Re: [agi] Approximations of Knowledge
On Wed, Jul 2, 2008 at 5:31 AM, Terren Suydam [EMAIL PROTECTED] wrote: Nevertheless, generalities among different instances of complex systems have been identified, see for instance: http://en.wikipedia.org/wiki/Feigenbaum_constants To be sure, but there are also plenty of complex systems where Feigenbaum's constants don't arise. I'm not saying there aren't theories that say things about more than one complex system - clearly there are - only that there aren't any that say nontrivial things about complex systems in general. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
That may be true, but it misses the point I was making, which was a response to Richard's lament about the seeming lack of any generality from one complex system to the next. The fact that Feigenbaum's constants describe complex systems of different kinds is remarkable because it suggests an underlying order among systems that are described by different equations. It is not unreasonable to imagine that in the future we will develop a much more robust mathematics of complex systems. --- On Thu, 7/3/08, Russell Wallace [EMAIL PROTECTED] wrote: [EMAIL PROTECTED] wrote: Nevertheless, generalities among different instances of complex systems have been identified, see for instance: http://en.wikipedia.org/wiki/Feigenbaum_constants To be sure, but there are also plenty of complex systems where Feigenbaum's constants don't arise. I'm not saying there aren't theories that say things about more than one complex system - clearly there are - only that there aren't any that say nontrivial things about complex systems in general. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
On Mon, Jun 30, 2008 at 8:10 PM, Richard Loosemore [EMAIL PROTECTED] wrote: My scepticism comes mostly from my personal observation that each complex systems scientist I come across tends to know about one breed of complex system, and have a great deal to say about that breed, but when I come to think about my preferred breed (AGI, cognitive systems) I cannot seem to relate their generalizations to my case. That's not very surprising if you think about it. Suppose we postulate the existence of a grand theory of complexity. That's a theory of everything that is not simple (in the sense being discussed here) - but a theory that says something about _every nontrivial thing in the entire Tegmark multiverse_ is rather obviously not going to say very much about any particular thing. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Nevertheless, generalities among different instances of complex systems have been identified, see for instance: http://en.wikipedia.org/wiki/Feigenbaum_constants Terren --- On Tue, 7/1/08, Russell Wallace [EMAIL PROTECTED] wrote: [EMAIL PROTECTED] wrote: My scepticism comes mostly from my personal observation that each complex systems scientist I come across tends to know about one breed of complex system, and have a great deal to say about that breed, but when I come to think about my preferred breed (AGI, cognitive systems) I cannot seem to relate their generalizations to my case. That's not very surprising if you think about it. Suppose we postulate the existence of a grand theory of complexity. That's a theory of everything that is not simple (in the sense being discussed here) - but a theory that says something about _every nontrivial thing in the entire Tegmark multiverse_ is rather obviously not going to say very much about any particular thing. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Richard, Thanks for your comments. Very interesting. I'm looking forward to reading the introductory book by Waldrop. Thanks again! Cheers, Brad Richard Loosemore wrote: Brad Paulsen wrote: Richard, I think I'll get the older Waldrop book now because I want to learn more about the ideas surrounding complexity (and, in particular, its association with, and differentiation from, chaos theory) as soon as possible. But, I will definitely put an entry in my Google calendar to keep a lookout for the new book in 2009. Thanks very much for the information! Cheers, Brad You're welcome. I hope it is not a disappointment: the subject is a peculiar one, so I believe that it is better to start off with the kind of journalistic overview that Waldrop gives. Let me know what your reaction is. Here is the bottom line. At the core of the complex systems idea there is something very significant and very powerful, but a lot of people have wanted it to lead to a new science just like some of the old science. In other words, they have wanted there to be a new, fabulously powerful 'general theory of complexity' coming down the road. However, no such theory is in sight, and there is one view of complexity (mine, for example) that says that there will probably never be such a theory. If this were one of the traditional sciences, the absence of that kind of progress toward unification would be a sign of trouble - a sign that this was not really a new science after all. Or, even worse, a sign that the original idea was bogus. But I believe that is the wrong interpretation to put on it. The complexity idea is very significant, but it is not a science by itself. Having said all of that, there are many people who so much want there to be a science of complexity (enough of a science that there could be an institute dedicated to it, where people have real jobs working on 'complex systems'), that they are prepared to do a lot of work that makes it look like something is happening. So, you can find many abstract papers about complex dynamical systems, with plenty of mathematics in them. But as far as I can see, most of that stuff is kind of peripheral ... it is something to do to justify a research program. At the end of the day, I think that the *core* complex systems idea will outlast all this other stuff, but it will become famous for its impact on oter sciences, rather than for the specific theories of 'complexity' that it generates. We will see. Richard Loosemore Richard Loosemore wrote: Brad Paulsen wrote: Or, maybe... Complexity: Life at the Edge of Chaos Roger Lewin, 2000 $10.88 (new, paperback) from Amazon (no used copies) Complexity: Life at the Edge of Chaos by Roger Lewin (Paperback - Feb 15, 2000) Nope, not that one either! Darn. I think it may have been Simplexity (Kluger), but I am not sure. Interestingly enough, Melanie Mitchell has a book due out in 2009 called The Core Ideas of the Sciences of Complexity. Interesting title, given my thoughts in the last post. 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/?; 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/?; 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Terren Suydam wrote: Hi Richard, I'll de-lurk here to say that I find this email to be utterly reasonable, and that's with my crackpot detectors going off a lot lately, no offense to you of course. I do disagree that complexity is not its own science. I'm not wedded to the idea, like the folks you profile in your email, but I think its contribution has been small because it's in its infancy. We've been developing reductionist tools for hundreds of years now. I think we're in the equivalent of the pre-calculus days when it comes to complexity science. And we haven't made much progress because the traditional scientific method depends on direct causal linkages. On the contrary, complex systems exhibit behavior at a global level that is not predictable from the local level... so there's a causal relationship only in the weakest sense. It's much more straightforward, I think, to say that the two levels, the global and the local, are causally orthogonal to one another. Both levels can be described by completely independent causal dynamics. It's a new science because it's a new method. Isolating variables to determine relationships doesn't lend itself well to massively parallel networks that are just lousy with feedback, because it's impossible to hold the other values still, and worse, the behavior is sensitive to experimental noise. You could write a book on the difference between the traditional scientific method and the methods for studying complexity. I'm sure it's been done, actually. The study of complexity will eventually fulfill its potential as a new science, because if we are ever to understand the brain and the mind and model them with any real precision, it will be due to complexity science *as much as* traditional reductionist science. We need the benefit of both to gain real understanding where traditional science has failed. Our human minds are simply too limited to grasp the enormity of the scale of complexity within a single cell, much less a collection of a few trillion of them, also arranged in an unfathomably complex arrangement. The idea that complexity science will *not* figure prominently into the study of the body, the brain, and the mind, is an absurd proposition to me. We will be going in the right direction when more and more of us are simulating something without any clue what the result will be. That's all for now... thanks for your post Richard. Thanks Terren Yes, in my more optimistic moments I believe that a full science of complexity will come about. It may redefine the meaning of 'science' though. My scepticism comes mostly from my personal observation that each complex systems scientist I come across tends to know about one breed of complex system, and have a great deal to say about that breed, but when I come to think about my preferred breed (AGI, cognitive systems) I cannot seem to relate their generalizations to my case. That is not to say that things will not converge, though. I should be careful not to prejudge something so young. Richard Loosemore --- On Sun, 6/29/08, Richard Loosemore [EMAIL PROTECTED] wrote: From: Richard Loosemore [EMAIL PROTECTED] Subject: Re: [agi] Approximations of Knowledge To: agi@v2.listbox.com Date: Sunday, June 29, 2008, 