Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
On Tuesday 22 April 2008 01:22:14 pm, Richard Loosemore wrote: The solar system, for example, is not complex: the planets move in wonderfully predictable orbits. http://space.newscientist.com/article/dn13757-solar-system-could-go-haywire-before-the-sun-dies.html?feedId=online-news_rss20 How will life on Earth end? The answer, of course, is unknown, but two new studies suggest a collision with Mercury or Mars could doom life long before the Sun swells into a red giant and bakes the planet to a crisp in about 5 billion years. The studies suggest that the solar system's planets will continue to orbit the Sun stably for at least 40 million years. But after that, they show there is a small but not insignificant chance that things could go terribly awry. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
J Storrs Hall, PhD wrote: On Tuesday 22 April 2008 01:22:14 pm, Richard Loosemore wrote: The solar system, for example, is not complex: the planets move in wonderfully predictable orbits. http://space.newscientist.com/article/dn13757-solar-system-could-go-haywire-before-the-sun-dies.html?feedId=online-news_rss20 How will life on Earth end? The answer, of course, is unknown, but two new studies suggest a collision with Mercury or Mars could doom life long before the Sun swells into a red giant and bakes the planet to a crisp in about 5 billion years. The studies suggest that the solar system's planets will continue to orbit the Sun stably for at least 40 million years. But after that, they show there is a small but not insignificant chance that things could go terribly awry. I am confused about the intended message. If you take the above quote from me in its original context, your illustration perfectly supports what I said, but with that one paragraph taken out of context it looks as if you are trying to contradict it. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Vladimir Nesov wrote: On Tue, Apr 22, 2008 at 5:59 AM, Richard Loosemore [EMAIL PROTECTED] wrote: H I detect a parody..? That is not what I intended to say. No, as horrible as it may sound, this is how I see the problem that you are trying to address. If you can pinpoint some specific errors in my description, without reiterating the whole description once again, that would probably be helpful. On a second reading, the description of my propsoed paradigm is not that inaccurate, it just emphasizes some things and de-emphasizes others, thereby making the whole thing look weird. I'll elaborate later. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
J Andrew Rogers writes: Most arguments and disagreements over complexity are fundamentally about the strict definition of the term, or the complete absence thereof. The arguments tend to evaporate if everyone is forced to unambiguously define such terms, but where is the fun in that. I agree with this to a point at least. My attempt to rephrase Richard's argument falters because I have not yet understood his use of the term 'complexity'. I'd prefer a rigorous definition but will settle for a better general understanding of what he means. Despite his several attempts to describe his meaning I have not been able yet to successfully grasp exactly what counts as complex and what does not, and for things inbetween, how to judge the degree of complexity. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
J. Andrew Rogers wrote: On Apr 21, 2008, at 6:53 PM, Richard Loosemore wrote: I have been trying to understand the relationship between theoretical models of thought (both natural and artificial) since at least 1980, and one thing I have noticed is that people devise theoretical structures that are based on the assumption that intelligence is not complex but then they use these structures in such a way that the resulting system is almost always complex. This is easily explained by the obvious fact that the definition of complex varies considerably across relevant populations, exacerbated in the case of AGI -- where it is arguably a germane element -- because many (most?) researchers are using complex in a colloquial (read: meaningless) sense rather than one of its more rigorously defined senses, of which there are a few interesting ones. Most arguments and disagreements over complexity are fundamentally about the strict definition of the term, or the complete absence thereof. The arguments tend to evaporate if everyone is forced to unambiguously define such terms, but where is the fun in that. It is correct to say that there is disagreement about what complexity means, but that is why I went to so much trouble to give a precise definition of it, and the use that precise definition consistently. Last thing I want to do is to engage in fruitless debates with other complex systems people about what exactly it means. But then, going back to your first comment above, no, you cannot use other people's confusion about the meaning of the term complexity to explain why models of thinking start off being designed as if they were not complex, but then get used in ways that makes the overall system complex. That observation is pretty much independent of the definition you choose, and any way it happens within my definition, so it still needs to be explained. The explanation, of course, is that intelligent systems really are (partially) complex, but everyone is trying to kid themselves that they are not, to make their research easier. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Richard: I get tripped up on your definition of complexity: A system contains a certain amount of complexity in it if it has some regularities in its overall behavior that are governed by mechanisms that are so tangled that, for all practical purposes, we must assume that we will never be able to find a closed-form explanation of how the global arises from the local.on figuring out what counts as a regularity in overall behavior. Consider a craps table. The trajectories of the dice would seem to have global regularities (for which craps players and normal people have words and phrases, like bouncing off the back, flying off the table, or whatever). Our ability to create concepts around this activity would seem to imply the existence of global regularities (finding them is what we do when we make concepts). Yet the behavior of those regularities is not just physical law but the specific configuration of the felt, the chips, the wind, and so forth, and all that data makes a closed-form explanation impractical. Yet, I don't get the sense that this is what you mean by a complex system. If it is, your contention that they are rare is certainly not correct, since many such examples can easily be found. This aspect of complexity iillustrates the butterfly effect often used in discussions of complexity. I'm not trying to be difficult; it's crucial for me to understand what you mean (versus my interpretation of what others have meant or my own internal definitions) if I am to follow your argument. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
