Vision could cover many things. Two eyeballs the size of planets that only
see neutrinos could constitute a vision system. Probes that see vibrations
or heat or chemicals are vision. RADAR, LADAR, SONAR, seismic,
electromagnetic, PET scan, salinity, ph, any type of particle, energy, space
detection
Pei, Good post. Ed Porter
-Original Message-
From: Pei Wang [mailto:[EMAIL PROTECTED]
Sent: Saturday, October 13, 2007 11:29 AM
To: agi@v2.listbox.com
Subject: [agi] "symbol grounding" Q&A
Hi,
The current discussion on symbol grounding, to me, includes several
different (though relate
Mike,
I think there is a miscommunication, either at my end or yours.
I was arguing that grounding would use senses besides vision.
My posts have indicated that I believe higher level concepts are derived
from lower level concepts (the gen/comp hierarchy of patterns I have
referred to, as reflec
Josh,
Also a good post.
You seem to be defining "grounding" as having meaning, in a semantic
sense. If so, why is it a meaningless question to ask if "2" in your
calculator has grounding, since you say the calculator has limited but
real semantics. Would not the relationships "2" has to other n
On Monday 15 October 2007 10:21:48 am, Edward W. Porter wrote:
> Josh,
>
> Also a good post.
Thank you!
> You seem to be defining "grounding" as having meaning, in a semantic
> sense.
Certainly it has meaning, as generally used in the philosophical literature.
I'm arguing that its meaning ma
On Sat, Oct 13, 2007 at 03:28:51PM +0100, Mike Tintner wrote:
>
> "I felt sad" - is a grounded statement - grounded in your internal
> kinaesthetic experience of your emotions.
OK..
> Would you like to rephrase your question in the light of this - the common
> sense nature of grounding, which
On Sat, Oct 13, 2007 at 03:35:07PM +0200, Lukasz Kaiser wrote:
> it has nothing to do with grounding as discussed here.
OK, clearly, I missed something. What, then, was meant by "grounding"?
> I think that people normally use much more concrete models in their
> heads when working and only later
In response to you below post, I have responded in all-cap to certain
quoted portions of it.
I'm arguing that its meaning makes an assumption about the nature of
semantics that obscures rather than informing some important questions
WHAT EXACTLY DO YOU MEAN?
I'd just say that for the 2 in my
Edward,
I think that Storrs-Hall's post threw unnecessary confusion onto what
was, in fact, a very clear statement that Pei Wang originally made on
the matter.
Harnad's original idea had something relatively simple at its core: if
you see an AGI system using concepts with names attached to
On Monday 15 October 2007 01:25:22 pm, Edward W. Porter wrote:
> I'm arguing that its meaning makes an assumption about the nature of
> semantics that obscures rather than informing some important questions
>
> WHAT EXACTLY DO YOU MEAN?
I think that will become clearer below:
> I JUST READ T
On Monday 15 October 2007 01:57:18 pm, Richard Loosemore wrote:
> AI programmers, in their haste to get something working, often simply
> write some code and then label certain symbols as if they are
> meaningful, when in fact they are just symbols-with-labels.
This is quite true, but I think it
This is in response to Josh Storrs Monday, October 15, 2007 3:02 PM post
and Richard Loosemores Mon 10/15/2007 1:57 PM post.
I mis-understood you, Josh. I thought you were saying semantics could be
a type of grounding. It appears you were saying that grounding requires
direct experience, but t
Linas:
However, once one has actually learned how to think abstractly,
its not obvious to me that sensory grounding is needed; and indeed,
trying to touch back to the grounding can prevent one from
making the next leap of abstraction.
Would you say that once your brain has learned that a set of
On 10/15/07, Linas Vepstas <[EMAIL PROTECTED]> wrote:
>
> Yes, of course, children learn to reason from concrete to more abstract
> levels, and lawyers, engineers and mathematicians working at a
> particularly abstract level. The concrete levels are indeed
> grounded in sensory input.
>
> However,
14 matches
Mail list logo