Sorry, but I simply do not accept that you can make "do really well on
a long series of IQ tests" into a computable function without getting
tangled up in an implicit homuncular trap (i.e. accidentally assuming
some "real" intelligence in the computable function).
Let me put it this way: would AIXI, in building an implementation of
this function, have to make use of a universe (or universe simulation)
that *implicitly* included intelligences that were capable of creating
the IQ tests?
So, if there were a question like this in the IQ tests:
"Anna Nicole is to Monica Lewinsky as Madonna is to ......"
Richard, perhaps your point is that IQ tests assume certain implicit
background knowledge. I stated in my email that AIXI would equal any
other intelligence starting with the same initial knowledge set.... So,
your point is that IQ tests assume an initial knowledge set that is part
and parcel of human culture.
One approach would be to use IQ tests that are purely formal and don't
require specific cultural knowledge. Test that consist of logic
puzzles, visual pattern recognition puzzles, etc. There are plenty of
IQ test questions like this.
Another approach would be to utilize a form of IQ test that assumes the
test-taker has access to a particular, standard subset of Wikipedia.
The questions would then be engineered not to require specific factual
knowledge about the world, aside from what's available in this subset of
Wikipedia.
This way, the initial knowledge base needed to answer the IQ questions
could be specified as a certain series of bits, which could be fed to
AIXI as part of its initial knowledge state.
So, I think my point still holds: "Do really well on a long series of IQ
tests, given an appropriate file of background knowledge" is a goal that
can be fit into the mathematical framework of AIXI. And the theorems
show that AIXI will kick ass at achieving this goal.
Your only way to argue against this, consistently, would be to argue
that there is no way to create an appropriate file of background
knowledge to feed AIXI, because passing an IQ test relies on a body of
knowledge that is intrinsically unformalizable, or at least incredibly
difficult to formalize.
I really don't believe this is true, but refuting it would require
detailed analysis of a long series of IQ questions, which sounds like a
boring way to spend the rest of the afternoon...
-- Ben
Would AIXI have to build a solution by implicitly deconstructing (if
you see what I mean) the entire real universe, including its real
human societies and real (intelligent) human beings and real social
relationships?
If AIXI does a post-hoc deconstruction of some "real" intelligent
systems as part of building its own "intelligent" function, it is
parasitic on that intelligence.
You can confirm that it is not parasitic in that way?
Richard Loosemore.
OTOH, Pei Wang has proposed that intelligence should be explicitly
defined as something roughly like "achieving complex goals given
limited resources" [not his exact wording]. In this case AIXI would
not be considered intelligent....
But my view is that the natural language concept of intelligence
actually is just about functionality rather than mechanisms. We say
someone is smart because of the problems they can solve, not because
of our understanding of how they go about solving the problems...
Anyway, the NL notion of "intelligence" is not necessarily any more
intrinsically meaningful than the NL concepts of "cup" and
"bowl".... It combines a bunch of deep ideas with some culturally
relative and anthropomorphic stuff that is not so important...
The notion of intelligence embodied in AIXI is an interesting one,
which things can be proved about.... I don't claim that it exhausts
the interesting insights contained in the ambiguous and diverse NL
concept of intelligence...
-- Ben G
-----
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=11983
-----
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=11983