Hope I'm not covering old ground, but I'm wondering whether any one is
interested and would like to comment on Marr's idea of vision involving a
primal sketch at a basic level. I'm interested, despite much ignorance here,
because it links to the image schemas of Lakoff and co..
Here's an inter
I believe I offered the beginning of a v. useful way to conceive of this
whole area in an earlier post.
The key concept is "inventory of the world."
First of all, what is actually being talked about here is only a
VERBAL/SYMBOLIC KB.
One of the grand illusions of a literature culture is that
I should add to the idea of our common sense knowledge inventory of the
world - because my talk of objects and movements may make it all sound v.
physical and external. That common sense inventory also includes a vast
amount of non-verbal knowledge, paradoxically, about how we think and
communi
This raises another v. interesting dimension of KB's and why they are limited.
The social dimension. You might, purely for argument's sake, be able to name a
vast amount of unnamed parts of the world. But you would then have to secure
social agreement for them to become practically useful. Not
I got the impression from the recent interesting thread re vision that the
surface of the retina may be especially designed so as to "re-distort" that
distorted retinal image back into the proper shape we actually see.
A robotics friend, however, who is very into the visual cortex, insisted
th
This friend has now pointed out that the distortion of images handled by the
visual cortex (and not just the retina) is even more marked than suggested:
".. you kind of left out what I thought was most important in my previous
reply, but this page shows several links regarding this topic. Thing
Richard,
Thanks for response. But it surely *is* still a puzzle as to how and indeed
where that distorted image on the retina gets rectified and raises major
questions about vision. No one as, I understand, has the answer. I am too
ignorant to have a POV here - but my general experience is th
Ben: One advantage AGIs will have over humans is better methods for
translating
procedural to declarative knowledge, and vice versa. For us to translate
"knowing how to do X" into
"knowing how we do X" can be really difficult (I play piano
improvisationally and by
ear, and I have a hard time fi
Ben: Anyway, I agree with you that formal logical rules and inference are not
the
end-all of AGI and are not the right tool for handling visual imagination or
motor learning. But I do think they have an important role to play even so.
Just one thought here that is worth trying to express, althoug
king in principally body form not just
about how to move our own body, but how other bodies do and will move -
mirroring with those mirror neurons.
Mike Tintner <[EMAIL PROTECTED]> wrote:
The idea that an AGI can symbolically encode all the knowledge, and
perform
all the thinking, ne
Richard: Mike Tintner wrote:
No one in AGI is aiming for common sense consciousness, are they?
Inasmuch as I understand what you mean by that, yes of course.
Both common sense and consciousness.
As Ben said, it's something like "multisensory integrative consciousness" -
i
Ben: MT:>> You guys seem to think this - true common sense consciousness -
can all be
cracked in a year or two. I think there's probably a lot of good
reasons -
and therefore major creative problems - why it took a billion years of
evolution to achieve.
Ben: I'm not trying to emulate th
Ben:What evidence do you have that this [body thinking] is the "largest
part" ... it does
not feel at all
that way to me, as a subjectively-experiencing human; and I know of no
evidence
in this regard
Like I said, I'm at the start here - and this is going against thousands of
years of literat
WP: > I'm going to try and elucidate my approach to building an intelligent
system, in a round about fashion. This is the problem I am trying to
solve.
Marks for at least trying to identify an AGI problem. I can't recall anyone
else doing so - which, to repeat, I think is appalling.
But I d
Er, just to clarify. You guys have, or know of, AI systems which run continuous
movies of the world, analysing and responding to those movies with all the
relevant senses, as discussed below, and then to the world beyond those movies,
in real time (or any time, for that matter)?
Mike
is that in discussing this whole area, both in
AI, philosophy & cog sci/psych, people tend to forget that consciousness is
a continuously moving picture with the other senses continuous too, and tend
to think, even if only implicitly, in terms of stills.
Mike Tintner wrote:
Er, just t
ent visual systems might make that connection.
And I would assert - and am increasingly confident - that the grammar of
language - how we put words together in whatever form - is based on cutting
together internal *movies* in our head - not still images,but movies.