9:23 PM Brad Paulsen wrote: Richard, I think I'll get the older Waldrop book now because I want to learn more about the ideas surrounding complexity (and, in particular, its association with, and differentiation from, chaos theory) as soon as possible. But, I will definitely put an entry in my Google calendar to keep a lookout for the new book in 2009. Thanks very much for the information! Cheers, Brad You're welcome. I hope it is not a disappointment: the subject is a peculiar one, so I believe that it is better to start off with the kind of journalistic overview that Waldrop gives. Let me know what your reaction is. Here is the bottom line. At the core of the complex systems idea there is something very significant and very powerful, but a lot of people have wanted it to lead to a new science just like some of the old science. In other words, they have wanted there to be a new, fabulously powerful 'general theory of complexity' coming down the road. However, no such theory is in sight, and there is one view of complexity (mine, for example) that says that there will probably never be such a theory. If this were one of the traditional sciences, the absence of that kind of progress toward unification would be a sign of trouble - a sign that this was not really a new science after all. Or, even worse, a sign that the original idea was bogus. But I believe that is the wrong interpretation to put on it. The complexity idea is very significant, but it is not a science by itself. Having said all of that, there are many people who so much want there to be a science of complexity (enough of a science that there could be an institute
Re: [agi] Approximations of Knowledge
Brad Paulsen wrote: Richard, I think I'll get the older Waldrop book now because I want to learn more about the ideas surrounding complexity (and, in particular, its association with, and differentiation from, chaos theory) as soon as possible. But, I will definitely put an entry in my Google calendar to keep a lookout for the new book in 2009. Thanks very much for the information! Cheers, Brad You're welcome. I hope it is not a disappointment: the subject is a peculiar one, so I believe that it is better to start off with the kind of journalistic overview that Waldrop gives. Let me know what your reaction is. Here is the bottom line. At the core of the complex systems idea there is something very significant and very powerful, but a lot of people have wanted it to lead to a new science just like some of the old science. In other words, they have wanted there to be a new, fabulously powerful 'general theory of complexity' coming down the road. However, no such theory is in sight, and there is one view of complexity (mine, for example) that says that there will probably never be such a theory. If this were one of the traditional sciences, the absence of that kind of progress toward unification would be a sign of trouble - a sign that this was not really a new science after all. Or, even worse, a sign that the original idea was bogus. But I believe that is the wrong interpretation to put on it. The complexity idea is very significant, but it is not a science by itself. Having said all of that, there are many people who so much want there to be a science of complexity (enough of a science that there could be an institute dedicated to it, where people have real jobs working on 'complex systems'), that they are prepared to do a lot of work that makes it look like something is happening. So, you can find many abstract papers about complex dynamical systems, with plenty of mathematics in them. But as far as I can see, most of that stuff is kind of peripheral ... it is something to do to justify a research program. At the end of the day, I think that the *core* complex systems idea will outlast all this other stuff, but it will become famous for its impact on oter sciences, rather than for the specific theories of 'complexity' that it generates. We will see. Richard Loosemore Richard Loosemore wrote: Brad Paulsen wrote: Or, maybe... Complexity: Life at the Edge of Chaos Roger Lewin, 2000 $10.88 (new, paperback) from Amazon (no used copies) Complexity: Life at the Edge of Chaos by Roger Lewin (Paperback - Feb 15, 2000) Nope, not that one either! Darn. I think it may have been Simplexity (Kluger), but I am not sure. Interestingly enough, Melanie Mitchell has a book due out in 2009 called The Core Ideas of the Sciences of Complexity. Interesting title, given my thoughts in the last post. 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/?; 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Hi Richard, I'll de-lurk here to say that I find this email to be utterly reasonable, and that's with my crackpot detectors going off a lot lately, no offense to you of course. I do disagree that complexity is not its own science. I'm not wedded to the idea, like the folks you profile in your email, but I think its contribution has been small because it's in its infancy. We've been developing reductionist tools for hundreds of years now. I think we're in the equivalent of the pre-calculus days when it comes to complexity science. And we haven't made much progress because the traditional scientific method depends on direct causal linkages. On the contrary, complex systems exhibit behavior at a global level that is not predictable from the local level... so there's a causal relationship only in the weakest sense. It's much more straightforward, I think, to say that the two levels, the global and the local, are causally orthogonal to one another. Both levels can be described by completely independent causal dynamics. It's a new science because it's a new method. Isolating variables to determine relationships doesn't lend itself well to massively parallel networks that are just lousy with feedback, because it's impossible to hold the other values still, and worse, the behavior is sensitive to experimental noise. You could write a book on the difference between the traditional scientific method and the methods for studying complexity. I'm sure it's been done, actually. The study of complexity will eventually fulfill its potential as a new science, because if we are ever to understand the brain and the mind and model them with any real precision, it will be due to complexity science *as much as* traditional reductionist science. We need the benefit of both to gain real understanding where traditional science has failed. Our human minds are simply too limited to grasp the enormity of the scale of complexity within a single cell, much less a collection of a few trillion of them, also arranged in an unfathomably complex arrangement. The idea that complexity science will *not* figure prominently into the study of the body, the brain, and the mind, is an absurd proposition to me. We will be going in the right direction when more and more of us are simulating something without any clue what the result will be. That's all for now... thanks for your post Richard. Terren --- On Sun, 6/29/08, Richard Loosemore [EMAIL PROTECTED] wrote: From: Richard Loosemore [EMAIL PROTECTED] Subject: Re: [agi] Approximations of Knowledge To: agi@v2.listbox.com Date: Sunday, June 29, 2008, 9:23 PM Brad Paulsen wrote: Richard, I think I'll get the older Waldrop book now because I want to learn more about the ideas surrounding complexity (and, in particular, its association with, and differentiation from, chaos theory) as soon as possible. But, I will definitely put an entry in my Google calendar to keep a lookout for the new book in 2009. Thanks very much for the information! Cheers, Brad You're welcome. I hope it is not a disappointment: the subject is a peculiar one, so I believe that it is better to start off with the kind of journalistic overview that Waldrop gives. Let me know what your reaction is. Here is the bottom line. At the core of the complex systems idea there is something very significant and very powerful, but a lot of people have wanted it to lead to a new science just like some of the old science. In other words, they have wanted there to be a new, fabulously powerful 'general theory of complexity' coming down the road. However, no such theory is in sight, and there is one view of complexity (mine, for example) that says that there will probably never be such a theory. If this were one of the traditional sciences, the absence of that kind of progress toward unification would be a sign of trouble - a sign that this was not really a new science after all. Or, even worse, a sign that the original idea was bogus. But I believe that is the wrong interpretation to put on it. The complexity idea is very significant, but it is not a science by itself. Having said all of that, there are many people who so much want there to be a science of complexity (enough of a science that there could be an institute dedicated to it, where people have real jobs working on 'complex systems'), that they are prepared to do a lot of work that makes it look like something is happening. So, you can find many abstract papers about complex dynamical systems, with plenty of mathematics in them. But as far as I can see, most of that stuff is kind of peripheral ... it is something to do to justify a research program. At the end of the day, I think that the *core* complex systems idea will outlast all this other stuff, but it will become famous for its impact on oter sciences
Re: [agi] Approximations of Knowledge
