Hey Ben!
The above is really your meaty hypothesis, I'd say...
Absolutely. And there's really only one way to prove or disprove it.
You may be right, but my feeling is that it will work more reliably to
start off with the ONE domain of embodied interaction w/ a 3D world,
and get the system to have knowledge of this domain via interacting
with it.
To me, these seem to be almost entirely different problems. I think that
for what you're trying to learn (and the way in which you're teaching
Novamente to learn), the embodied approach might teach you a lot. My
approach has the benefit of also having tangible side-projects that I'm
interested in. Diversity is good and we can always learn from each other
after we've gotten somewhere (or not :-).
Then, with this knowledge and the ability to
generalize/analogize/etc., the bootstrapping process you mention will
more more feasible for extending the system's understanding into other
domains.
I think that generalization and analogization (how's that for verbification
that a system needs to learn how to handle?) is actually intrinsic *in the
structure* of the system that I'm proposing/building but something that
you're going to have to do with a lot of work on your Mind Agents. A
clearer way of stating how I perceive our approaches as differing would be
to say that I believe that you are learning by discovery while I am
accumulating already discovered knowledge and resolving conflicts. I think
that we are attacking two very different, complementary problems.
Mark
----- Original Message -----
From: "Benjamin Goertzel" <[EMAIL PROTECTED]>
To: <agi@v2.listbox.com>
Sent: Wednesday, April 18, 2007 9:51 AM
Subject: Re: [agi] AGI interests
Hi Mark,
Preposition disambiguation is "badly unsolved" because (I believe) it
requires domain knowledge to do effectively and people are trying to do
it
without domain knowledge. The same is true of reference resolution. I
think that these things are eminently soluble once you have the domain
knowledge wired in (and I think that you can bootstrap enough of the
domain
knowledge with the simple stupid parser, active search, and inheritance).
The above is really your meaty hypothesis, I'd say...
You may be right, but my feeling is that it will work more reliably to
start off with the ONE domain of embodied interaction w/ a 3D world,
and get the system to have knowledge of this domain via interacting
with it.
Then, with this knowledge and the ability to
generalize/analogize/etc., the bootstrapping process you mention will
more more feasible for extending the system's understanding into other
domains.
-- 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/?&;
-----
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