They don't teach movie
Robert:
I think it would be more accurate to say that technological meme evolution was
caused by the biological evolution, rather than being the extension of it,
since they are in fact two quite different evolutionary systems, with different
kinds of populations/survival conditions.
I would sa
Vlad:> Don't you know about change blindness and the like? You don't
actually
see all these details, it's delusional. You only get the gist of the
scene, according to current context that forms the focus of your
attention. Amount of information you extract from watching a movie is
not dramatica
ies, and
presumably all the visual arts. Strange too that the brain should spend most
of the night then creating its own movies and insists on seeing events when
according to you guys, it could just much more quickly and less effortfully
look at their symbolic forms.
You're right, this is fun.
detailed,impressive timetable for how long it'll take them to produce such
an idea, they just will never produce one. Frankly, they're too scared).
Mike Tintner <[EMAIL PROTECTED]> wrote:
You must first define its existing skills, then define the new challenge
with some d
it
doesn't work this way. Because it can't work that way. An AGI
working in unknown territory will have to make mistakes.
Andi
Quoting Mike Tintner <[EMAIL PROTECTED]>:
Jeez, Will, the point of Artificial General Intelligence is that it can
start adapting to an unfamiliar
on this list who dream of creating an AGI, no?
-Original Message-
From: Mike Tintner [mailto:[EMAIL PROTECTED]
Sent: March-02-08 5:36 AM
To: agi@v2.listbox.com
Subject: Re: [agi] Thought experiment on informationally limited
systems
Jeez, Will, the point of Artificial General Intelligence i
YKY: the way our language builds up new ideas seems to be very complex, and it
makes natural language a bad knowledge representation for AGI.
An even more complex example:
"spread the jam with a knife"
"draw a circle with a knife"
"cut the cake with a knife"
"rape the girl with a knife"
"stop
You seem to grasp my point, and then let it slip through your fingers -
although perhaps I need to spell it out.
Human concepts (of which language is the most prominent example) are
fundamentally open-ended - and MEANT to be. Philosophers and rational thinkers
of all kinds have fought against t
David: >I was specifically referring to your comment ending in "BY ITSELF".
Jeez, Will, the point of Artificial General Intelligence is that it
can start adapting to an unfamiliar situation and domain BY ITSELF.
I believe this statement is just plain incorrect.
David,
I find that extraordi
Will:Is generalising a skill logically the first thing that you need to
make an AGI? Nope, the means and sufficient architecture to acquire
skills and competencies are more useful early on in an agi
development
Ah, you see, that's where I absolutely disagree, and a good part of why I'm
hammering
Dead right (in an ambiguous way :) )
Basically an AGI without open-ended concepts will never live in the real world.
I should add that I don't believe early, true AGI's *will* be anywhere near
capable of natural language. All they will need is one or more systems of
open-ended concepts.
Emoti
Vlad: How to survive a zombie attack?
I really like that thought :). You're right:we should seriously consider
that possibility. But personally, I don't think we need to be afraid ... I'm
sure they will be friendly zombies...
---
agi
Archives: http:/
Pei:ScienceDaily (Mar. 4, 2008) — iCub, a one metre-high baby robot which
will be used to study how a robot could quickly pick up language
skills, will be available next year.
http://www.sciencedaily.com/releases/2008/02/080229141032.htm
Thanks - but it looks like here we go again:
"now, within
Bob:
http://streebgreebling.blogspot.com/2008/03/running-before-you-can-walk.html
The "running before you walk" analogy is interesting. It gives rise to the
seed of an idea. Basically, a vast amount of what is happening and has
happened in AGI and robotics is ridiculous - a whole series o
[Someone please explain this to me]:
http://www.eurekalert.org/pub_releases/2008-03/danl-loa030708.php
Language of a fly proves surprising
Insect's sensory data tells a new story about neural networks
LOS ALAMOS, New Mexico, March 10, 2008-A group of researchers has developed a
novel way to view t
William,
This is v. helpful. It sounds like you're saying that neural networks have
treated what could actually be different kinds of music, with many of the
features of music, such as length of note and rhythm, purely quantitatively
for just, say, the number of beats. In which case we could b
Charles: >> I don't think a General Intelligence could be built entirely out
of
narrow AI components, but it might well be a relatively trivial add-on.