How confident are you that this only-complex-AI limitation applies in reality? How much would you bet on it? I'm not convinced, and I think that if you are convinced too much, you made wrong conclusions from your data, unless you communicated too little of what formed your intuition. I am completely sure that it applies (although your phrasing makes me wonder if you have interpreted my exact worry accurately... I will have to come back to that). I am also sure that it applies but don't believe that it is a huge problem unless you ignore it. Remember, gravity with three bodies is a complex problem -- but it is relatively easy to characterize and solve to reasonable limits (just don't try to make plans too far in the future without making periodic readings to ensure that reality still matches your model). --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Derek Zahn wrote: Richard: I get tripped up on your definition of complexity: A system contains a certain amount of complexity in it if it has some regularities in its overall behavior that are governed by mechanisms that are so tangled that, for all practical purposes, we must assume that we will never be able to find a closed-form explanation of how the global arises from the local. on figuring out what counts as a regularity in overall behavior. Consider a craps table. The trajectories of the dice would seem to have global regularities (for which craps players and normal people have words and phrases, like bouncing off the back, flying off the table, or whatever). Our ability to create concepts around this activity would seem to imply the existence of global regularities (finding them is what we do when we make concepts). Yet the behavior of those regularities is not just physical law but the specific configuration of the felt, the chips, the wind, and so forth, and all that data makes a closed-form explanation impractical. Yet, I don't get the sense that this is what you mean by a complex system. If it is, your contention that they are rare is certainly not correct, since many such examples can easily be found. This aspect of complexity iillustrates the butterfly effect often used in discussions of complexity. I'm not trying to be difficult; it's crucial for me to understand what you mean (versus my interpretation of what others have meant or my own internal definitions) if I am to follow your argument. Okay, I will respond to your questions on two fronts (!) - I just posted a reply to your comment on the blog, too. In the above, you mention butterfly effects. This is not a mainstream example of complexity, it is chaos, which is not exactly the same thing. More generally, you cannot say that a system is complex by itself, it is a system with respect to a particular regularity in its behavior. The solar system, for example, is not complex: the planets move in wonderfully predictable orbits. BUT... actually the solar system *is* complex, because Pluto's behavior is unstable, and every once in a while it comes in and messes with everyone else. So if the solar system remains utterly predictable for a hundred million years, and then Pluto goes AWOL for a few years, what is it? It is partially complex, with just a tiny degree of complexity superimposed on otherwise non-complex behavior. We cannot give a black and white answer to the question is it complex?. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
One more bit of ranting on this topic, to try to clarify the sort of thing I'm trying to understand. Some dude is telling my AGI program: There's a piece called a 'knight'. It moves by going two squares in one direction and then one in a perpendicular direction. And here's something neat: Except for one other obscure case I'll tell you about later, it's the only piece that moves by jumping through the air instead of moving a square at a time on its journey. When I try to think about how an intelligence works, I wonder about specific cases like these (and thanks to William Pearson for inventing this one) -- the genesis of the knight concept from this specific purely verbal exchange. How could this work? What is it about the specific word sequences and/or the conversational context that creates this new thing -- the Knight? It would have to be a hugely complicated language processing system... so where did that language processing system come from? Did somebody hardcode a model of language and conversation and explicitly insert generate concept here actions? That sounds like a big job. If it was learned (much better), how was it learned? What is the internal representation of the language processing model that leads to this particular concept formation, and how was it generated? If I can see something specific like that in a system (say Novamente) I can start to really understand the theory of mind it expresses. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
On Mon, Apr 21, 2008 at 8:32 PM, Derek Zahn [EMAIL PROTECTED] wrote: One more bit of ranting on this topic, to try to clarify the sort of thing I'm trying to understand. Some dude is telling my AGI program: There's a piece called a 'knight'. It moves by going two squares in one direction and then one in a perpendicular direction. And here's something neat: Except for one other obscure case I'll tell you about later, it's the only piece that moves by jumping through the air instead of moving a square at a time on its journey. When I try to think about how an intelligence works, I wonder about specific cases like these (and thanks to William Pearson for inventing this one) -- the genesis of the knight concept from this specific purely verbal exchange. How could this work? What is it about the specific word sequences and/or the conversational context that creates this new thing -- the Knight? It would have to be a hugely complicated language processing system... so where did that language processing system come from? Did somebody hardcode a model of language and conversation and explicitly insert generate concept here actions? That sounds like a big job. If it was