Re: [agi] AGI Alife
Interesting article: http://www.newscientist.com/article/mg20727723.700-artificial-life-forms-evolve-basic-intelligence.html?page=1 On Sun, Aug 1, 2010 at 3:13 PM, Jan Klauck jkla...@uni-osnabrueck.dewrote: Ian Parker wrote I would like your opinion on *proofs* which involve an unproven hypothesis, I've no elaborated opinion on that. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ 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/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] The Math Behind Creativity
That's interesting, and I think I agree mostly, at least abstractly. So this is really just a high-level comment on how to approach creativity, correct? I guess the title Mathematics of Creativity is what confused me. None of this suggests any real mathematical or computational perspective that will tell us something new or useful (or creative?) about creativity, right? Or am I missing something? On Sun, Jul 25, 2010 at 9:42 PM, Mike Tintner tint...@blueyonder.co.ukwrote: I wasn't trying for a detailed model of creative thinking with explanatory power - merely one dimension (and indeed a foundation) of it. In contrast to rational, deterministically programmed computers and robots wh. can only operate in closed spaces externally, (artificial environments) and only think in closed spaces internally, human (real AGI) agents are designed to operate in the open world externally, (real world environments) and to think in open worlds internally. IOW when you think about any creative problem, like what am I going to do tonight? or let me write a post in reply to MT - you *don't* have a nice neat space/frame of options lined up as per a computer program, which your brain systematically checks through. You have an open world of associations - associated with varying degrees of power - wh. you have to search, or since AI has corrupted that word, perhaps we should say quest through in haphazard, nonsystematic fashion. You have to *explore* your brain for ideas - and it is a risky business, wh. (with more difficult problems) may draw a blank. (Nor BTW does your brain set up a space for solving creative problems - as was vaguely mooted in a recent discussion with Ben. Closed spaces are strictly for rational problems). IMO though this contrast of narrow AI/rationality as thinking in closed spaces vs AGI/creativity as thinking in open worlds is a very powerful one. Re your examples, I don't think Koestler or Fauconnier are talking of defined or closed spaces. The latter is v. vague about the nature of his spaces. I think they're rather like the formulae for creativity that our folk culture often talks about. V. loosely. They aren't used in the strict senses the terms have in rationality - logic/maths/programming. Note that Calvin's/Piaget's idea of consciousness as designed for when you don't know what to do accords with my idea of creative thinking as effectively starting from a blank page rather than than a ready space of options, and going on to explore a world of associations for ideas. P.S. I should have stressed that the open world of the brain is **multidomain**, indeed **open-domain by contrast with the spaces of programs wh. are closed, uni-domain. When you search for what am I going to do..? your brain can go through an endless world of domains - movies,call a friend, watch TV, browse the net, meal, go for walk, play a sport, ask s.o. for novel ideas, spend time with my kid ... and on and on. The space thinking of rationality is superefficient but rigid and useless for AGI. The open world of the human, creative mind is highly inefficient by comparison but superflexible and the only way to do AGI. *From:* rob levy r.p.l...@gmail.com *Sent:* Monday, July 26, 2010 1:06 AM *To:* agi agi@v2.listbox.com *Subject:* Re: [agi] The Math Behind Creativity On Sun, Jul 25, 2010 at 5:05 PM, Mike Tintner tint...@blueyonder.co.ukwrote: I think it's v. useful - although I was really extending his idea. Correct me - but almost no matter what you guys do, (or anyone in AI does) , you think in terms of spaces, or frames. Spaces of options. Whether you're doing logic, maths, or programs, spaces in one form or other are fundamental. But you won't find anyone - or show me to the contrary - applying spaces to creative problems (or AGI problems). T I guess we may somehow be familiar with different and non-overlapping literature, but it seems to me that most or at least many approaches to modeling creativity involve a notion of spaces of some kind. I won't make a case to back that up but I will list a few examples: Koestler's bisociation is spacial, D. T. Campbell, the Fogels, Finke et al, and William Calvin's evolutionary notion of creativity involve a behavioral or conceptual fitness landscape, Gilles Fauconnier Mark Turner's theory of conceptual blending on mental space, etc. etc. The idea of the website you posted is very lacking in any kind of explanatory power in my opinion. To me any theory of creativity should be able to show how a system is able to generate novel and good results. Creativity is more than just outside what is known, created, or working. That is a description of novelty, and with no suggestions for the why or how of generating novelty. Creativity also requires the semantic potential to reflect on and direct the focusing in on the stream of playful novelty to that which is desired or considered good. I
Re: [agi] The Math Behind Creativity
Not sure how that is useful, or even how it relates to creativity if
considered as an informal description?