Just consider how much of human intelligence is demonstrably "narrow AI"
(well, not artificial, but you know what I mean). Object recognition,
e
John,
I'm developing this argument more fully elsewhere, so I'll just give a
partial gist. What I'm saying - and I stand to be corrected - is that I
suspect that literally no one in AI and AGI (and perhaps philosophy) present
or past understands the nature of the tools they are using.
All th
Ben:It's not just that we can CHOOSE the meanings of concepts from a fixed
menu
of possibilities ... we CREATE the meanings of concepts as we use them ...
this is how and why concept-meanings continually change over time in
individual minds and in cultures...
Yes. Good point. Generality/open-end
d agent -
hence the use of the word "handle" in this construction.
-Steve
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: Mike Ti
ecise geometry/ geography) of thought - i.e.
a system of mental image schemas - becomes apparent.
- Original Message -
From: Stephen Reed
To: agi@v2.listbox.com
Sent: Friday, March 28, 2008 4:30 AM
Subject: Re: [agi] Microsoft Launches Singularity
- Original Message
Robert/Ben:. In fact. I would suggest that AGI researchers start to
distinguish
themselves from narrow AGI by replacing the over ambiguous concepts from
AI,
one by one. For example:
knowledge representation = world model.
learning = world model creation
reasoning = world model simulation
goal
Durk,
Absolutely right about the need for what is essentially an imaginative level of
mind. But wrong in thinking:
"Vision may be classified under "Narrow" AI"
You seem to be treating this extra "audiovisual perception layer" as a purely
passive layer. The latest psychology & philosophy recogn
In this & surrounding discussions, everyone seems deeply confused - & it's
nothing personal, so is our entire culture - about the difference between
SYMBOLS
1. "Derek Zahn" "curly hair" "big jaw" "intelligent eyes" . etc. etc
and
IMAGES
2. http://robot-club.com/teamtoad/nerc/h2-derek
MW:
MT:>> Why are images almost always more powerful than the corresponding
symbols? Why do they communicate so much faster?
Um . . . . dude . . . . it's just a bandwidth thing.
Vlad:Because of higher bandwidth?
Well, guys, if the only difference between an image and, say, a symbol
e important.
But if you can't see things whole, then you can't see or connect with the real
world. And, in case you haven't noticed, no AGI can connect with the real
world. In fact, there is no such thing as an AGI at the moment. And there never
will be if machines can't do w
FAKES your conscious mind
into believing that the input came in that way. Why can't you believe that a
computer can do the same thing? Why can't one input device of an AGI take a
natural language description and convert it into a picture and send it to the
main AGI consciousness whi
Richard: What *exactly* do you mean by "an AGI must be able to see in
wholes"? My point is that you cannot make criticisms at that level of
vagueness.
I'll give the detailed explanation that I think you're looking for, within
a few days.
P.S. Maybe then you'll be able to return the favour,
Richard: I already did publish a paper doing exactly that ... haven't you
read it?
Yep. And I'm still mystified. I should have added that I have a vague idea
of what you mean by complex system and its newness, but no idea of why it
will solve any unsolved problem of AGI, and absolutely no id
Charles H: Due to this, the resource management should not be algorithmic,
but
free to adapt to the amount of resources at hand. I'm intent on a
economic solution to the problem, where each activity is an economic
actor.
The idea of economics is v. interesting & important. I think - & I'm
ideas.
P.S. An advertising/marketing no-no - never use s.o. else' s title for your
site. It doesn't bespeak originality.
Mike Tintner wrote:
Richard: I already did publish a paper doing exactly that ... haven't
you read it?
Yep. And I'm still mystified. I should have added t
meone
saying: "What's my idea? I'll tell you - I'm going to get the best brains
[or computers] that money can buy - loads & loads of them. And get them to
come up with an idea. Pretty original, huh?"