learned (much better), how was it learned? What is the internal representation of the language processing model that leads to this particular concept formation, and how was it generated? If I can see something specific like that in a system (say Novamente) I can start to really understand the theory of mind it expresses. Generating concepts out of thin air is no big deal, if only a resource-hungry process. You can create a dozen for each episode, for example. A more challenging task is to arrange so that all these concepts actually lead to correct decisions, influence other concepts in a right way without destroying them. New concepts need to be friendly to inference system before modification. -- Vladimir Nesov [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Stephen Reed writes: Hey Texai, let's program [Texai] I don't know how to program, can you teach me by yourself? Sure, first thing is that a program consists of statements that each does something [Texai] I assume by program you mean a sequence of instructions that a computer can interpret and execute, and that by statement you mean a line of code written as part of a computer program Right. One type of instruction is the assignment statement. [Texai] OK, how is it interpreted? It has two parts, one part identifies a variable that receives a copy of, or a reference to, an evaluated expression described by the other part of the instruction [Texai] I assume by variable you mean a symbol (like x or y) that is used in mathematical or logical expressions to represent a variable quantity. What's an evaluated expression? And under what circumstances does the situation in which the variable receives a copy of the evaluated expression occur, as contrasted with the situation in which the variable receives a reference to the evaluated expression? Wow, if that turns out to be an actual transcript sent back through a time machine (I mean, if it works like you think), that's amazingly impressive. Every part of it, from knowing to ask you to teach it to do something, to connecting 'program' used as a verb to 'program' used as a noun, to knowing all about sequences of instructions, what computers are and how they work, what a line of code even means, and so on. I assume these things were taught to it through previous teaching sessions, and I'm really eager to see that in action. Of particular interest to me here is the conceptual leap from equality in a mathematical expression (which I guess the system already knows about) to the very different idea of assignment in a normal programming language. The origin of a variable as a named thing that can hold a value was an interesting concept to communicate to undergraduate business majors back in the day when I taught introductory programming... you could just see them get it after trying analogies with mailboxes and diagrams of computer memory and whatnot. It had never occurred to some of them to put a number in a box for later use before but I clearly remember the instant of concept formation occurring in their fresh young minds :) Now the aha moment behind learning the concept of recursion is even more interesting... --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Hi Derek,
Thanks for encouragement. Take a look at WordNet online here and you will see
why an initial Texai goal is to fully understand the word sense definitions
(e.g. program).
It's been so long that I cannot recall the year, or even the season, but I do
recall to this day exactly where I was when the recursion aha moment occurred
for me. From the computer center, I was walking alone, traversing an empty
quad in the twilight, back to my dorm at Stony Brook. Of course its a typical
youngster's attitude to believe that simple elegant principles can solve great
challenges, but still it was thrilling - thanks for provoking its recollection.
Cheers,
-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: Derek Zahn [EMAIL PROTECTED]
To: agi@v2.listbox.com
Sent: Monday, April 21, 2008 12:43:37 PM
Subject: RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent
input and responses
.hmmessage P { margin:0px;padding:0px;} body.hmmessage {
FONT-SIZE:10pt;FONT-FAMILY:Tahoma;} Stephen Reed writes:
Hey Texai, let's program [Texai] I don't know how to program, can you teach
me by yourself? Sure, first thing is that a program consists of statements that
each does something [Texai] I assume by program you mean a sequence of
instructions that a computer can interpret and execute, and that by statement
you mean a line of code written as part of a computer program Right. One type
of instruction is the assignment statement.
[Texai] OK, how is it interpreted? It has two parts, one part identifies a
variable that receives a copy of, or a reference to, an evaluated expression
described by the other part of the instruction [Texai] I assume by variable you
mean a symbol (like x or y) that is used in mathematical or logical expressions
to represent a variable quantity. What's an evaluated expression? And under
what circumstances does the situation in which the variable receives a copy of
the evaluated expression occur, as contrasted with the situation in which the
variable receives a reference to the evaluated expression? Wow, if that turns
out to be an actual transcript sent back through a time machine (I mean, if it
works like you think), that's amazingly impressive. Every part of it, from
knowing to ask you to teach it to do something, to connecting 'program' used as
a verb to 'program' used as a noun, to knowing all about sequences of
instructions, what computers are and
how they work, what a line of code even means, and so on. I assume these
things were taught to it through previous teaching sessions, and I'm really
eager to see that in action. Of particular interest to me here is the
conceptual leap from equality in a mathematical expression (which I guess the
system already knows about) to the very different idea of assignment in a
normal programming language. The origin of a variable as a named thing that
can hold a value was an interesting concept to communicate to undergraduate
business majors back in the day when I taught introductory programming... you
could just see them get it after trying analogies with mailboxes and diagrams
of computer memory and whatnot. It had never occurred to some of them to put a
number in a box for later use before but I clearly remember the instant of
concept formation occurring in their fresh young minds :)
Now the aha moment behind learning the concept of recursion is even more
interesting...