On Sun, Jul 25, 2010 at 10:15 AM, Mike Tintner tint...@blueyonder.co.ukwrote:
I came across this, thinking it was going to be an example of maths
fantasy, but actually it has a rather nice idea about the mathematics of
creativity.
The Math Behind Creativity http://www.alwayscreative.com/math/
By Chuck Scott http://www.alwayscreative.com/author/admin/ on June 15,
2010
The Science of Creativity is based on the following mathematical formula
for Creativity:
[image: C = {infty} - {pi}R^2]
In other words, Creativity is equal to infinity minus the area of a defined
circle of what’s working.
Note: [image: {pi}R^2] is the geometric formula for calculating the area
of a circle; where [image: pi] is 3.142 rounded to the nearest thousandth,
and R is a circle’s radius (the length from a circle’s center to edge).
**
Simply, it's saying - that for every problem, and ultimately that's not
just creative but rational problems, there's a definable space of options -
the spaces you guys work with in your programs - wh. may work, if the
problem is rational, but normally don't if it's creative. And beyond that
space is the undefined space of creativity, wh. encompasses the entire world
in an infinity of combinations. (Or all the fabulous multiverse[s] of Ben's
mind). Creative ideas - and that can be small everyday ideas as well as
large cultural ones - can come from anywhere in, and any combinations of,
the entire world (incl butterflies in Brazil and caterpillars in Katmandu -
QED I just drew that last phrase off the cuff from that vast world).
Creative thinking - and that incl. the thinking of all humans from children
on - is what in the world ? thinking - that can and does draw upon the
infinite resources of the world. What in the world is he on about? Where
in the world will I find s.o. who..? What in the world could be of help
here?
And that is another way of highlighting the absurdity of current approaches
to AGI - that would seek to encompass the entire world of creative
ideas/options in the infinitesimal spaces/options of programs.
*agi* | Archives https://www.listbox.com/member/archive/303/=now
https://www.listbox.com/member/archive/rss/303/ |
Modifyhttps://www.listbox.com/member/?;Your Subscription
http://www.listbox.com
---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c
Powered by Listbox: http://www.listbox.com
math_994_a9533b31457bd21311d15e42a60f9153.pngmath_994_d895701496b1057f4cbe3c7c38db0d30.pngmath_994.5_8edb2cf68079344a2edd739531259f6c.png
Re: [agi] The Math Behind Creativity
On Sun, Jul 25, 2010 at 5:05 PM, Mike Tintner tint...@blueyonder.co.ukwrote: I think it's v. useful - although I was really extending his idea. Correct me - but almost no matter what you guys do, (or anyone in AI does) , you think in terms of spaces, or frames. Spaces of options. Whether you're doing logic, maths, or programs, spaces in one form or other are fundamental. But you won't find anyone - or show me to the contrary - applying spaces to creative problems (or AGI problems). T I guess we may somehow be familiar with different and non-overlapping literature, but it seems to me that most or at least many approaches to modeling creativity involve a notion of spaces of some kind. I won't make a case to back that up but I will list a few examples: Koestler's bisociation is spacial, D. T. Campbell, the Fogels, Finke et al, and William Calvin's evolutionary notion of creativity involve a behavioral or conceptual fitness landscape, Gilles Fauconnier Mark Turner's theory of conceptual blending on mental space, etc. etc. The idea of the website you posted is very lacking in any kind of explanatory power in my opinion. To me any theory of creativity should be able to show how a system is able to generate novel and good results. Creativity is more than just outside what is known, created, or working. That is a description of novelty, and with no suggestions for the why or how of generating novelty. Creativity also requires the semantic potential to reflect on and direct the focusing in on the stream of playful novelty to that which is desired or considered good. I would disagree that creativity is outside the established/known. A better characterization would be that it resides on the complex boundary of the novel and the established, which is what make it interesting instead just a copy, or just total gobbledygook randomness. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Of definitions and tests of AGI
A child AGI should be expected to need help learning how to solve many problems, and even be told what the steps are. But at some point it needs to have developed general problem-solving skills. But I feel like this is all stating the obvious. On Tue, Jul 20, 2010 at 11:32 PM, Matt Mahoney matmaho...@yahoo.com wrote: Mike, I think we all agree that we should not have to tell an AGI the steps to solving problems. It should learn and figure it out, like the way that people figure it out. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Of definitions and tests of AGI