That's not an idea, Richard. *You* have to come up with that..
meone
saying: "What's my idea? I'll tell you - I'm going to get the best brains
[or computers] that money can buy - loads & loads of them. And get them to
come up with an idea. Pretty original, huh?"
That's not an idea, Richard. *You* have to come up with that..
"What's my idea? I'll tell you - I'm going to get the best brains
[or computers] that money can buy - loads & loads of them. And get them to
come up with an idea. Pretty original, huh?"
That's not an idea, Richard. *You* have to come up with that..
P.S. Yes I did
http://www.sciencedaily.com/releases/2008/03/080329122121.htm
http://cordis.europa.eu/ictresults/index.cfm/section/news/tpl/article/BrowsingType/Features/ID/89632
New Breed Of Cognitive Robot Is A Lot Like A Puppy
ScienceDaily (Mar. 31, 2008) - Designers of artificial cognitive systems
have te
t made to his audience to have a
clear demo of his system.
If you want to send me something, I'll gladly look at it & reply offline -
although I'm real busy at the mo. answering *your* last question.!
Best
Mike Tintner wrote:
Richard,
I can't swear that I did read it
I want to return to what seems to me the high-school-naive idea of how an AGI's
or any body of knowledge can and/or does grow - i.e. linearly, mathematically
and logically.
Correct me, but I haven't seen any awareness in AI of the huge difficulties
that result from the problem of : how do you t
MW/MT: Correct me, but I haven't seen any awareness in AI of the huge
difficulties that result from the problem of : how do you test acquired
knowledge?
MW:You're missing seeing it. It's generally phrased as "converting data to
knowledge" or "concept formulation" and it's currently generally
My broad point is that there is only one way to test knowledge ultimately -
physically.
Science demands physical evidence for everything.
It then has in effect a graded system of veracity (although there is no
formalised system). The truest knowledge comes from direct physical observation
an
Richard:the idea
that "perception is [the] fairly passive reception of impressions..." is
so old and out of date that if you pick up a textbook on cognitive
psychology printed 30 years ago you will find it dismissed as wrong.
This is the issue of top-down vs bottom-up processing
No it isn't. You'
Richard:Now, if what you *meant* to talk about was links between action and
perception, all well and good, but I was just addressing the above
comment of yours.
I'm certainly not reiterating an ancient debate. This has been from the
start an exploratory thread. Prinz summarises fairly well wha
Richard:Personally, I think that embodiment makes the development process
vastly
easier, but this black and white declaration of IMPOSSIBLE! that you
shout seems to go too far.
Well, that's the point of discussing this - yes, the culture still allows
your position. But the new cog sci developme
Richard,
Just an addendum to my question - I'm quite happy to take just one
disembodied subject area. But - and this is an interesting point - since
we're talking A*General*I - there should really be at least two.
---
agi
Archives: http://www.listbox.
MW: I believe that I was also quite clear with my follow-on comment of "a
cart
before the horse problem. Once we know how to acquire and store
knowledge, then we can develop metrics for testing it -- but, for now,
it's too early to go after the problem." as well.
You're basically agreeing wit
Impressive. Especially their Rhex robot - v. resilient in v. different
terrains:
http://www.youtube.com/watch?v=wIuRVr8z_WE&feature=related
Peruse the video:
http://www.youtube.com/watch?v=W1czBcnX1Ww&feature=related
Of course, they are only showing the best stuff. And I am sure there
is ple
Brad:What's really impressive is how "natural" the leg movements are
So natural, I wondered whether it wasn't a hoax with real people in there.
---
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive
Steve:If you've
got a messy real-world problem, you know little, if you have an
algorithm giving the solution, you know all.
This is the bit where, like most, you skip over the nature of AGI - messy
real-world problems. What you're saying is: "hey if you've got a messy problem,
it's great, nay
Pei: I believe AGI is basically a theoretical problem, which will be solved
by a single person or a small group, with little funding
How do you define that problem?