agi | Archives | Modify Your Subscription
Be a better friend, newshound, and
know-it-all with Yahoo! Mobile. Try it now.
http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ
---
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4
Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
roughly Novamente-like machines. In 8 to 20 years I would be surprised if we do not see machines that are at least at human levels in virtually all mental skills it is desirable for machines to have. -Original Message- From: Derek Zahn [mailto:[EMAIL PROTECTED] Sent: Monday, April 21, 2008 12:33 PM To: agi@v2.listbox.com Subject: RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses One more bit of ranting on this topic, to try to clarify the sort of thing I'm trying to understand. Some dude is telling my AGI program: There's a piece called a 'knight'. It moves by going two squares in one direction and then one in a perpendicular direction. And here's something neat: Except for one other obscure case I'll tell you about later, it's the only piece that moves by jumping through the air instead of moving a square at a time on its journey. When I try to think about how an intelligence works, I wonder about specific cases like these (and thanks to William Pearson for inventing this one) -- the genesis of the knight concept from this specific purely verbal exchange. How could this work? What is it about the specific word sequences and/or the conversational context that creates this new thing -- the Knight? It would have to be a hugely complicated language processing system... so where did that language processing system come from? Did somebody hardcode a model of language and conversation and explicitly insert generate concept here actions? That sounds like a big job. If it was learned (much better), how was it learned? What is the internal representation of the language processing model that leads to this particular concept formation, and how was it generated? If I can see something specific like that in a system (say Novamente) I can start to really understand the theory of mind it expresses. _ agi | http://www.listbox.com/member/archive/303/=now Archives http://www.listbox.com/member/archive/rss/303/ | http://www.listbox.com/member/?; Modify Your Subscription http://www.listbox.com --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Vladimir Nesov writes: Generating concepts out of thin air is no big deal, if only a resource-hungry process. You can create a dozen for each episode, for example. If I am not certain of the appropriate mechanism and circumstances for generating one concept, it doesn't help to suggest that a dozen get generated instead... now I have twelve times as many things to explain. If you are suggesting that concept formation is a (perhaps stochastic) generate-and-test procedure, that seems like an okay idea but the issues are then redescribed as: what is the generation procedure, what causes it to be invoked, what the test procedure is, and so on. These questions cannot be answered outside the context of a particular system; they are just the things I'd like to understand exactly how they would happen in Novamente or Texai or whatever, with all handwaving removed. To get back to the original question of this thread, these are some of the many missing conceptual pieces TO ME because I cannot see the specific nuts and bolts solution for any proposed system. It may in fact be that for any non-toy example the mechanisms and data are going to be too complicated for such analysis... that is, my brain is too puny and ineffective to understand (in a clear and relatively complete way) the inner workings of a general intelligence. In that case, all I can do is hope for proof by performance. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
On Mon, Apr 21, 2008 at 11:45 PM, Derek Zahn [EMAIL PROTECTED] wrote: If I am not certain of the appropriate mechanism and circumstances for generating one concept, it doesn't help to suggest that a dozen get generated instead... now I have twelve times as many things to explain. If you are suggesting that concept formation is a (perhaps stochastic) generate-and-test procedure, that seems like an okay idea but the issues are then redescribed as: what is the generation procedure, what causes it to be invoked, what the test procedure is, and so on. I just wanted to emphasize the importance of how new concepts actively influence the system (as opposed to being passively created). If new concepts don't do anything, you don't need them. If they can be observed and acted upon, they already change the way system behaves. This does look shallow without specific framework in mind though. In my current model, there is only a 'test', no 'generate': new concepts are not usually created at all (only to change resource quota), instead existing concepts are adapted, allowing themselves to be influenced by other concepts. So, from my current point of view, it's much more natural to look at what new concept does to existing system than at how it originates. -- Vladimir Nesov [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Zahn=== If you are suggesting that concept formation is a (perhaps stochastic) generate-and-test procedure, that seems like an okay idea but the issues are then redescribed as: what is the generation procedure, what causes it to be invoked, what the test procedure is, and so on. These questions cannot be answered outside the context of a particular system; they are just the things I'd like to understand exactly how they would happen in Novamente or Texai or whatever, with all handwaving removed. To get back to the original question of this thread, these are some of the many missing conceptual pieces TO ME because I cannot see the specific nuts and bolts solution for any proposed system. It may in fact be that for any non-toy example the mechanisms and data are going to be too complicated for such analysis... that is, my brain is too puny and ineffective