Ben,
Thanks for reply.
What then is the idea[s] for grounding this system?
When the Opencog brain says "pick up the box" to the robot, what will "box"
and "pick up" connect to in the robot system?
How does Arel, say, (your collaborator?) represent "box" in his
recognition system? An algorithm that can be instantiated in various
physical/visual forms?
And what will the robot system have for "pick up"? Again some kind of
variable movement routine?
Is this sort of thing BTW discussed much here/elsewhere? I can't recall many
if any discussions about the exact principles for grounding - correct me.
We certainly should be discussing ideas for all this a lot.
-----Original Message-----
From: Ben Goertzel
Sent: Tuesday, August 28, 2012 2:46 PM
To: AGI
Subject: Re: [agi] Finding the "Right" Computational Model to Support
Occam's Razor
On Tue, Aug 28, 2012 at 5:47 AM, Mike Tintner <[email protected]>
wrote:
This isn't designed to produce a real world embedded language user, is it?
S.o. who can go into the world and sit on a "chair", "pick up" a "box",
"move" this over "there", is it? S.o. who *understands* language and
"knows
what they're talking about" ?
As I have very clearly articulated in the past many times: yes, that
is the intention
Why is this any different from, or superior to, NLP?
The specific subproject under discussion **is** NLP; but it's NLP done
in the context
of an integrative AI system (OpenCog), that also involves many things
that are not NLP.
At the moment OpenCog is being used to control a video game agent in
a game world,
but we are planning a collaboration w/ David Hanson to use it to
control his Robokind
robots.
So, the NLP subsystem in question would be used as one ingredient in an
overall
system aimed at controlling autonomous agents. However, due to the wonders
of
modular software design, this same NLP subsystem could be used in narrow AI
applications, or in other AGI designs quite different from my own
(e.g. it could be used
in purely NLP-focused AGI designs with no embodiment component).
I understand fully that you find this sort of integrative approach
unpromising, and so this
reply is mainly directed to any newbies on the list who might otherwise get
confused by your reply...
-- Ben G
-----Original Message----- From: Ben Goertzel
Sent: Tuesday, August 28, 2012 1:15 AM
To: AGI
Subject: Re: [agi] Finding the "Right" Computational Model to Support
Occam's Razor
Our internal semantic representation has nothing in common with the link
parser representation either:
http://wiki.opencog.org/w/OpenCogAtomTypes
Pretty much, I suppose if you don't like this sort of representation,
then
you won't want to do your project in OpenCog...
And see here
http://wiki.opencog.org/w/WordNode
for the way linguistic content is currently represented, though many of
these
details will be changed/augmented as a result of Ruiting's work in the
next
months...
-- Ben
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/6952829-59a2eca5
Modify Your Subscription: https://www.listbox.com/member/?&;
Powered by Listbox: http://www.listbox.com
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/212726-11ac2389
Modify Your Subscription:
https://www.listbox.com/member/?&;
Powered by Listbox: http://www.listbox.com
--
Ben Goertzel, PhD
http://goertzel.org
"My humanity is a constant self-overcoming" -- Friedrich Nietzsche
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/6952829-59a2eca5
Modify Your Subscription:
https://www.listbox.com/member/?&;
Powered by Listbox: http://www.listbox.com
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription:
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com