---
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listb
Pei: I don't really want
a big gang at now (that will only waste the time of mine and the
others), but a small-but-good gang, plus more time for myself ---
which means less group debates, I guess. ;-)
Alternatively, you could open your problems for group discussion &
think-tanking... I'm surp
[Sci Am] May 08
The first generation of World Wide Web capabilities
rapidly transformed retailing and information
search. More recent attributes such as blogging,
tagging and social networking, dubbed Web 2.0,
have just as quickly expanded people's ability not just
to consume online information b
Current Directions in Psychological Science - April 2008 - In Press
http://www.psychologicalscience.org/journals/cd/17_2_inpress/Barsalou_completed.pdf
THE DOMINANT THEORY IN COGNITIVE SCIENCE
Across diverse areas of psychology, computer science, linguistics, and
philosophy, the
dominant accou
gence by processing holistic images.
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: Mike Tintner <[EMAIL PROTECTED]>
To: agi@v2.listbox
orth. The brain does not achieve its
powerful forms of intelligence by processing holistic images.
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:
Ben/Joshua:
How do you think the AI and AGI fields relate to the embodied & grounded
cognition movements in cog. sci? My impression is that the majority of
people here (excluding you) still have only limited awareness of them - &
are still operating in total & totally doomed defiance of their
I think one can now present a convincing case why any symbolic/linguistic
approach to AGI, that is not backed by imaginative simulation, simply will
not work. For example, any attempt to build an AGI with a purely symbolic
database of knowledge mined from the Net or other texts, is doomed.
Th
Abram,
Both to-the-point responses. One: how much, you're asking, are statements
about movement central to language? Extremely central. That's precisely why
we have this core "general activity/movement language" that we all share -
all those very basic movement words - we use them so often. H
Abram,
Just to illustrate further, here's the opening lines of today's Times sports
report on a football match.[Liverpool v Chelsea] How on earth could this be
understood without massive imaginative simulation? [Stephen?] And without
mainly imaginative memories of football matches?
"John Arn
in the same way Cyc did.
-Steve
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: Mike Tintner <[EMAIL PROTECTED]>
To: agi@v2.list
Stephen:Mike, have you given any thought to how deaf and blind humans become
mentally competent?
Certainly. By using their touch, smell, kinaesthetic and the other
sensorimotor sensations of their own body to get to know the world. Blind
people can draw - they can draw outlines of object
ing back where we
might claim to "understand" text w/o sensory experience of its subject
matter. So my question is: what's the difference? (Unless it really is
just holding back those claims of text understanding w/o real-world
sensory data-- which is a fine point.)
On Wed, Apr
Vlad: I agree that some kind of simulation is necessary, probably something
equivalent on high level to a 3D vector sketch of the events
developing in time, containing actors, where necessary structural
schemes of their bodies interacting with structure of the scene, etc.
The recurrent, but u
Steve:What is a novel solution?! Since THIS question seems to be driving much
the current AGI efforts, I think that this should be completely wrung out.My
program will identify the parts of the problem that ARE known and direct effort
to the "missing pieces".
You're right that creativity, smal
MW: I see all your references are reinforcing the need for grounding and
some
showing how grounding *can* be accomplished by images (among many other
methods :-), but I have yet to find any of your references clearly saying
all meanings must be grounded BY IMAGES. That was the basis for my last
between "metric" and "semantic" approaches to vision
processing.
Comments?
Bob: Mike Tintner >> The recurrent, but underlying question in many
related discussions here is
whether you, (& Bob & a & linas), think a visual scene - let's say some
people
MT: http://honolulu.hawaii.edu/distance/sci122/Programs/p3/Rorschach.gif
(Oh - and a, linas, Bob, Mark, et al - can we agree that there is no way
for maths to process that image, period?)
Mark:No. I strongly disagree with your assertion. What you believe you are
processing (w)holistically can
Just getting a basically
adaptive program that pace Ben's could develop something like hide-and-seek
independently, after learning to fetch, is hard enough - or a maze-running
creature that could, say, learn to climb over maze walls and not just run round
them..