Richard, I presume this is the Waldrop Complexity book to which you referred: Complexity: The Emerging Science at the Edge of Order and Chaos M. Mitchell Waldrop, 1992, $10.20 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/Complexity-Emerging-Science-Order-Chaos/dp/0671872346/ref=pd_bbs_sr_1?ie=UTF8s=booksqid=1214641304sr=1-1 Is this the newer book you had in mind? At Home in the Universe: The Search for the Laws of Self-Organization and Complexity Stuart Kauffman (The Santa Fe Institute), 1995, $18.95 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/At-Home-Universe-Self-Organization-Complexity/dp/0195111303/ref=reg_hu-wl_mrai-recs Cheers, Brad Richard Loosemore wrote: Jim Bromer wrote: From: Richard Loosemore Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). Richard Loosemore Well lets forget about your theory for a second. I think that an advanced AI program is going to have to be able to deal with complexity and that your analysis is certainly interesting and illuminating. But I want to make sure that I understand what you mean here. First of all, your statement, it is not possible to use analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. By analytic mathematics are you referring to numerical analysis, which the article in Wikipedia, http://en.wikipedia.org/wiki/Numerical_analysis describes as the study of algorithms for the problems of continuous mathematics (as distinguished from discrete mathematics). Because if you are saying that the study of continuous mathematics -as distinguished from discrete mathematics- cannot be used to represent discreet system complexity, then that is kind of a non-starter. It's a cop-out by initial definition. I am primarily interested in discreet programming ( I am, of course also interested in continuous systems as well), but in this discussion I was expressing my interest in measures that can be taken to simplify computational complexity. Again, Wikipedia gives a slightly more complex definition of complexity than you do. http://en.wikipedia.org/wiki/Complexity I am not saying that your particular definition of complexity is wrong, I only want to make sure that I understand what it is that you are getting at. The part of your sentence that read, ...given only the rules that determine the local mechanisms, sounds like it might well apply to the kind of system that I think would be necessary for a better AI program, but it is not necessarily true of all kinds of demonstrations of complexity (as I understand them). For example, consider a program that demonstrates the emergence of complex behaviors from collections of objects that obey simple rules that govern their interactions. One can use a variety of arbitrary settings for the initial state of the program to examine how different complex behaviors may emerge in different environments. (I am hoping to try something like this when I buy my next computer with a great graphics chip in it.) This means that complexity does not have to be represented only in states that had been previously generated by the system, as can be obviously seen in the fact that initial states are a necessity of such systems. I think I get what you are saying about complexity in AI and the problems of research into AI that could be caused if complexity is the reality of advanced AI programming. But if you are throwing technical arguments at me, some of which are trivial from my perspective like the definition of, continuous mathematics (as distinguished from discrete mathematics), then all I can do is wonder why. Jim, With the greatest of respect, this is a topic that will require some extensive background reading on your part, because the misunderstandings in your above test are too deep for me to remedy in the scope of one or two list postings. For example, my reference to analytic mathematics has nothing at all to do with the wikipedia entry you found, alas. The word has many uses, and the one I am employing is meant to point up a distinction between classical mathematics that allows equations to be solved algebraically, and experimental mathematics that solves systems by simulation. Analytic means by analysis in this context...but this is a very
Re: [agi] Approximations of Knowledge
Or, maybe... Complexity: Life at the Edge of Chaos Roger Lewin, 2000 $10.88 (new, paperback) from Amazon (no used copies) Complexity: Life at the Edge of Chaos by Roger Lewin (Paperback - Feb 15, 2000) Brad Richard Loosemore wrote: Jim Bromer wrote: From: Richard Loosemore Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). Richard Loosemore Well lets forget about your theory for a second. I think that an advanced AI program is going to have to be able to deal with complexity and that your analysis is certainly interesting and illuminating. But I want to make sure that I understand what you mean here. First of all, your statement, it is not possible to use analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. By analytic mathematics are you referring to numerical analysis, which the article in Wikipedia, http://en.wikipedia.org/wiki/Numerical_analysis describes as the study of algorithms for the problems of continuous mathematics (as distinguished from discrete mathematics). Because if you are saying that the study of continuous mathematics -as distinguished from discrete mathematics- cannot be used to represent discreet system complexity, then that is kind of a non-starter. It's a cop-out by initial definition. I am primarily interested in discreet programming ( I am, of course also interested in continuous systems as well), but in this discussion I was expressing my interest in measures that can be taken to simplify computational complexity. Again, Wikipedia gives a slightly more complex definition of complexity than you do. http://en.wikipedia.org/wiki/Complexity I am not saying that your particular definition of complexity is wrong, I only want to make sure that I understand what it is that you are getting at. The part of your sentence that read, ...given only the rules that determine the local mechanisms, sounds like it might well apply to the kind of system that I think would be necessary for a better AI program, but it is not necessarily true of all kinds of demonstrations of complexity (as I understand them). For example, consider a program that demonstrates the emergence of complex behaviors from collections of objects that obey simple rules that govern their interactions. One can use a variety of arbitrary settings for the initial state of the program to examine how different complex behaviors may emerge in different environments. (I am hoping to try something like this when I buy my next computer with a great graphics chip in it.) This means that complexity does not have to be represented only in states that had been previously generated by the system, as can be obviously seen in the fact that initial states are a necessity of such systems. I think I get what you are saying about complexity in AI and the problems of research into AI that could be caused if complexity is the reality of advanced AI programming. But if you are throwing technical arguments at me, some of which are trivial from my perspective like the definition of, continuous mathematics (as distinguished from discrete mathematics), then all I can do is wonder why. Jim, With the greatest of respect, this is a topic that will require some extensive background reading on your part, because the misunderstandings in your above test are too deep for me to remedy in the scope of one or two list postings. For example, my reference to analytic mathematics has nothing at all to do with the wikipedia entry you found, alas. The word has many uses, and the one I am employing is meant to point up a distinction between classical mathematics that allows equations to be solved algebraically, and experimental mathematics that solves systems by simulation. Analytic means by analysis in this context...but this is a very abstract sense of the word that I am talking about here, and it is very hard to convey. This topic is all about 'complex systems' which is a technical term that does not mean systems that are complicated (in the everyday sense of 'complicated'). To get up to speed on this, I recommend a popular science book called Complexity by Waldrop, although there was also a more recent book whose name I forget, which may be better. You could also read Wolfram's A New Kind of Science, but that is huge and does not come
Re: [agi] Approximations of Knowledge
Richard Loosemore said: With the greatest of respect, this is a topic that will require some extensive background reading on your part, because the misunderstandings in your above test are too deep for me to remedy in the scope of one or two list postings. For example, my reference to analytic mathematics has nothing at all to do with the wikipedia entry you found, alas. --- But you did remedy the deep misunderstanding that you saw in my one question simply by answering it. If you ever change your mind and decide someday in the future that you would like to discuss this with me please let me know. Jim Bromer - Original Message From: Richard Loosemore [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Friday, June 27, 2008 9:13:01 PM Subject: Re: [agi] Approximations of Knowledge Jim Bromer wrote: From: Richard Loosemore Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). Richard Loosemore Well lets forget about your theory for a second. I think that an advanced AI program is going to have to be able to deal with complexity and that your analysis is certainly interesting and illuminating. But I want to make sure that I understand what you mean here. First of all, your statement, it is not possible to use analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. By analytic mathematics are you referring to numerical analysis, which the article in Wikipedia, http://en.wikipedia.org/wiki/Numerical_analysis describes as the study of algorithms for the problems of continuous mathematics (as distinguished from discrete mathematics). Because if you are saying that the study of continuous mathematics -as distinguished from discrete mathematics- cannot be used to represent discreet system complexity, then that is kind of a non-starter. It's a cop-out by initial definition. I am primarily interested in discreet programming ( I am, of course also interested in continuous systems as well), but