I completely agree with this characterization, I was just pointing out the importance already-existing generally intelligent entities in providing scaffolding for the system's learning and meta-learning processes. On Wed, Jul 21, 2010 at 12:25 PM, Mike Tintner tint...@blueyonder.co.ukwrote: Infants *start* with general learning skills - they have to extensively discover for themselves how to do most things - control head, reach out, turn over, sit up, crawl, walk - and also have to work out perceptually what the objects they see are, and what they do... and what sounds are, and how they form words, and how those words relate to objects - and how language works it is this capacity to keep discovering ways of doing things, that is a major motivation in their continually learning new activities - continually seeking novelty, and getting bored with too repetitive activities obviously an AGI needs some help.. but at the mo. all projects get *full* help/ *complete* instructions - IOW are merely dressed up versions of narrow AI no one AFAIK is dealing with the issue of how do you produce a true goalseeking agent who *can* discover things for itself? - an agent, that like humans and animals, can *find* its way to its goals generally, as well as to learning new activities, on its own initiative - rather than by following instructions. (The full instruction method only works in artificial, controlled environments and can't possibly work in the real, uncontrollable world - where future conditions are highly unpredictable, even by the sagest instructor). [Ben BTW strikes me as merely gesturing at all this]. There really can't be any serious argument about this - humans and animals clearly learn all their activities with v. limited and largely general rather than step-by-step instructions. You may want to argue there is an underlying general program that effectively specifies every step they must take (good luck) - but with respect to all their specialist.particular activities, - think having a conversation, sex, writing a post, an essay, fantasying, shopping, browsing the net, reading a newspaper - etc etc. - you got and get v. little step-by-step instruction about these and all your other activities So AGI's require a fundamentally and massively different paradigm of instruction to the program, comprehensive, step-by-step paradigm of narrow AI. [The rock wall/toybox tests BTW are AGI activities, where it is *impossible* to give full instructions, or produce a formula, whatever you may want to do]. *From:* rob levy r.p.l...@gmail.com *Sent:* Wednesday, July 21, 2010 3:56 PM *To:* agi agi@v2.listbox.com *Subject:* Re: [agi] Of definitions and tests of AGI A child AGI should be expected to need help learning how to solve many problems, and even be told what the steps are. But at some point it needs to have developed general problem-solving skills. But I feel like this is all stating the obvious. On Tue, Jul 20, 2010 at 11:32 PM, Matt Mahoney matmaho...@yahoo.comwrote: Mike, I think we all agree that we should not have to tell an AGI the steps to solving problems. It should learn and figure it out, like the way that people figure it out. *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Of definitions and tests of AGI
However, I see that there are no valid definitions of AGI that explain what AGI is generally , and why these tests are indeed AGI. Google - there are v. few defs. of AGI or Strong AI, period. I like Fogel's idea that intelligence is the ability to solve the problem of how to solve problems in new and changing environments. I don't think Fogel's method accomplishes this, but the goal he expresses seems to be the goal of AGI as I understand it. Rob --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Of definitions and tests of AGI
Well, solving ANY problem is a little too strong. This is AGI, not AGH (artificial godhead), though AGH could be an unintended consequence ;). So I would rephrase solving any problem as being able to come up with reasonable approaches and strategies to any problem (just as humans are able to do). On Mon, Jul 19, 2010 at 11:32 AM, Mike Tintner tint...@blueyonder.co.ukwrote: Whaddya mean by solve the problem of how to solve problems? Develop a universal approach to solving any problem? Or find a method of solving a class of problems? Or what? *From:* rob levy r.p.l...@gmail.com *Sent:* Monday, July 19, 2010 1:26 PM *To:* agi agi@v2.listbox.com *Subject:* Re: [agi] Of definitions and tests of AGI However, I see that there are no valid definitions of AGI that explain what AGI is generally , and why these tests are indeed AGI. Google - there are v. few defs. of AGI or Strong AI, period. I like Fogel's idea that intelligence is the ability to solve the problem of how to solve problems in new and changing environments. I don't think Fogel's method accomplishes this, but the goal he expresses seems to be the goal of AGI as I understand it. Rob *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Of definitions and tests of AGI