Mike,
On 4/24/08,
BillK: MT:>> So what you must tell me is how your or any geometrical system
of analysis
is going to be able to take a rorschach and come up similarly with a
recognizable object or creature. Bear in mind, your system will be given
no
initial clues as to what objects or creatures are suitable as
Matthias: a state description could be:
...I am in a kitchen. The door is open. It has two windows. There is a
sink. And three cupboards. Two chairs. A fly is on
the right window. The sun is shining. The color of the chair is... etc.
etc.
..
Bob: I'm not totally convinced that having a high number of degrees of
freedom is actually necessary for the development of intelligence. Of
greater importance is the sensory capability, and the ways in which
that data is processed. A birds beak is a far less elaborate tool
than a human hand or
Bob: Particularly I'd be interested in having
the robot learn a model of its own body kinematics - the beginnings of
a sense of self - based on data mining its sensory data and also using
experimental movements to confirm or refute hypotheses, which mught to
a naive observer look like "play".
Cor
Russell,
This is a definite start and I'm just trying to put together a reasoned
thesis on this area. You're absolutely right that this is essential to
understanding AGI - General Intelligence - and literally no one does have
other than tiny fragments of understanding here, either in AI/AGI or
Moving on from my previous post, the key distinction in mentality between
the literate and the new multimediate mentality is between PRE-SEMIOTIC and
SEMIOTIC.
The presemiotic person starts from the POV of his specialist sign system
and medium, when thinking about solving particular problems,
igence is
viewed without distinguishing "mature" from fledgling.
I'm interested in the "minimal" system. I consider it my good fortune to
have a good seat to observe historic events - I appreciate the project,
this list, and it's contributors.
Mike Tintner
ds work is the cross-modal interaction, and
understanding the details of how the heuristics arise in the first place
from
the pressures of real-time processing constraints and deliberative
modelling.
Josh
On Tuesday 29 April 2008 11:12:28 am, Mike Tintner wrote:
Josh:You can't d
JAR/Russell:
This seems to be an example of what I was talking about in the other
thread - AI-ers starting with the set of sign systems and tools - and here
the kinds of intelligence - they know of personally, professionally, and
assume that they are the only kind, and encompass all types of
So what are the principles that enable animated characters and materials
here to react/move in individual continually different ways, where previous
characters reacted typically and consistently?
Ben Now this looks like a fairly AGI-friendly approach to controlling
animated characters ... unfo
..or is it just that these figures respond differently to the slightest
difference in angle and force of impact?
---
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscri
Charles: as far as I can tell ALL modes of human thought
only operate within restricted domains.
I literally can't conceive where you got this idea from :). Writing an
essay - about, say, the French Revolution, future of AGI, flaws in Hamlet,
what you did in the zoo, or any of the other many
The link from Lukas seems to suggest that applying this technology is
something of an art (is that right?):
"As a side note, the fickle nature of the evolutionary approach is the
primary reason why euphoria isn't middleware; the team at NaturalMotion
helps you integrate it. Most often, you hav
Charles: Flaws in Hamlet: I don't think of this as involving general
intelligence. Specialized intelligence, yes, but if you see general
intelligence at work there you'll need to be more explicit for me to
understand what you mean. Now determining whether a particular deviation
from iambic
Charles,
We're still a few million miles apart :). But perhaps we can focus on
something constructive here. On the one hand, while, yes, I'm talking about
extremely sophisticated behaviour in essaywriting, it has generalizable
features that characterise all life. (And I think BTW that a dog is
Matthias,
Your remarks stimulated some interesting thoughts for me re concept
organisation. I agree with what you seem to be implying that every concept
must be a cluster of different POV images, and/or image schemas in the
brain.
But that cluster must have a normal organisation.
The bigges
MH: Since we cannot explain qualia we can also a never answer the question
whether qualia is necessary for AGI
Well, clearly you do need emotions, continually evaluating the
worthwhileness of your current activity and its goals/ risks and costs - as
set against the other goals of your psychoeco
301 - 400 of 908 matches
Mail list logo