- Original Message
From: Mike Tintner <[EMAIL PROTECTED]>
To: agi@v2.listbox.com
Sent: Thursday, May 8, 2008 9:05:22 PM
Subject: Re: Symbol Grounding [WAS Re: [agi] AGI-08 videos]
I just want to make the point that I think categorical "grounding" is necessary
Hi Jim,
Funny, I was just thinking re the reply to your point, the second before I
read it. What I was going to say was: I read a lot of Harnad many years ago,
and I was a bit confused then about exactly what he was positing re the
intermediate levels of processing - iconic/categorical.
- Original Message
From: Mike Tintner <[EMAIL PROTECTED]>
To: agi@v2.listbox.com
Sent: Thursday, May 8, 2008 8:16:32 PM
Subject: Re: Symbol Grounding [WAS Re: [agi] AGI-08 videos]
No, a symbol is simply anything abstract that stands for an object - word
sounds, alphabetic
No, a symbol is simply anything abstract that stands for an object - word
sounds, alphabetic words, numbers, logical variables etc. The earliest
proto-symbols may well have been emotions.
My point is that Harnad clearly talks of two intermediate visual/sensory
levels of processing - the iconi
You may want to check out the background material on this issue. Harnad
invented the idea that there is a 'symbol grounding problem', so that is
why I quoted him. His usage of the word 'symbol' is the one that is
widespread in cognitive science, but it appears that you are missing
this, and
ve
Stephen L. Reed
Artificial Intelligence Researcher
http://texai.org/blog
http://texai.org
3008 Oak Crest Ave.
Austin, Texas, USA 78704
512.791.7860
- Original Message
From: Lukasz Stafiniak <[EMAIL PROTECTED]>
To: agi@v2.listbox.com
Sent: Tuesday, May 6, 2008 11:25:35 AM
Subjec
On Tue, May 6, 2008 at 4:07 PM, Mark Waser <[EMAIL PROTECTED]> wrote:
>
> Note: Most of these complaints do *NOT* apply to Texai (except possibly
> the two to five level complaint -- except that Texai is actually starting at
> what I would call one of the middle levels and looks like it has reaso
ep problems and
less hacking to quickly achieve low-hanging fruit (and then stalling out
afterwards) definitely needs to be given more currency.
- Original Message -
From: "Benjamin Johnston" <[EMAIL PROTECTED]>
To:
Sent: Tuesday, May 06, 2008 4:36 AM
Subject: Re:
Richard Loosemore said:
But instead of deep-foundation topics like these, what do we get?
Mostly what we get is hacks. People just want to dive right and make
quick assumptions about the answers to all of these issues, then they
get hacking and build something - *anything* - to make it look
Richard wrote:
> Then, when we came back from the break, Ben Goertzel announced that the
> roundtable on symbol grounding was cancelled, to make room for some other
> discussion on a topic like "the future of AGI", or some such. I was
> outraged by this. The subsequent discussion was a pathetic
ttram <[EMAIL PROTECTED]>
To: agi@v2.listbox.com
Sent: Monday, May 5, 2008 5:02:28 PM
Subject: Re: [agi] AGI-08 videos
I was just watching Ben's AGI-08 presentation on neural nets
(http://video.google.co.uk/videoplay?docid=8672459372566545966) and
this does seem like an interesting and novel
I was just watching Ben's AGI-08 presentation on neural nets
(http://video.google.co.uk/videoplay?docid=8672459372566545966) and
this does seem like an interesting and novel idea as far as I know. I
hope Hugo de Garis was taking notes because that could be something
which he might be able to build
2008/5/5 Richard Loosemore <[EMAIL PROTECTED]>:
> I was pointing out that the 'interpreter' (i.e. the programmer) could build
> mechanisms that are only meaningful of the symbols conform to their
> interpretation of what the symbols mean.
>
> But if the system itself then builds symbols and uses
Ahah! Now I get it . . . .