Fogel originally used the phrase to argue that evolutionary computation makes sense as a cognitive architecture for a general-purpose AI problem solver. On Mon, Jul 19, 2010 at 11:45 AM, rob levy r.p.l...@gmail.com wrote: Well, solving ANY problem is a little too strong. This is AGI, not AGH (artificial godhead), though AGH could be an unintended consequence ;). So I would rephrase solving any problem as being able to come up with reasonable approaches and strategies to any problem (just as humans are able to do). On Mon, Jul 19, 2010 at 11:32 AM, Mike Tintner tint...@blueyonder.co.ukwrote: Whaddya mean by solve the problem of how to solve problems? Develop a universal approach to solving any problem? Or find a method of solving a class of problems? Or what? *From:* rob levy r.p.l...@gmail.com *Sent:* Monday, July 19, 2010 1:26 PM *To:* agi agi@v2.listbox.com *Subject:* Re: [agi] Of definitions and tests of AGI However, I see that there are no valid definitions of AGI that explain what AGI is generally , and why these tests are indeed AGI. Google - there are v. few defs. of AGI or Strong AI, period. I like Fogel's idea that intelligence is the ability to solve the problem of how to solve problems in new and changing environments. I don't think Fogel's method accomplishes this, but the goal he expresses seems to be the goal of AGI as I understand it. Rob *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Of definitions and tests of AGI
And are you happy with: AGI is about devising *one-off* methods of problemsolving (that only apply to the individual problem, and cannot be re-used - at least not in their totality) Yes exactly, isn't that what people do? Also, I think that being able to recognize where past solutions can be generalized and where past solutions can be varied and reused is a detail of how intelligence works that is likely to be universal. vs narrow AI is about applying pre-existing *general* methods of problemsolving (applicable to whole classes of problems)? *From:* rob levy r.p.l...@gmail.com *Sent:* Monday, July 19, 2010 4:45 PM *To:* agi agi@v2.listbox.com *Subject:* Re: [agi] Of definitions and tests of AGI Well, solving ANY problem is a little too strong. This is AGI, not AGH (artificial godhead), though AGH could be an unintended consequence ;). So I would rephrase solving any problem as being able to come up with reasonable approaches and strategies to any problem (just as humans are able to do). On Mon, Jul 19, 2010 at 11:32 AM, Mike Tintner tint...@blueyonder.co.ukwrote: Whaddya mean by solve the problem of how to solve problems? Develop a universal approach to solving any problem? Or find a method of solving a class of problems? Or what? *From:* rob levy r.p.l...@gmail.com *Sent:* Monday, July 19, 2010 1:26 PM *To:* agi agi@v2.listbox.com *Subject:* Re: [agi] Of definitions and tests of AGI However, I see that there are no valid definitions of AGI that explain what AGI is generally , and why these tests are indeed AGI. Google - there are v. few defs. of AGI or Strong AI, period. I like Fogel's idea that intelligence is the ability to solve the problem of how to solve problems in new and changing environments. I don't think Fogel's method accomplishes this, but the goal he expresses seems to be the goal of AGI as I understand it. Rob *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield steve.richfi...@gmail.comwrote: Rob, I just LOVE opaque postings, because they identify people who see things differently than I do. I'm not sure what you are saying here, so I'll make some random responses to exhibit my ignorance and elicit more explanation. I think based on what you wrote, you understood (mostly) what I was trying to get across. So I'm glad it was at least quasi-intelligible. :) It sounds like this is a finer measure than the dimensionality that I was referencing. However, I don't see how to reduce anything as quantized as dimensionality into finer measures. Can you say some more about this? I was just referencing Gardenfors' research program of conceptual spaces (I was intentionally vague about committing to this fully though because I don't necessarily think this is the whole answer). Page 2 of this article summarizes it pretty succinctly: http:// goog_1627994790 www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf However, different people's brains, even the brains of identical twins, have DIFFERENT mappings. This would seem to mandate experience-formed topology. Yes definitely. Since these conceptual spaces that structure sensorimotor expectation/prediction (including in higher order embodied exploration of concepts I think) are multidimensional spaces, it seems likely that some kind of neural computation over these spaces must occur, I agree. though I wonder what it actually would be in terms of neurons, (and if that matters). I don't see any route to the answer except via neurons. I agree this is true of natural intelligence, though maybe in modeling, the neural level can be shortcut to the topo map level without recourse to neural computation (use some more straightforward computation like matrix algebra instead). Rob --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
Sorry, the link I included was invalid, this is what I meant: http://www.geog.ucsb.edu/~raubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdf On Tue, Jun 29, 2010 at 2:28 AM, rob levy r.p.l...@gmail.com wrote: On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield steve.richfi...