in this discussion I was expressing my interest in measures that can be taken to simplify computational complexity. Again, Wikipedia gives a slightly more complex definition of complexity than you do. http://en.wikipedia.org/wiki/Complexity I am not saying that your particular definition of complexity is wrong, I only want to make sure that I understand what it is that you are getting at. The part of your sentence that read, ...given only the rules that determine the local mechanisms, sounds like it might well apply to the kind of system that I think would be necessary for a better AI program, but it is not necessarily true of all kinds of demonstrations of complexity (as I understand them). For example, consider a program that demonstrates the emergence of complex behaviors from collections of objects that obey simple rules that govern their interactions. One can use a variety of arbitrary settings for the initial state of the program to examine how different complex behaviors may emerge in different environments. (I am hoping to try something like this when I buy my next computer with a great graphics chip in it.) This means that complexity does not have to be represented only in states that had been previously generated by the system, as can be obviously seen in the fact that initial states are a necessity of such systems. I think I get what you are saying about complexity in AI and the problems of research into AI that could be caused if complexity is the reality of advanced AI programming. But if you are throwing technical arguments at me, some of which are trivial from my perspective like the definition of, continuous mathematics (as distinguished from discrete mathematics), then all I can do is wonder why. Jim, With the greatest of respect, this is a topic that will require some extensive background reading on your part, because the misunderstandings in your above test are too deep for me to remedy in the scope of one or two list postings. For example, my reference to analytic mathematics has nothing at all to do with the wikipedia entry you found, alas. The word has many uses, and the one I am employing is meant to point up a distinction between classical mathematics that allows equations
Re: [agi] Approximations of Knowledge
Brad: I presume this is the Waldrop Complexity book to which you referred: Complexity: The Emerging Science at the Edge of Order and Chaos M. Mitchell Waldrop, 1992, $10.20 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/Complexity-Emerging-Science-Order-Chaos/dp/0671872346/ref=pd_bbs_sr_1?ie=UTF8s=booksqid=1214641304sr=1-1 Is this the newer book you had in mind? At Home in the Universe: The Search for the Laws of Self-Organization and Complexity Stuart Kauffman (The Santa Fe Institute), 1995, $18.95 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/At-Home-Universe-Self-Organization-Complexity/dp/0195111303/ref=reg_hu-wl_mrai-recs Speaking of Kauffman, here's a quote from him, illustrating the points I was making in the other thread, re how a totally algorithmic approach to AGI - including an algorithmic trial-and-error approach - won't work (I disagree with him though - the mind IS a machine, just much more sophisticated than our current conceptions of machines): The second, predominant view among cognitive scientists is that consciousness arises when enough computational elements are networked together. In this view, a mind is a machine, and a complex set of buckets of water pouring water into one another would become conscious. I just cannot believe this. I cannot however disprove it, but I can offer arguments against it. On this view, the mind is algorithmic. With Penrose, in The Emperor's New Mind, I believe that the mind is not algorithmic, although it can act algorithmically. If it is not algorithmic, then the mind is not a machine and consciousness may not arise in a classical - as opposed to possibly to a quantum - system. Penrose bases his argument on the claim that in seeking a proof a mathematician does not follow an algorithm himself. I think he is right, but the example is not felicitous, for the proof itself is patently an algorithm, and how do we know that the mathematician did not subconsciously follow that algorithm in finding the proof. My arguments start from humbler conditions. Years ago my computer sat on my front table, plugged into a floor socket. I feared my family would bump into the cord and pull the computer off the table, breaking it. I now describe the table: 3 x 5 feet, three wooden boards on top, legs with certain carvings, chipped paint with the wood surface showing through with indefinitely many distances between points on the chipped flecks, two cracks, one crack seven feet from the fireplace, eleven feet from the kitchen, 238,000 miles from the moon, a broken leaf on the mid board of the top...You get the idea that there is no finite description of the table - assuming for example continuous spacetime. So I invented a solution. I jammed the cord into one of the cracks and pulled it tight so that my family would not be able to pull the computer off the table. Now it seems to me that there is no way to turn this Herculian mental performance into an algorithm. How would one bound the features of the situation finitely? How would one even list the features of the table in a denumerably infinite list? One cannot. Thus it seems to me that no algorithm was performed. As a broader case, we are all familiar with struggling to formulate a problem. Do you remotely think that your struggle is an effective mechanical or algorithmic procedure? I do not. I also do not know how to prove that a given performance is not algorithmic. What would count as such a proof? So I must leave my conviction with you, unproven, but powerful I think. If true, then the mind is not a machine. Stuart A. Kauffman , BEYOND REDUCTIONISM, Reinventing The Sacred, Edge, 11.13.06, http://www.edge.org/3rd_culture/kauffman06/kauffman06_index.html --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Brad Paulsen wrote: Richard, I presume this is the Waldrop Complexity book to which you referred: Complexity: The Emerging Science at the Edge of Order and Chaos M. Mitchell Waldrop, 1992, $10.20 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/Complexity-Emerging-Science-Order-Chaos/dp/0671872346/ref=pd_bbs_sr_1?ie=UTF8s=booksqid=1214641304sr=1-1 Is this the newer book you had in mind? At Home in the Universe: The Search for the Laws of Self-Organization and Complexity Stuart Kauffman (The Santa Fe Institute), 1995, $18.95 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/At-Home-Universe-Self-Organization-Complexity/dp/0195111303/ref=reg_hu-wl_mrai-recs Uh, no: Kauffman's book is also good, but that was not the one I am thinking of. Trouble is, it had some title that (IIRC) did not directly reference the word complex, so after looking at it in the bookstore I forgot it. I think one of the problems with complexity is that only a small chunk of it is necessary ... there is a lot of material that, to my mind, does not contribute much to the core idea. And the core idea is not quite enough for an entire book. But, having said that, the core idea is so subtle and so easily misunderstood that people trip over it without realizing its significance. Hm.. maybe that means there really should be a book length treatment of it after all. 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Jim Bromer wrote: Richard Loosemore said: With the greatest of respect, this is a topic that will require some extensive background reading on your part, because the misunderstandings in your above test are too deep for me to remedy in the scope of one or two list postings. For example, my reference to analytic mathematics has nothing at all to do with the wikipedia entry you found, alas. --- But you did remedy the deep misunderstanding that you saw in my one question simply by answering it. If you ever change your mind and decide someday in the future that you would like to discuss this with me please let me know. Jim Bromer I am happy to discuss it at any time, but it would help if you read either the paper I wrote, or my blog posts on the topic, or Waldrop's book. 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Brad Paulsen wrote: Or, maybe... Complexity: Life at the Edge of Chaos Roger Lewin, 2000 $10.88 (new, paperback) from Amazon (no used copies) Complexity: Life at the Edge of Chaos by Roger Lewin (Paperback - Feb 15, 2000) Nope, not that one either! Darn. I think it may have been Simplexity (Kluger), but I am not sure. Interestingly enough, Melanie Mitchell has a book due out in 2009 called The Core Ideas of the Sciences of Complexity. Interesting title, given my thoughts in the last post. 