Interesting . . . . In a lot of ways, this is actually a (relatively minor)
variant on what I'm always arguing with Ben when I keep insisting that more
levels and encapsulation and modularity need to be added to the design of
Novamente. He does seem to believe that
Bob Mottram wrote:
2008/5/5 Richard Loosemore <[EMAIL PROTECTED]>:
"The goal of symbol grounding is not to guarantee uniqueness but to ensure
that the connection between the symbols and the objects they are
systematically interpretable as being about does not depend exclusively on
an interpreta
2008/5/5 Richard Loosemore <[EMAIL PROTECTED]>:
> "The goal of symbol grounding is not to guarantee uniqueness but to ensure
> that the connection between the symbols and the objects they are
> systematically interpretable as being about does not depend exclusively on
> an interpretation projected
Derek Zahn wrote:
Richard Loosemore:
> So, for example, if I were organizing a conference on AGI I would want
> people to address such questions as:
I find your list of questions to be quite fascinating, and I'd love to
participate in an active list or conference devoted to these
"Foundati
Richard Loosemore:> So, for example, if I were organizing a conference on AGI I
would want > people to address such questions as:
I find your list of questions to be quite fascinating, and I'd love to
participate in an active list or conference devoted to these "Foundations of
Cognitive Comput
Mark Waser wrote:
> Hey Richard,
>
>You and I seem to have stalled out on the complexity question . . . .
Oh, it is only that I am under so much time pressure that I have become
exhausted by it. Sorry about that.
(Plus I have become distracted by comments elsewhere...)
>I don't mea
I'm not quite sure why Richard would want to quote Harnad. Harnad's idea of
how the brain works depends on it first processing our immediate sensory
images as "iconic representations" - not 1m miles from Lakoff's image
schemas. He sees the brain as first developing some kind of horse graphics,
Richard Loosemore writes:
> some very useful text about the symbol grounding problem.
Thank you Richard. For once I don't feel like a complete idiot. I am familiar
with these Harnad papers and find them quite clear. Beyond that I understand
your further explanation and even agree personal
Question 2.
A lot of the time it seems as if you are saying that engineering a complex
system is impossible . . . . (and that AGI *IS* complex).
Am I correct in this interpretation of your words?
If so, are you saying that AGI is entirely doomed or do you have some
solution?
Hey Richard,
You and I seem to have stalled out on the complexity question . . . .
I don't mean to be difficult but I'm still not sure that I'm getting the
point . . . . so let me try to recap what I think you're saying . . . .
Question 1.
Richard > The purpose of the argument
Richard
Bruno Frandemiche wrote:
bonjour richard
i read your mails.i don't understand your position and your agi
theory.can you explain me completely,slowly and argumentaly your theory
and your practice?and what are the difference about agi-08 and
you ?thanks you
Bruno,
I will do this, but it will
Derek Zahn wrote:
Richard Loosemore:
> I read Pei's paper and there was nothing horrifying about it (please
> spare the sarcasm).
No sarcasm intended. If I had just come to the conclusion that 28
papers in a row were a waste of time, I'd be horrified at the prospect
of a 29th that would a
Derek Zahn wrote:
Richard Loosemore:
> My god, Mark: I had to listen to people having a general discussion of
> "grounding" (the supposed them of that workshop) without a single person
> showing the slightest sign that they had more than an amateur's
> perspective on what that concept actual
Ben Goertzel wrote:
Loosemore wrote:
I hear people enthusing about systems that are filled with holes that were
discovered decades ago, but still no fix. I read vague speculations and the
use of buzzwords ('Theory of Mind'!?). I see papers discussing narrow AI
projects.
I suppose there was
AIL PROTECTED]>
À : agi@v2.listbox.com
Envoyé le : Dimanche, 4 Mai 2008, 21h52mn 34s
Objet : Re: [agi] AGI-08 videos
Derek Zahn wrote:
>
> I noticed yesterday that most of the videos of talks and panels from
> AGI-08 have been uploaded (http://www.agi-08.org/schedule.php). Big
&
Richard Loosemore:> My god, Mark: I had to listen to people having a general
discussion of > "grounding" (the supposed them of that workshop) without a
single person > showing the slightest sign that they had more than an amateur's
> perspective on what that concept actually means.
I was not a
Richard Loosemore:> I read Pei's paper and there was nothing horrifying about
it (please > spare the sarcasm).