@gmail.com wrote: Rob, I just LOVE opaque postings, because they identify people who see things differently than I do. I'm not sure what you are saying here, so I'll make some random responses to exhibit my ignorance and elicit more explanation. I think based on what you wrote, you understood (mostly) what I was trying to get across. So I'm glad it was at least quasi-intelligible. :) It sounds like this is a finer measure than the dimensionality that I was referencing. However, I don't see how to reduce anything as quantized as dimensionality into finer measures. Can you say some more about this? I was just referencing Gardenfors' research program of conceptual spaces (I was intentionally vague about committing to this fully though because I don't necessarily think this is the whole answer). Page 2 of this article summarizes it pretty succinctly: http:// http://goog_1627994790 www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf However, different people's brains, even the brains of identical twins, have DIFFERENT mappings. This would seem to mandate experience-formed topology. Yes definitely. Since these conceptual spaces that structure sensorimotor expectation/prediction (including in higher order embodied exploration of concepts I think) are multidimensional spaces, it seems likely that some kind of neural computation over these spaces must occur, I agree. though I wonder what it actually would be in terms of neurons, (and if that matters). I don't see any route to the answer except via neurons. I agree this is true of natural intelligence, though maybe in modeling, the neural level can be shortcut to the topo map level without recourse to neural computation (use some more straightforward computation like matrix algebra instead). Rob --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
In order to have perceptual/conceptual similarity, it might make sense that there is distance metric over conceptual spaces mapping (ala Gardenfors or something like this theory) underlying how the experience of reasoning through is carried out. This has the advantage of being motivated by neuroscience findings (which are seldom convincing, but in this case it is basic solid neuroscience research) that there are topographic maps in the brain. Since these conceptual spaces that structure sensorimotor expectation/prediction (including in higher order embodied exploration of concepts I think) are multidimensional spaces, it seems likely that some kind of neural computation over these spaces must occur, though I wonder what it actually would be in terms of neurons, (and if that matters). But that is different from what would be considered quantitative reasoning, because from the phenomenological perspective the person is training sensorimotor expectations by perceiving and doing. And creative conceptual shifts (or recognition of novel perceptual categories) can also be explained by this feedback between trained topographic maps and embodied interaction with environment (experienced at the ecological level as sensorimotor expectations (driven by neural maps). Sensorimotor expectation is the basis of dynamics of perception and coceptualization). On Sun, Jun 27, 2010 at 7:24 PM, Ben Goertzel b...@goertzel.org wrote: On Sun, Jun 27, 2010 at 7:09 PM, Steve Richfield steve.richfi...@gmail.com wrote: Ben, On Sun, Jun 27, 2010 at 3:47 PM, Ben Goertzel b...@goertzel.org wrote: know what dimensional analysis is, but it would be great if you could give an example of how it's useful for everyday commonsense reasoning such as, say, a service robot might need to do to figure out how to clean a house... How much detergent will it need to clean the floors? Hmmm, we need to know ounces. We have the length and width of the floor, and the bottle says to use 1 oz/M^2. How could we manipulate two M-dimensioned quantities and 1 oz/M^2 dimensioned quantity to get oz? The only way would seem to be to multiply all three numbers together to get ounces. This WITHOUT understanding things like surface area, utilization, etc. I think that the El Salvadorean maids who come to clean my house occasionally, solve this problem without any dimensional analysis or any quantitative reasoning at all... Probably they solve it based on nearest-neighbor matching against past experiences cleaning other dirty floors with water in similarly sized and shaped buckets... -- ben g *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Questions for an AGI
I definitely agree, however we lack a convincing model or plan of any sort for the construction of systems demonstrating subjectivity, and it seems plausible that subjectivity is functionally necessary for general intelligence. Therefore it is reasonable to consider symbiosis as both a safe design and potentially the only possible design (at least at first), depending on how creative and resourceful we get in cog sci/ AGI in coming years. On Sun, Jun 27, 2010 at 1:13 PM, Matt Mahoney matmaho...@yahoo.com wrote: This is wishful thinking. Wishful thinking is dangerous. How about instead of hoping that AGI won't destroy the world, you study the problem and come up with a safe design. -- Matt Mahoney, matmaho...@yahoo.com -- *From:* rob levy r.p.l...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Sat, June 26, 2010 1:14:22 PM *Subject:* Re: [agi] Questions for an AGI why should AGIs give a damn about us? I like to think that they will give a damn because humans have a unique way of experiencing reality and there is no reason to not take advantage of that precious opportunity to create astonishment or bliss. If anything is important in the universe, its insuring positive experiences for all areas in which it is conscious, I think it will realize that. And with the resources available in the solar system alone, I don't think we will be much of a burden. I like that idea. Another reason might be that we won't crack the problem of autonomous general intelligence, but the singularity will proceed regardless as a symbiotic relationship between life and AI. That would be beneficial to us as a form of intelligence expansion, and beneficial to the artificial entity a way of being alive and having an experience of the world. *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Questions for an AGI