to understand (in a clear and relatively complete way) the inner workings of a general intelligence. In that case, all I can do is hope for proof by performance. Porter=== With regard to the generate part of generate and test --- there are multiple ways to generate patterns and concepts. I think a lot can be achieved just by recording significant parts of the hierarchical memory activation states (such as the most attended parts of the most attended state). And then generalizing over such states, as described in my recent posts regarding hierarchical memory. But many feel this relatively direct recording of experience at multiple generalizational and compositional levels is not good enough. Novamente uses an evolutionary learning process in addition to its more standard record and generalize type of learning. Wlodzislaw Duch at AGI 2008 told me that one of the current theories of cortical columns in the brain is that they receive input patterns and they project them into a much higher dimensional space (i.e., making from a given input pattern many output patterns) , making available for learning a larger number of representations of patterns, some of which my be more helpful for finding the valuable commonalities and valuable distinctions between patterns. This is somewhat like the way in which the kernel trick, in effect, project data from a lower dimensional space into a higher dimensional space so support vectors can better distinguish between classes. With regard to test part of generate and test --- reinforcement learning, has proved to be a very powerful form or machine learning. It provides a good model for how a network representation can properly allocate scores reflecting the values their various states and transition links have played in obtaining some desired reward, by distributing value back from the rewarded state to the transitions and states through which it was reached in a particular experience. A similar type of projecting of value back from rewarded states into patterns that prove useful in achieving that state could be used in a Novamente type system. Your statement about the brain being too puny to totally understand a powerful AGI system is true for all humans. This is analogous to the fact that one of the major things speeding brain science today is computer simulation, which is allowing simulated neural network circuits to indicate how various hypothesized circuits in the brain would work at a level of model complexity in which human minds would it find virtually impossible to make accurate predictions. If you spend enough time reading about AI and AGI architectures and brain science you should be able to develop a feeling for how an you might expect one or more AGI systems to work. But it is impossible to actually imagine the full complexity of a roughly human level AGI. We can have feelings that certain types of architectures should behave in certain ways, some based on evidence of similar systems, and some based on intuition and partial simulations in our own mind. But for complex things --- like the meaning of all the patterns in a human level, automatically created memory hierarchy --- , or like the most efficient behaviors and parameters for tuning spreading activation and implication --- I think at this stage we will have to build such systems to learn how to do this well. Any simulation of them is way beyond the human mind --- and would probably be as complex to do by computer simulation as by the building of a real AGI computer system itself. -Original Message- From: Derek Zahn [mailto:[EMAIL PROTECTED] Sent: Monday, April 21, 2008 3:46 PM To: agi@v2.listbox.com Subject: RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses Vladimir Nesov writes: Generating concepts out of thin air is no big deal, if only a resource-hungry process. You can create a dozen for each episode, for example. If I am not certain of the appropriate mechanism and circumstances for generating one concept, it doesn't help to suggest
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
On 21/04/2008, Ed Porter [EMAIL PROTECTED] wrote: So when people are given a sentence such as the one you quoted about verbs, pronouns, and nouns, presuming they have some knowledge of most of the words in the sentence, they will understand the concept that verbs are doing words. This is because of the groupings of words that tend to occur in certain syntactical linguistic contexts, the ones that would be most associated with the types of experiences the mind would associates with doing would be largely word senses that are verbs and that the mind's experience and learned patterns most often proceeds by nouns or pronouns. So all this stuff falls out of the magic of spreading activation in a Novamente-like hierarchical experiential memories (with the help of a considerable control structure such as that envisioned for Novamente). Declarative information learned by NL gets projected into the same type of activations in the hierarchical memory How does this happen? What happens when you try and project, This sentence is false. into the activations of the hierarchical memory? And consider that the whole of the english understanding is likely to be in the hierarchical memory. That is the projection must be learnt. as would actual experiences that teaches the same thing, but at least as episodes, and in some patterns generalized from episodes, such declarative information would remain linked to the experience of having been learned from reading or hearing from other humans. So in summary, a Novamete-like system should be able to handle this alleged problem, and at the moment it does not appear to provide an major unanswered conceptual problem. My conversation with Ben about similar subject (words acting on the knowledge of words) didn't get anywhere. The conversation starting here - http://www.mail-archive.com/agi@v2.listbox.com/msg09485.html And I consider him the authority on Novamente-like systems, for now at