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Mike Tintner wrote: Brad: I presume this is the Waldrop Complexity book to which you referred: Complexity: The Emerging Science at the Edge of Order and Chaos M. Mitchell Waldrop, 1992, $10.20 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/Complexity-Emerging-Science-Order-Chaos/dp/0671872346/ref=pd_bbs_sr_1?ie=UTF8s=booksqid=1214641304sr=1-1 Is this the newer book you had in mind? At Home in the Universe: The Search for the Laws of Self-Organization and Complexity Stuart Kauffman (The Santa Fe Institute), 1995, $18.95 (new, paperback) from Amazon (used copies also available) http://www.amazon.com/At-Home-Universe-Self-Organization-Complexity/dp/0195111303/ref=reg_hu-wl_mrai-recs Speaking of Kauffman, here's a quote from him, illustrating the points I was making in the other thread, re how a totally algorithmic approach to AGI - including an algorithmic trial-and-error approach - won't work (I disagree with him though - the mind IS a machine, just much more sophisticated than our current conceptions of machines): The second, predominant view among cognitive scientists is that consciousness arises when enough computational elements are networked together. In this view, a mind is a machine, and a complex set of buckets of water pouring water into one another would become conscious. I just cannot believe this. I cannot however disprove it, but I can offer arguments against it. On this view, the mind is algorithmic. With Penrose, in The Emperor's New Mind, I believe that the mind is not algorithmic, although it can act algorithmically. If it is not algorithmic, then the mind is not a machine and consciousness may not arise in a classical - as opposed to possibly to a quantum - system. Penrose bases his argument on the claim that in seeking a proof a mathematician does not follow an algorithm himself. I think he is right, but the example is not felicitous, for the proof itself is patently an algorithm, and how do we know that the mathematician did not subconsciously follow that algorithm in finding the proof. My arguments start from humbler conditions. Years ago my computer sat on my front table, plugged into a floor socket. I feared my family would bump into the cord and pull the computer off the table, breaking it. I now describe the table: 3 x 5 feet, three wooden boards on top, legs with certain carvings, chipped paint with the wood surface showing through with indefinitely many distances between points on the chipped flecks, two cracks, one crack seven feet from the fireplace, eleven feet from the kitchen, 238,000 miles from the moon, a broken leaf on the mid board of the top...You get the idea that there is no finite description of the table - assuming for example continuous spacetime. So I invented a solution. I jammed the cord into one of the cracks and pulled it tight so that my family would not be able to pull the computer off the table. Now it seems to me that there is no way to turn this Herculian mental performance into an algorithm. How would one bound the features of the situation finitely? How would one even list the features of the table in a denumerably infinite list? One cannot. Thus it seems to me that no algorithm was performed. As a broader case, we are all familiar with struggling to formulate a problem. Do you remotely think that your struggle is an effective mechanical or algorithmic procedure? I do not. I also do not know how to prove that a given performance is not algorithmic. What would count as such a proof? So I must leave my conviction with you, unproven, but powerful I think. If true, then the mind is not a machine. Stuart A. Kauffman , BEYOND REDUCTIONISM, Reinventing The Sacred, Edge, 11.13.06, http://www.edge.org/3rd_culture/kauffman06/kauffman06_index.html What Kauffman is talking about here is the Frame Problem. Anyone who has gone through a standard AI/Cognitive Science training should recognize that. But now here is the trouble with this argument. What does he mean by saying that the mind is not 'algorithmic'? He uses the keyphrase 'effective procedure' when trying to describe this, but that is a loaded techical term What he means by 'algorithm' in this context is what some of us would call the rigid manipulation of simple, hard-edged symbols, using metods that have explicit semantics. BUT if you go outside that interpretation of 'algorithm' and include mechanisms that work by a process of dynamic, stochastic relaxation, it is easy in principle to see how this issue (the Frame Problem) could be solved. Or rather, it becomes difficult to see that a problem actually exists at all. The trouble is, that many of us would say that dynamic relaxation is just as algorithmic as anything else. It just does not involve symbols and mechanisms closed-form, explicit semantics. There is no big mystery here, no destruction of the Computational Paradigm.
Re: [agi] Approximations of Knowledge
Richard, I think I'll get the older Waldrop book now because I want to learn more about the ideas surrounding complexity (and, in particular, its association with, and differentiation from, chaos theory) as soon as possible. But, I will definitely put an entry in my Google calendar to keep a lookout for the new book in 2009. Thanks very much for the information! Cheers, Brad Richard Loosemore wrote: Brad Paulsen wrote: Or, maybe... Complexity: Life at the Edge of Chaos Roger Lewin, 2000 $10.88 (new, paperback) from Amazon (no used copies) Complexity: Life at the Edge of Chaos by Roger Lewin (Paperback - Feb 15, 2000) Nope, not that one either! Darn. I think it may have been Simplexity (Kluger), but I am not sure. Interestingly enough, Melanie Mitchell has a book due out in 2009 called The Core Ideas of the Sciences of Complexity. Interesting title, given my thoughts in the last post. 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Richard wrote: Interestingly enough, Melanie Mitchell has a book due out in 2009 called The Core Ideas of the Sciences of Complexity. Interesting title, given my thoughts in the last post. Thanks for the tip, Richard! I like her book on CopyCat, and I'd heard she had been doing complexity stuff. I will look for that. I looked at the complexity stuff when it was first coming out. As far as I can remember, not much has really come out of it, but it will be nice to hear what she has to say. andi --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Abram Demski wrote: Ah, so you do not accept AIXI either. Goodness me, no ;-). As far as I am concerned, AIXI is a mathematical formalism with loaded words like 'intelligence' attached to it, and then the formalism is taken as being about the real things in the world (i.e. intelligent systems) that those words normally signify. Put this way, your complex system dilemma applies only to pure AGI, and not to any narrow AI attempts, no matter how ambitious. But I suppose other, totally different reasons (such as P != NP, if so) can block those. Is this the best way to understand your argument? Meaning, is the key idea intelligence is a complex global property, so we can't define it? If so, my original blog post is way of. My interpretation was more like intelligence is a complex global property, so we can't predict its occurring based on local properties. These are two very different arguments. Perhaps you are arguing both points? My feeling is that it is a mixture of the two. My main concern is not to *assert* that intelligence is a complex global property, but to ask Is there a risk that intelligence is a complex global property? and then to follow that with a second question, namely If it is complex, then what impact would this have on the methodology of AGI?. The answers that I tried to bring out in that paper were that (1) there is a substantial risk that all intelligent systems must be at least partially complex (reason: nobody seems to know how to build a complete intelligence without including a substantial dose of the kind of tangled mechanisms that almost always give rise to complexity), and (2) the impact on AGI methodology is potentially devastating, and (disturbingly) so subtle that it would be possible for a skeptic to deny it forever. The impact would be devastating because the current approach to AI, if applied to a situation in which the target was a complex system, would just run around in circles forever, always building systems that were kind of smart, but which did not scale up to the real thing, or which could only work if we hand-craft every piece of knowledge that the system uses, and so on. In fact, the predicted progress rate in AI research would show exactly the type of pattern that has existed for the last fifty years. As I said in another response to someone recently, all of the progress that has been made is essentially a result of AI researchers implictly using their own intuitions about how their minds work, while at the same time (mostly) denying that they are doing this. So, going back to your question. I do think that if intelligence is a (partially) complex global property, then it cannot be defined in a way that allows us to go from a definition to a prescription for a mechanism (i.e., we cannot simply set it up as an optimization problem). That is not the direct purpose of my argument, but it is corollary. Your second point is closer to the goal of my argument, but I would rephrase it to say that getting a real intelligence (an AGI) to work probably will require at least part of the system to have a disconnected relationship between global and local, so in that sense we would not be able to 'predict' the occurence of intelligence based on local properties. Remember the bottom line. My only goal is to ask how different methodologies would fare if intelligence is 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