why should AGIs give a damn about us? I like to think that they will give a damn because humans have a unique way of experiencing reality and there is no reason to not take advantage of that precious opportunity to create astonishment or bliss. If anything is important in the universe, its insuring positive experiences for all areas in which it is conscious, I think it will realize that. And with the resources available in the solar system alone, I don't think we will be much of a burden. I like that idea. Another reason might be that we won't crack the problem of autonomous general intelligence, but the singularity will proceed regardless as a symbiotic relationship between life and AI. That would be beneficial to us as a form of intelligence expansion, and beneficial to the artificial entity a way of being alive and having an experience of the world. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] The problem with AGI per Sloman
But there is some other kind of problem. We should have figured it out by now. I believe that there must be some fundamental computational problem that is standing as the major obstacle to contemporary AGI. Without solving that problem we are going to have to wade through years of incremental advances. I believe that the most likely basis of the problem is efficient logical satisfiability. It makes the most senese given the nature of the computer and the nature of the best theories of mind. I think there must be a computational or physical/computational problem we have yet to clearly identify that goes along with an objection certain philosophers like Chalmers have made about neural correlates, roughly: why should one level of analysis or type of structure (eg neurons, brain regions, dynamically synchronized ensembles of neurons, or even the organism-environment system), have this magic property of consciousness? Since to me at least it seem obvious that the ecological level is the relevant level of analysis at which to find the meaning relevant to biological organisms, my sense is that we can reduce the above problem to a question about meaning/significance, that is: what is it about a system that makes it unified/integrated such that its relationship to other things constitutes a landscape of relevant meaning to the system as a whole. I think that if that an explanation of meaning-to-a-system is either the same as an explanation of first-hand subjectivity, or is closely tied to it, though if subjectivity turns out to be part of a physical problem and not a purely computational one, then we probably won't solve the above-posed problem without such a physical explanation being clarified (not necessarily explained though, just as we don't know what electricity really is for example). All computer software and situated robots that have ever been made are composed of actions or expressions that are meaningful to people, but software or robots have never been created that can refer to their own actions in a way that demonstrates skillful knowledge indicating that they are organized in a truly semantic way, as opposed to a merely programmatic way. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
[agi] Fwd: AGI question
Hi I'm new to this list, but I've been thinking about consciousness, cognition and AI for about half of my life (I'm 32 years old). As is probably the case for many of us here, my interests began with direct recognition of the depth and wonder of varieties of phenomenological experiences-- and attempting to comprehend how these constellations of significance fit in with a larger picture of what we can reliably know about the natural world. I am secondarily motivated by the fact that (considerations of morality or amorality aside) AGI is inevitable, though it is far from being a forgone conclusion that powerful general thinking machines will have a first-hand subjective relationship to a world, as living creatures do-- and therefore it is vital that we do as well as possible in understanding what makes systems conscious. A zombie machine intelligence singularity is something I would refer to rather as a holocaust, even if no one were directly killed, assuming these entities could ultimately prevail over the previous forms of life on our planet. I'm sure I'm not the only one on this list who sees a behavioral/ecological level of analysis as the most likely correct level at which to study perception and cognition, and perception as being a kind of active relationship between an organism and an environment. Having thoroughly convinced my self of a non-dualist, embodied, externalist perspective on cognition, I turn to the nature of life itself (and possibly even physics but maybe that level will not be necessary) to make sense of the nature of subjectivity. I like Bohm's or Bateson's panpsychism about systems as wholes, and significance as informational distinctions (which it would be natural to understand as being the basis of subjective experience), but this is descriptive rather than explanatory. I am not a