least. Will --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Ed Porter wrote: Richard, There is no evidence you are more justified in laughing at my position than I am in saying your complexity issues do not appear to represent a major unsolved conceptual issues. Remember I am not denying complexity issues don't exist. Instead I am saying it is not clear they provide a major conceptual problem. There are many tools for controlling the dynamic complexity in a Novamente-like system. How long it will take to tune and refine them is an issue. In WebMind Ben said parameter tuning turned out to be a substantial problem, particularly because of the slowness of the system on which they were exploring the parameter space. So I think it will present an engineering challenge and require more thought to provide the dynamic control required for things like efficient inferencing. But it is not clear such control issues will present a major conceptual problem. And remember I have admitted you might, in fact, be correct, and that complexity may turn out to present a major conceptual problem --- although I doubt it. So you are treating my viewpoint with much less respect than you are treating mine and it is far from clear your greater certitude is at all justified by the evidence. Merely referring to Morton-Thiokol in no way proves that you like them were right when others were wrong. Ed, Everything you have said in this and the last few posts about the 'complex systems issue' has nothing whatsoever to do with the complex systems problem that I have described - there is simply no connection between the CSP and your reflected-back version of it. That is not lack of respect for your viewpoint, it is a simple statement of fact. In my anecdote about Morton Thiolokol, your contribution would be one of the people who present a complete misunderstanding of what I was talking about. I do not laugh at your misunderstanding, I laugh at the general complacency; the attitude that a problem denied is a problem solved. I laugh at the tragicomedic waste of effort. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Richard Loosemore: I do not laugh at your misunderstanding, I laugh at the general complacency; the attitude that a problem denied is a problem solved. I laugh at the tragicomedic waste of effort. I'm not sure I have ever seen anybody successfully rephrase your complexity argument back at you; since nobody understands what you mean it's not surprising that people are complacent about it. I was going to wait for some more blog posts to have a go at rephrasing it myself but my (probably wrong effort) would go like this: 1. Many things we want to build have desired properties that are described at a different level than the things we build them out of. Flying is emergent in this sense from rivets and sheet metal, for example. Thinking is emergent from neurons, for another example. 2. Some such things are complex in that the emergent properties cannot be predicted from the lower-level details. 3. Flying as above is not complex in this way. In fact, all of engineering is the study of how to build things that are increasingly complicated but NOT complex. We do not want airplanes to have complex behavior and the engineering methodology is expressly for squeezing complexity out. 4. Thinking must be complex. [my understanding of why this must be true is lacking. Something like: otherwise we'd be able to predict the behavior of an AGI which would make it useless?] 5. Therefore we have no methods for building thinking machines, since engineering discipline does not address how to build complex devices. Building them as if they are not complex will result in poor behavior; squeezing out the complexity will squeeze out the thinking, and leaving it in makes traditional engineering impossible. Not quite right I suppose, but I'll keep working at it. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
On Tue, Apr 22, 2008 at 2:07 AM, Richard Loosemore [EMAIL PROTECTED] wrote: I do not laugh at your misunderstanding, I laugh at the general complacency; the attitude that a problem denied is a problem solved. I laugh at the tragicomedic waste of effort. How confident are you that this only-complex-AI limitation applies in reality? How much would you bet on it? I'm not convinced, and I think that if you are convinced too much, you made wrong conclusions from your data, unless you communicated too little of what formed your intuition. -- Vladimir Nesov [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
On Tue, Apr 22, 2008 at 2:28 AM, Derek Zahn [EMAIL PROTECTED] wrote: I'm not sure I have ever seen anybody successfully rephrase your complexity argument back at you; since nobody understands what you mean it's not surprising that people are complacent about it. Derek, I'll not paraphrase the argument itself, but the conclusion. Thinking can't be designed from ground up, little success after success, module after module, elaboration and generalization. Instead, it can only be build as an opaque mess, and in a clean laboratory it's not possible for us miserable apes to invent it. But we have a working prototype, brains, so by limiting the design by properties we know from studying cognitive science, it's possible to leave few enough possibilities to enumerate by (more or less) blind search. That is what Richard's framework is supposed to do: you feed in the restrictions, and it automatically tests a whole set of designs limited by such restrictions. As a result, you experiment with restrictions and not with individual designs. Within each restriction set, there are designs that behave very differently, but framework allows you to sort out the weed and luckily find some gemstones. -- Vladimir Nesov [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