From: Richard Loosemore Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). Richard Loosemore Well lets forget about your theory for a second. I think that an advanced AI program is going to have to be able to deal with complexity and that your analysis is certainly interesting and illuminating. But I want to make sure that I understand what you mean here. First of all, your statement, it is not possible to use analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. By analytic mathematics are you referring to numerical analysis, which the article in Wikipedia, http://en.wikipedia.org/wiki/Numerical_analysis describes as the study of algorithms for the problems of continuous mathematics (as distinguished from discrete mathematics). Because if you are saying that the study of continuous mathematics -as distinguished from discrete mathematics- cannot be used to represent discreet system complexity, then that is kind of a non-starter. It's a cop-out by initial definition. I am primarily interested in discreet programming ( I am, of course also interested in continuous systems as well), but in this discussion I was expressing my interest in measures that can be taken to simplify computational complexity. Again, Wikipedia gives a slightly more complex definition of complexity than you do. http://en.wikipedia.org/wiki/Complexity I am not saying that your particular definition of complexity is wrong, I only want to make sure that I understand what it is that you are getting at. The part of your sentence that read, ...given only the rules that determine the local mechanisms, sounds like it might well apply to the kind of system that I think would be necessary for a better AI program, but it is not necessarily true of all kinds of demonstrations of complexity (as I understand them). For example, consider a program that demonstrates the emergence of complex behaviors from collections of objects that obey simple rules that govern their interactions. One can use a variety of arbitrary settings for the initial state of the program to examine how different complex behaviors may emerge in different environments. (I am hoping to try something like this when I buy my next computer with a great graphics chip in it.) This means that complexity does not have to be represented only in states that had been previously generated by the system, as can be obviously seen in the fact that initial states are a necessity of such systems. I think I get what you are saying about complexity in AI and the problems of research into AI that could be caused if complexity is the reality of advanced AI programming. But if you are throwing technical arguments at me, some of which are trivial from my perspective like the definition of, continuous mathematics (as distinguished from discrete mathematics), then all I can do is wonder why. Jim Bromer --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Jim Bromer wrote: From: Richard Loosemore Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). Richard Loosemore Well lets forget about your theory for a second. I think that an advanced AI program is going to have to be able to deal with complexity and that your analysis is certainly interesting and illuminating. But I want to make sure that I understand what you mean here. First of all, your statement, it is not possible to use analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. By analytic mathematics are you referring to numerical analysis, which the article in Wikipedia, http://en.wikipedia.org/wiki/Numerical_analysis describes as the study of algorithms for the problems of continuous mathematics (as distinguished from discrete mathematics). Because if you are saying that the study of continuous mathematics -as distinguished from discrete mathematics- cannot be used to represent discreet system complexity, then that is kind of a non-starter. It's a cop-out by initial definition. I am primarily interested in discreet programming ( I am, of course also interested in continuous systems as well), but in this discussion I was expressing my interest in measures that can be taken to simplify computational complexity. Again, Wikipedia gives a slightly more complex definition of complexity than you do. http://en.wikipedia.org/wiki/Complexity I am not saying that your particular definition of complexity is wrong, I only want to make sure that I understand what it is that you are getting at. The part of your sentence that read, ...given only the rules that determine the local mechanisms, sounds like it might well apply to the kind of system that I think would be necessary for a better AI program, but it is not necessarily true of all kinds of demonstrations of complexity (as I understand them). For example, consider a program that demonstrates the emergence of complex behaviors from collections of objects that obey simple rules that govern their interactions. One can use a variety of arbitrary settings for the initial state of the program to examine how different complex behaviors may emerge in different environments. (I am hoping to try something like this when I buy my next computer with a great graphics chip in it.) This means that complexity does not have to be represented only in states that had been previously generated by the system, as can be obviously seen in the fact that initial states are a necessity of such systems. I think I get what you are saying about complexity in AI and the problems of research into AI that could be caused if complexity is the reality of advanced AI programming. But if you are throwing technical arguments at me, some of which are trivial from my perspective like the definition of, continuous mathematics (as distinguished from discrete mathematics), then all I can do is wonder why. Jim, With the greatest of respect, this is a topic that will require some extensive background reading on your part, because the misunderstandings in your above test are too deep for me to remedy in the scope of one or two list postings. For example, my reference to analytic mathematics has nothing at all to do with the wikipedia entry you found, alas. The word has many uses, and the one I am employing is meant to point up a distinction between classical mathematics that allows equations to be solved algebraically, and experimental mathematics that solves systems by simulation. Analytic means by analysis in this context...but this is a very abstract sense of the word that I am talking about here, and it is very hard to convey. This topic is all about 'complex systems' which is a technical term that does not mean systems that are complicated (in the everyday sense of 'complicated'). To get up to speed on this, I recommend a popular science book called Complexity by Waldrop, although there was also a more recent book whose name I forget, which may be better. You could also read Wolfram's A New Kind of Science, but that is huge and does not come to the simple point very easily. I am happy to make an attempt to bridge the gap by answering questions, but you must begin with the understanding that this would be a dialog between someone who has been doing research in a field for over 25
Re: [agi] Approximations of Knowledge
Jim Bromer wrote: - Original Message From: Richard Loosemore Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). Richard Loosemore -- I don't feel that you are seriously interested in discussing the subject with me. Let me know if you ever change your mind. No, I am seriously interested in discussing the subject with you: I just explained a problem with the statement you made. If I was not interested in discussing, I would not have gone to that trouble. I suspect you are offended by my comment that I cannot make sense of what you say. This is just my honest reaction to what you wrote. 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Ah, so you do not accept AIXI either. Put this way, your complex system dilemma applies only to pure AGI, and not to any narrow AI attempts, no matter how ambitious. But I suppose other, totally different reasons (such as P != NP, if so) can block those. Is this the best way to understand your argument? Meaning, is the key idea intelligence is a complex global property, so we can't define it? If so, my original blog post is way of. My interpretation was more like intelligence is a complex global property, so we can't predict its occurring based on local properties. These are two very different arguments. Perhaps you are arguing both points? On Wed, Jun 25, 2008 at 6:20 PM, Richard Loosemore [EMAIL PROTECTED] wrote: [..] The confusion in our discussion has to do with the assumption you listed above: ...I am implicitly assuming that we have some exact definition of intelligence, so that we know what we are looking for... This is precisely what we do not have, and which we will quite possibly never have. [..] 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Loosemore said: But now ... suppose, ... that there do not exist ANY 3-sex cellular automata in which there are emergent patterns equivalent to the glider and glider gun. ...Conway ... can search through the entire space of 3-sex automata..., and he will never build a system that satisfies his requirement. This is the boxed-in corner that I am talking about. We decide that intelligence must be built with some choice of logical formalism, plus heuristics, and we assume that we can always keep jiggling the heuristics until the system as a whole shows a significant degree of intelligence. But there is nothing in the world that says that this is possible. ...mathematics cannot possibly tell you that this part of the space does not contain any solutions. That is the whole point of complex systems, n'est pas? No analysis will let you know what the global properties are without doing a brute force exploration of (simulations of) the system. But we can invent a 'mathematics' or a program that can. By understanding that a model is not perfect, and recognizing that references may not mesh perfectly, a program can imagine other possibilities and these possibilities can be based on complex interrelations built between feasible strands. Approximations do not need to be limited to weighted expressions, general vagueness or something like that. From this point it is just a matter of devising a 'mathematical' - a programmed - system to discover actual feasibilities. The Game of Life did not solve the contemporary problem of AI because it was biased to create a chain of progression and it wasted the memory of those results that did not immediately result in a payoff but may have fit into other developments. And it did not explore the relative reduction space. The reconciliation between the study of possible splices of previously seen chains of products and empirical feasibility may be an open ended process but it could be governed by a program. It may be AI-complete but the sub tasks to run a search from imaginative feasibility to empirical feasibility can be governed by logic (even though it would be open ended AI-complete search.) I agree with what you are saying in the broader sense, but I do believe that the research problem could be governed by a logical system, although it would require