biologist, but I am increasingly interested in finding answers to what it is about living organisms that gives them a unity such that something is something to the system as a whole. The line of investigation that theoretical biologists like Robert Rosen and other NLDS/chaos people have pursued is interesting, but I am unfamiliar with related work that might have made more progress on the system-level properties that give life its characteristic unity and system-level responsiveness. To me, this seems the most likely candidate for a paradigm shift that would produce AGI. In contrast I'm not particularly convinced that modeling a brain is a good way to get AGI, although I'd guess we could learn a few more things about the coordination of complex behavior if we could really understand them. Another way to put this is that obviously evolutionary computation would be more than just boring hill-climbing if we knew what an organism even IS (perhaps in a more precise computational sense). If we can know what an organism is then it should be (maybe) trivial to model concepts, consciousness, and high level semantics to the umpteenth degree, or at least this would be a major hurtle I think. Even assuming a solution to the problem posed above, there is still plenty of room for other minds skepticism in non-living entities implemented on questionably foreign mediums but there would be a lot more reason to sleep well that the science/technology is leading in a direction in which questions about subjectivity could be meaningfully investigated. Rob --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] An alternative plan to discover self-organization theory
(I'm a little late in this conversation. I tried to send this message the other day but I had my list membership configured wrong. -Rob) -- Forwarded message -- From: rob levy r.p.l...@gmail.com Date: Sun, Jun 20, 2010 at 5:48 PM Subject: Re: [agi] An alternative plan to discover self-organization theory To: agi@v2.listbox.com On a related note, what is everyone's opinion on why evolutionary algorithms are such a miserable failure as creative machines, despite their successes in narrow optimization problems? I don't want to conflate the possibly separable problems of biological development and evolution, though they are interrelated. There are various approaches to evolutionary theory such as Lima de Faria's evolution without selection ideas and Reid's evolution by natural experiment that suggest natural selection is not all it's cracked up to be, and that the step of generating, (mutating, combining, ) is where the more interesting stuff happens. Most of the alternatives to Neodarwinian Synthesis I have seen are based in dynamic models of emergence in complex systems. The upshot is, you don't get creativity for free, you actually still need to solve a problem that is as hard as AGI in order to get creativity for free. So, you would need to solve the AGI-hard problem of evolution and development of life, in order to then solve AGI itself (reminds me of the old SNL sketch: first, get a million dollars...). Also, my hunch is that there is quite a bit of overlap between the solutions to the two problems. Rob Disclaimer: I'm discussing things above that I'm not and don't claim to be an expert in, but from what I have seen so far on this list, that should be alright. AGI is by its nature very multidisciplinary which necessitates often being breadth-first, and therefore shallow in some areas. On Sun, Jun 20, 2010 at 2:06 AM, Steve Richfield steve.richfi...@gmail.comwrote: No, I haven't been smokin' any wacky tobacy. Instead, I was having a long talk with my son Eddie, about self-organization theory. This is *his*proposal: He suggested that I construct a simple NN that couldn't work without self organizing, and make dozens/hundreds of different neuron and synapse operational characteristics selectable ala genetic programming, put it on the fastest computer I could get my hands on, turn it loose trying arbitrary combinations of characteristics, and see what the winning combination turns out to be. Then, armed with that knowledge, refine the genetic characteristics and do it again, and iterate until it *efficiently* self organizes. This might go on for months, but self-organization theory might just emerge from such an effort. I had a bunch of objections to his approach, e.g. Q. What if it needs something REALLY strange to work? A. Who better than you to come up with a long list of really strange functionality? Q. There are at least hundreds of bits in the genome. A. Try combinations in pseudo-random order, with each bit getting asserted in ~half of the tests. If/when you stumble onto a combination that sort of works, switch to varying the bits one-at-a-time, and iterate in this way until the best combination is found. Q. Where are we if this just burns electricity for a few months and finds nothing? A. Print out the best combination, break out the wacky tobacy, and come up with even better/crazier parameters to test. I have never written a line of genetic programming, but I know that others here have. Perhaps you could bring some rationality to this discussion? What would be a simple NN that needs self-organization? Maybe a small pot of neurons that could only work if they were organized into layers, e.g. a simple 64-neuron system that would work as a 4x4x4-layer visual recognition system, given the input that I fed it? Any thoughts on how to score partial successes? Has anyone tried anything like this in the past? Is anyone here crazy enough to want to help with such an effort? This Monte Carlo approach might just be simple enough to work, and simple enough that it just HAS to be tried. All thoughts, stones, and rotten fruit will be gratefully appreciated. Thanks in advance. Steve *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] An alternative plan to discover self-organization theory