William, Re the Epimenides paradox, Eliezer Yudkowsky had some interesting comments in Levels of Organization in General Intelligence, Section 2.7.1 From Thoughts to deliberation. Which I quote below -In the universe of bad TV shows, speaking the Epimenides Paradox1 This sentence is false to an artificial mind causes that mind to scream in horror and collapse into a heap of smoldering parts. This is based on a stereotype of thought processes that cannot divert, cannot halt, and possess no bottom-up ability to notice regularities across an extended thought sequence. Given how deliberation emerges from the thought level, it is possible to imagine a sufficiently sophisticated, sufficiently reflective AI that could naturally surmount the Epimenides Paradox. Encountering the paradox This sentence is false would probably indeed lead to a looping thought sequence at first, but this would not cause the AI to become permanently stuck; it would instead lead to categorization across repeated thoughts (like a human noticing the paradox after a few cycles), which categorization would then become salient and could be pondered in its own right by other sequiturs. If the AI is sufficiently competent at deductive reasoning and introspective generalization, it could generalize across the specific instances of If the statement is true, it must be false and If the statement is false, it must be true as two general classes of thoughts produced by the paradox, and show that reasoning from a thought of one class leads to a thought of the other class; if so the AI could deduce - not just inductively notice, but deductively confirm - that the thought process is an eternal loop. Of course, we won't know whether it really works this way until we try it. -The use of a blackboard sequitur model is not automatically sufficient for deep reflectivity; an AI that possessed a limited repertoire of sequiturs, no reflectivity, no ability to employ reflective categorization, and no ability to notice when a train of thought hasn't yielded anything useful for a while, might still loop eternally through the paradox as the emergent but useless product of the sequitur repertoire. Transcending the Epimenides Paradox requires the ability to perform inductive generalization and deductive reasoning on introspective experiences. But it also requires bottom-up organization in deliberation, so that a spontaneous introspective generalization can capture the focus of attention. Deliberation must emerge from thoughts, not just use thoughts to implement rigid algorithms. -Original Message- From: William Pearson [mailto:[EMAIL PROTECTED] Sent: Monday, April 21, 2008 5:42 PM To: agi@v2.listbox.com Subject: Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses On 21/04/2008, Ed Porter [EMAIL PROTECTED] wrote: So when people are given a sentence such as the one you quoted about verbs, pronouns, and nouns, presuming they have some knowledge of most of the words in the sentence, they will understand the concept that verbs are doing words. This is because of the groupings of words that tend to occur in certain syntactical linguistic contexts, the ones that would be most associated with the types of experiences the mind would associates with doing would be largely word senses that are verbs and that the mind's experience and learned patterns most often proceeds by nouns or pronouns. So all this stuff falls out of the magic of spreading activation in a Novamente-like hierarchical experiential memories (with the help of a considerable control structure such as that envisioned for Novamente). Declarative information learned by NL gets projected into the same type of activations in the hierarchical memory How does this happen? What happens when you try and project, This sentence is false. into the activations of the hierarchical memory? And consider that the whole of the english understanding is likely to be in the hierarchical memory. That is the projection must be learnt. as would actual experiences that teaches the same thing, but at least as episodes, and in some patterns generalized from episodes, such declarative information would remain linked to the experience of having been learned from reading or hearing from other humans. So in summary, a Novamete-like system should be able to handle this alleged problem, and at the moment it does not appear to provide an major unanswered conceptual problem. My conversation with Ben about similar subject (words acting on the knowledge of words) didn't get anywhere. The conversation starting here - http://www.mail-archive.com/agi@v2.listbox.com/msg09485.html And I consider him the authority on Novamente-like systems, for now at least. Will --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your
RE: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Richard, I read you Complex Systems, Artificial Intelligence and Theoretical Psychology article, and I still don't know what your are talking about other than the game of life. I know you make a distinction between Richard and non-Richard complexity. I understand computational irreducibility. And I understand that how complex a program is, in terms of its number of lines is not directly related to how varied and unpredictable its output will be. I would appreciate it, Richard, if you could explain what you mean by Richard complexity vs. non-Richard complexity. Ed Porter -Original Message- From: Richard Loosemore [mailto:[EMAIL PROTECTED] Sent: Monday, April 21, 2008 6:08 PM To: agi@v2.listbox.com Subject: Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses Ed Porter wrote: Richard, There is no evidence you are more justified in laughing at my position than I am in saying your complexity issues do not appear to represent a major unsolved conceptual issues. Remember I am not denying complexity issues don't exist. Instead I am saying it is not clear they provide a major conceptual problem. There are many tools for controlling the dynamic complexity in a Novamente-like system. How long it will take to tune and refine them is an issue. In WebMind Ben said parameter tuning turned out to be a substantial problem, particularly because of the slowness of