a great many resources to search the Cantorian diagonal infinities space of possible arrangements of relative reductions. Relative reduction means that in order to discover the nature of certain mathematical problems we may (usually) have to use reductionism to discover all of the salient features that would be necessary to create a mathematical algorithm to produce the range of desired outputs. But the system of reductionist methods has to be relative to the features of the system; a set of elements cannot be taken for granted, you have to discover the pseudo-elements (or relative elements) of the system relative to the features of the problem. Jim Bromer - Original Message From: Richard Loosemore [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Tuesday, June 24, 2008 9:02:31 PM Subject: Re: [agi] Approximations of Knowledge Abram Demski wrote: I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... And at that point, your lab and my lab are essentially starting to do the same thing. You need to start searching the space of possible heuristics in a systematic way, rather than just pick a hunch and go with it. The problem, though, is that you might already have gotten yourself into a You Can't Get There By Starting From Here situation. Suppose your choice of basic logical formalism, and knowledge representation format (and the knowledge acquisition methods that MUST come along with that formalism) has boxed you into a corner in which there does not exist any choice of heuristic control mechanism that will get your system up into human-level intelligence territory? If the underlying search space was sufficiently general, we are OK, there is no way to get boxed in except by the heuristic. Wait: we are not talking about the same thing here. Analogous situation. Imagine that John Horton Conway is trying to invent a cellular automaton with particular characteristics - say, he has already decided that the basic rules MUST show the global characteristic of having a thing like a glider and a thing like a glider gun. (This is equivalent to us saying that we want to build a system that has the particular characteristics that we colloquially call 'intelligence', and we will do it with a system that is complex). But now
Re: [agi] Approximations of Knowledge
Jim Bromer wrote: Loosemore said: But now ... suppose, ... that there do not exist ANY 3-sex cellular automata in which there are emergent patterns equivalent to the glider and glider gun. ...Conway ... can search through the entire space of 3-sex automata..., and he will never build a system that satisfies his requirement. This is the boxed-in corner that I am talking about. We decide that intelligence must be built with some choice of logical formalism, plus heuristics, and we assume that we can always keep jiggling the heuristics until the system as a whole shows a significant degree of intelligence. But there is nothing in the world that says that this is possible. ...mathematics cannot possibly tell you that this part of the space does not contain any solutions. That is the whole point of complex systems, n'est pas? No analysis will let you know what the global properties are without doing a brute force exploration of (simulations of) the system. But we can invent a 'mathematics' or a program that can. By understanding that a model is not perfect, and recognizing that references may not mesh perfectly, a program can imagine other possibilities and these possibilities can be based on complex interrelations built between feasible strands. Approximations do not need to be limited to weighted expressions, general vagueness or something like that. From this point it is just a matter of devising a 'mathematical' - a programmed - system to discover actual feasibilities. The Game of Life did not solve the contemporary problem of AI because it was biased to create a chain of progression and it wasted the memory of those results that did not immediately result in a payoff but may have fit into other developments. And it did not explore the relative reduction space. The reconciliation between the study of possible splices of previously seen chains of products and empirical feasibility may be an open ended process but it could be governed by a program. It may be AI-complete but the sub tasks to run a search from imaginative feasibility to empirical feasibility can be governed by logic (even though it would be open ended AI-complete search.) I agree with what you are saying in the broader sense, but I do believe that the research problem could be governed by a logical system, although it would require a great many resources to search the Cantorian diagonal infinities space of possible arrangements of relative reductions. Relative reduction means that in order to discover the nature of certain mathematical problems we may (usually) have to use reductionism to discover all of the salient features that would be necessary to create a mathematical algorithm to produce the range of desired outputs. But the system of reductionist methods has to be relative to the features of the system; a set of elements cannot be taken for granted, you have to discover the pseudo-elements (or relative elements) of the system relative to the features of the problem. Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
It seems as if we are beginning to talk past eachother. I think the problem may be that we have different implicit conceptions of the sort of AI being constructed. My implicit conception is that of an optimization problem. The AI is given the challenge of formulating the best response to its input that it can muster within real-world time constraints. This in some sense always a search problem; it just might be all heuristic, so that it doesn't look much like a search. In designing an AI, I am implicitly assuming that we have some exact definition of intelligence, so that we know what we are looking for. This makes the optimization problem well-defined: the search space is that of all possible responses to the input, and the utility function is our definition of intelligence. *Our* problem is to find (1) efficient optimal search strategies, and where that fails, (2) good heuristics. I'll admit that the general Conway analogy applies, because we are looking for heuristics with the property of giving good answers most of the time, and the math is sufficiently complicated as to be intractable in most cases. But your more recent variation, where Conway goes amiss, does not seem to be analogous? On Tue, Jun 24, 2008 at 9:02 PM, Richard Loosemore [EMAIL PROTECTED] wrote: Abram Demski wrote: I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... And at that point, your lab and my lab are essentially starting to do the same thing. You need to start searching the space of possible heuristics in a systematic way, rather than just pick a hunch and go with it. The problem, though, is that you might already have gotten yourself into a You Can't Get There By Starting From Here situation. Suppose your choice of basic logical formalism, and knowledge representation format (and the knowledge acquisition methods that MUST come along with that formalism) has boxed you into a corner in which there does not exist any choice of heuristic control mechanism that will get your system up into human-level intelligence territory? If the underlying search space was sufficiently general, we are OK, there is no way to get boxed in except by the heuristic. Wait: we are not talking about the same thing here. Analogous situation. Imagine that John Horton Conway is trying to invent a cellular automaton with particular characteristics - say, he has already decided that the basic rules MUST show the global characteristic of having a thing like a glider and a thing like a glider gun. (This is equivalent to us saying that we want to build a system that has the particular characteristics that we colloquially call 'intelligence', and we will do it with a system that is complex). But now Conway boxes himself into a corner: he decides, a priori, that the cellular automaton MUST have three sexes, instead of the two sexes that we are familiar with in Game of Life. So three states for every cell. But now (we will suppose, for the sake of the argument), it just happens to be the case that there do not exist ANY 3-sex cellular automata in which there are emergent patterns equivalent to the glider and glider gun. Now, alas, Conway is up poop creek without an instrument of propulsion - he can search through the entire space of 3-sex automata until the end of the universe, and he will never build a system that satisfies his requirement. This is the boxed-in corner that I am talking about. We decide that intelligence must be built with some choice of logical formalism, plus heuristics, and we assume that we can always keep jiggling the heuristics until the system as a whole shows a significant degree of intelligence. But there is nothing in the world that says that this is possible. We could be in exactly the same system as our hypothetical Conway, trying to find a solution in a part of the space of all possible systems in which there do not exist any solutions. The real killer is that, unlike the example you mention below, mathematics cannot possibly tell you that this part of the space does not contain any solutions. That is the whole point of complex systems, n'est pas? No analysis will let you know what the global properties are without doing a brute force exploration of (simulations of) the system. Richard Loosemore This is what the mathematics is good for. An experiment, I think, will not tell you this, since a formalism can cover almost everything but not everything. For example, is a given notation for functions Turing-complete, or merely primitive recursive? Primitive recursion is amazingly expressive, so I think it would be easy to be fooled. But a proof of Turing-completeness will suffice.