Matt, I'm not sure I buy that argument for the simple reason that we have massive cheap processing now and pretty good knowledge of the initial conditions of life on our planet (if we are going literal here and not EC in the abstract), but it's definitely a possible answer. Perhaps not enough people have attempted to run evolutionary computation experiments at these massive scales either. Rob On Mon, Jun 21, 2010 at 12:59 PM, Matt Mahoney matmaho...@yahoo.com wrote: rob levy wrote: On a related note, what is everyone's opinion on why evolutionary algorithms are such a miserable failure as creative machines, despite their successes in narrow optimization problems? Lack of computing power. How much computation would you need to simulate the 3 billion years of evolution that created human intelligence? -- Matt Mahoney, matmaho...@yahoo.com -- *From:* rob levy r.p.l...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Mon, June 21, 2010 11:56:53 AM *Subject:* Re: [agi] An alternative plan to discover self-organization theory (I'm a little late in this conversation. I tried to send this message the other day but I had my list membership configured wrong. -Rob) -- Forwarded message -- From: rob levy r.p.l...@gmail.com Date: Sun, Jun 20, 2010 at 5:48 PM Subject: Re: [agi] An alternative plan to discover self-organization theory To: agi@v2.listbox.com On a related note, what is everyone's opinion on why evolutionary algorithms are such a miserable failure as creative machines, despite their successes in narrow optimization problems? I don't want to conflate the possibly separable problems of biological development and evolution, though they are interrelated. There are various approaches to evolutionary theory such as Lima de Faria's evolution without selection ideas and Reid's evolution by natural experiment that suggest natural selection is not all it's cracked up to be, and that the step of generating, (mutating, combining, ) is where the more interesting stuff happens. Most of the alternatives to Neodarwinian Synthesis I have seen are based in dynamic models of emergence in complex systems. The upshot is, you don't get creativity for free, you actually still need to solve a problem that is as hard as AGI in order to get creativity for free. So, you would need to solve the AGI-hard problem of evolution and development of life, in order to then solve AGI itself (reminds me of the old SNL sketch: first, get a million dollars...). Also, my hunch is that there is quite a bit of overlap between the solutions to the two problems. Rob Disclaimer: I'm discussing things above that I'm not and don't claim to be an expert in, but from what I have seen so far on this list, that should be alright. AGI is by its nature very multidisciplinary which necessitates often being breadth-first, and therefore shallow in some areas. On Sun, Jun 20, 2010 at 2:06 AM, Steve Richfield steve.richfi...@gmail.com wrote: No, I haven't been smokin' any wacky tobacy. Instead, I was having a long talk with my son Eddie, about self-organization theory. This is *his*proposal: He suggested that I construct a simple NN that couldn't work without self organizing, and make dozens/hundreds of different neuron and synapse operational characteristics selectable ala genetic programming, put it on the fastest computer I could get my hands on, turn it loose trying arbitrary combinations of characteristics, and see what the winning combination turns out to be. Then, armed with that knowledge, refine the genetic characteristics and do it again, and iterate until it *efficiently* self organizes. This might go on for months, but self-organization theory might just emerge from such an effort. I had a bunch of objections to his approach, e.g. Q. What if it needs something REALLY strange to work? A. Who better than you to come up with a long list of really strange functionality? Q. There are at least hundreds of bits in the genome. A. Try combinations in pseudo-random order, with each bit getting asserted in ~half of the tests. If/when you stumble onto a combination that sort of works, switch to varying the bits one-at-a-time, and iterate in this way until the best combination is found. Q. Where are we if this just burns electricity for a few months and finds nothing? A. Print out the best combination, break out the wacky tobacy, and come up with even better/crazier parameters to test. I have never written a line of genetic programming, but I know that others here have. Perhaps you could bring some rationality to this discussion? What would be a simple NN that needs self-organization? Maybe a small pot of neurons that could only work if they were organized into layers, e.g. a simple 64-neuron system that would work as a 4x4x4-layer visual recognition system, given the input that I fed it? Any thoughts