the system on which they were exploring the parameter space. So I think it will present an engineering challenge and require more thought to provide the dynamic control required for things like efficient inferencing. But it is not clear such control issues will present a major conceptual problem. And remember I have admitted you might, in fact, be correct, and that complexity may turn out to present a major conceptual problem --- although I doubt it. So you are treating my viewpoint with much less respect than you are treating mine and it is far from clear your greater certitude is at all justified by the evidence. Merely referring to Morton-Thiokol in no way proves that you like them were right when others were wrong. Ed, Everything you have said in this and the last few posts about the 'complex systems issue' has nothing whatsoever to do with the complex systems problem that I have described - there is simply no connection between the CSP and your reflected-back version of it. That is not lack of respect for your viewpoint, it is a simple statement of fact. In my anecdote about Morton Thiolokol, your contribution would be one of the people who present a complete misunderstanding of what I was talking about. I do not laugh at your misunderstanding, I laugh at the general complacency; the attitude that a problem denied is a problem solved. I laugh at the tragicomedic waste of effort. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Vladimir Nesov wrote: On Tue, Apr 22, 2008 at 2:07 AM, Richard Loosemore [EMAIL PROTECTED] wrote: I do not laugh at your misunderstanding, I laugh at the general complacency; the attitude that a problem denied is a problem solved. I laugh at the tragicomedic waste of effort. How confident are you that this only-complex-AI limitation applies in reality? How much would you bet on it? I'm not convinced, and I think that if you are convinced too much, you made wrong conclusions from your data, unless you communicated too little of what formed your intuition. I am completely sure that it applies (although your phrasing makes me wonder if you have interpreted my exact worry accurately... I will have to come back to that). I am confident becasue of this. I have been trying to understand the relationship between theoretical models of thought (both natural and artificial) since at least 1980, and one thing I have noticed is that people devise theoretical structures that are based on the assumption that intelligence is not complex but then they use these structures in such a way that the resulting system is almost always complex. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Ed Porter wrote: Richard, I read you Complex Systems, Artificial Intelligence and Theoretical Psychology article, and I still don't know what your are talking about other than the game of life. I know you make a distinction between Richard and non-Richard complexity. I understand computational irreducibility. And I understand that how complex a program is, in terms of its number of lines is not directly related to how varied and unpredictable its output will be. I would appreciate it, Richard, if you could explain what you mean by Richard complexity vs. non-Richard complexity. [?] Maybe you should get to me offlist about this. I don't quite know that means. Did you read the blog post on this topic? It was supposed to be more accessible than the paper. Blog is at susaro.com Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
Vladimir Nesov wrote: On Tue, Apr 22, 2008 at 2:28 AM, Derek Zahn [EMAIL PROTECTED] wrote: I'm not sure I have ever seen anybody successfully rephrase your complexity argument back at you; since nobody understands what you mean it's not surprising that people are complacent about it. Derek, I'll not paraphrase the argument itself, but the conclusion. Thinking can't be designed from ground up, little success after success, module after module, elaboration and generalization. Instead, it can only be build as an opaque mess, and in a clean laboratory it's not possible for us miserable apes to invent it. But we have a working prototype, brains, so by limiting the design by properties we know from studying cognitive science, it's possible to leave few enough possibilities to enumerate by (more or less) blind search. That is what Richard's framework is supposed to do: you feed in the restrictions, and it automatically tests a whole set of designs limited by such restrictions. As a result, you experiment with restrictions and not with individual designs. Within each restriction set, there are designs that behave very differently, but framework allows you to sort out the weed and luckily find some gemstones. H I detect a parody..? That is not what I intended to say. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? --- recent input and responses
On Apr 21, 2008, at 6:53 PM, Richard Loosemore wrote: I have been trying to understand the relationship between theoretical models of thought (both natural and artificial) since at least 1980, and one thing I have noticed is that people devise theoretical structures that are based on the assumption that intelligence is not complex but then they use these structures in such a way that the resulting system is almost always complex. This is easily explained by the obvious fact that the definition of complex varies considerably across relevant populations, exacerbated in the case of AGI -- where it is arguably a germane element -- because many (most?) researchers are using complex in a colloquial (read: meaningless) sense rather than one of its more rigorously defined senses, of which there are a few interesting ones. Most arguments and disagreements over complexity are fundamentally about the strict definition of the term, or the complete absence thereof. The arguments tend to evaporate if everyone is forced to unambiguously define such terms, but where is the fun in that. J. Andrew Rogers --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