No sarcasm intended. If I had just come to the conclusion that 28 papers in a
row were a waste of time, I'd be horrified at the prospect of a 29th that would
also not give me what I
Richard wrote:
> My god, Mark: I had to listen to people having a general discussion of
> "grounding" (the supposed them of that workshop) without a single person
> showing the slightest sign that they had more than an amateur's perspective
> on what that concept actually means.
I guess you are
Loosemore wrote:
> I hear people enthusing about systems that are filled with holes that were
> discovered decades ago, but still no fix. I read vague speculations and the
> use of buzzwords ('Theory of Mind'!?). I see papers discussing narrow AI
> projects.
I suppose there was all that at AGI-
Mark Waser wrote:
Richard,
You're not gaining any supporters this way
Prompted by your enthusiastic write-up, I just wasted one and a half
hours scanning through all of the AGI-08 papers that I downloaded
previously. I have 28 of them; they did not include anything from
Stephen Reed, nor
Derek Zahn wrote:
Richard Loosemore writes:
> Prompted by your enthusiastic write-up, I just wasted one and a half
> hours scanning through all of the AGI-08 papers that I downloaded
> previously. I have 28 of them; they did not include anything from
> Stephen Reed, nor any NARS paper, so I
On Mon, May 5, 2008 at 12:44 AM, Richard Loosemore <[EMAIL PROTECTED]> wrote:
>
> Then it is just another bandwagon, like "Expert Systems", "Neural
> Networks", "Embodied Systems" ..
>
> I have had branding up to the eyeballs.
>
> Content is what matters.
>
There would be little content if
Richard Loosemore writes:> Prompted by your enthusiastic write-up, I just
wasted one and a half > hours scanning through all of the AGI-08 papers that I
downloaded > previously. I have 28 of them; they did not include anything from
> Stephen Reed, nor any NARS paper, so I guess my collection mus
Vladimir Nesov wrote:
On Sun, May 4, 2008 at 11:52 PM, Richard Loosemore <[EMAIL PROTECTED]> wrote:
I saw absolutely nothing that makes me believe that a field called
"Artificial General Intelligence" even exists yet. To the extent that there
were any proposals concerning complete architecture
On Sun, May 4, 2008 at 11:52 PM, Richard Loosemore <[EMAIL PROTECTED]> wrote:
>
> I saw absolutely nothing that makes me believe that a field called
> "Artificial General Intelligence" even exists yet. To the extent that there
> were any proposals concerning complete architectures, those proposal
Derek Zahn wrote:
I noticed yesterday that most of the videos of talks and panels from
AGI-08 have been uploaded (http://www.agi-08.org/schedule.php). Big
thanks to the organizers for that!
I have some difficulty getting into some of the papers but the 10-ish
minute overview talks are by a
Hi,
>Somebody could write an excellent paper about the
> potential pitfalls of such an approach (detail, fidelity, deep causality
> issues behind appearance, function, and inter-object + inter-feature
> relationships, and so on). If nobody else is working in detail on
> publishing such an analysi
Thanks for the comments from Derek and Bob!
Here are some assumptions made when planning AGI-08:
(1) As the very first conference in the field, it should play an
important role in the forming of the community, which means to let the
researchers know each other. For this reason, it was decided to
Bob Mottram writes:
> I havn't watched all of the AGI-08 videos, but of those that I have> seen the
> 15 minute format left me non the wiser. With limited time I> would have
> preferred longer talks with more depth but perhaps fewer in> number,
> especially on the more mathematical topics. >
2008/5/4 Derek Zahn <[EMAIL PROTECTED]>:
> I have a suggestion for such a task: figuring out how to operate the
> buttons-and-light system that determines whose turn it is to talk during
> panel discussions. It may be too ambitious though, as clearly it requires
> superhuman intelligence (har ha
2008/5/4 Derek Zahn <[EMAIL PROTECTED]>:
> * Limiting people to 10-12 minutes makes it basically impossible to present
> the contents of a paper, so the talks turn into project overviews. Actually
> I found that to be a GOOD thing, and hope it continues that way (as long as
> we don't get the sam
One other observation I forgot to mention: Several people brought up the
desirability of some kind of benchmark problem area to help compare the methods
and effectiveness of various approaches. For a bunch of reasons I think it
will be difficult to define such things in a way that researchers
45 matches
Mail list logo
