposed to a few Watts.
Any comments?
Rene.
-------------------------------------------
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=8660244&id_secret=111637683-c8fa51
Powered by Listbox: http://www.listbox.com