RE: [agi] Approximations of Knowledge
Richard, If I can make a guess at where Jim is coming from: Clearly, intelligent systems CAN be produced. Assuming we can define intelligent system well enough to recognize it, we can generate systems at random until one is found. That is impractical, however. So, we can look at the problem as one of search optimization. Evolution produced intelligent systems through a biased search, for example, so it is at least possible to improve search over completely random generate and test. What other ways can be used to speed up search? Jim is suggesting some methods that he believes may help. If I understand what you've said about your approach, you have some very different methods than what he is proposing to focus the search. I do not understand exactly what Jim is proposing; presumably he is aiming to use his SAT solver to guide the search toward areas that contain partial solutions or promising partial models of some sort. It seems to me very difficult to define the goal formally, very difficult to develop a meta system in which a sufficiently broad class of candidate systems can be expressed, and very difficult to describe the splices or reductions or partial models in such a way to smooth the fitness landscape and thus speed up search. So I don't know how practical such a plan is. But (again assuming I understand Jim's approach) it avoids your complex system arguments because it is not making any effort to predict global behavior from the low-level system components, it's just searching through possibilities. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Jim, On 6/24/08, Jim Bromer [EMAIL PROTECTED] wrote: Although I do suffer from an assortment of biases, I would not get worried to see any black man walking behind me at night. For example, if I saw Andrew Young or Bill Cosby walking behind me I don't think I would be too worried. However, you would have to look very carefully to identify these people with confidence. Why would you bother to look so carefully? Obviously, because of some sense of alarm. Or, if I was walking out of a campus library and a young black man carrying some books was walking behind me, Again, you would have to look carefully enough to verify age, and that the books weren't bound together with a belt or rope so they could be used as a weapon. Again, why would you bother to look so carefully? Obviously again, because of some sense of alarm. I would not be too worried about that either. OK, so you have eliminated ~1% of the cases. How about the other 99% of the cases? Your statement was way over the line, and it showed some really bad judgment. Apparently you don't follow the news very well. My statement was an obvious paraphrase from a fairly recent statement made by Rev Jesse Jackson, who says that HE gets worried when a black man is walking behind him. Perhaps I should have attributed my statement for those who don't follow the news. I think that if he gets worried, that the rest of us should also pay some attention. However, your comment broadly dismissing what I said (reason for possible alarm) based on some narrow possible exceptions (which would only be carefully verified *BECAUSE* of such alarm) does indeed show that your thinking is quite clouded and wound around the axle of PC (Political Correctness), and hence we shouldn't be expecting any new ideas from you anytime soon. The message here that you will probably still completely miss, but which hopefully other readers here will get, is that even bright people like you are UNABLE to program AGIs, or to state non-dangerous goals, or even to recognize obvious dangers. The whole concept of human guidance is SO deeply flawed that I see no hope of it ever working in any useful way. Not in this century or the next. Again, for the umpteenth time, and ANYONE here bothered yet to read the REST of the Colossus trilogy that started with *The Forbin Project* movie? If we are going to rehash issues that have already been written about, it would sure be nice to fast-forward over past writings. Steve Richfield = - Original Message From: Steve Richfield [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, June 23, 2008 10:53:07 PM Subject: Re: [agi] Approximations of Knowledge Andy, This is a PERFECT post, because it so perfectly illustrates a particular point of detachment from reality that is common among AGIers. In the real world we do certain things to achieve a good result, but when we design politically correct AGIs, we banish the very logic that allows us to function. For example, if you see a black man walking behind you at night, you rightly worry, but if you include that in your AGI design, you would be dismissed as a racist. Effectively solving VERY VERY difficult problems, like why a particular corporation is failing after other experts have failed, is a multiple-step process that starts with narrowing down the vast field of possibilities. As others have already pointed out here, this is often done in a rather summary and non-probabilistic way. Perhaps all of the really successful programmers that you have known have had long hair, so if the programming is failing and the programmer has short hair, then maybe there is an attitude issue to look into. Of course this does NOT necessarily mean that there is any linkage at all - just another of many points to focus some attention to. Similarly, over the course of 100 projects I have developed a long list of rules that help me find the problems with a tractable amount of effort. No, I don't usually tell others my poorly-formed rules because they prove absolutely NOTHING, only focus further effort. I have a special assortment of rules to apply whenever God is mentioned. After all, not everyone thinks that God has the same motivations, so SOME approach is needed to paradigm shift one person's statements to be able to be understood by another person. The posting you responded to was expressing one such rule. That having been said... On 6/22/08, J. Andrew Rogers [EMAIL PROTECTED] wrote: Somewhere in the world, there is a PhD chemist and a born-again Christian on another mailing list ...the project had hit a serious snag, and so the investors brought in a consultant that would explain why the project was broken by defectively reasoning about dubious generalizations he pulled out of his ass... Of course I don't make any such (I freely admit to dubious) generalizations to investors. However, I immediately drill down to find out
Re: [agi] Approximations of Knowledge
Abram Demski wrote: It seems as if we are beginning to talk past eachother. I think the problem may be that we have different implicit conceptions of the sort of AI being constructed. My implicit conception is that of an optimization problem. The AI is given the challenge of formulating the best response to its input that it can muster within real-world time constraints. This in some sense always a search problem; it just might be all heuristic, so that it doesn't look much like a search. In designing an AI, I am implicitly assuming that we have some exact definition of intelligence, so that we know what we are looking for. This makes the optimization problem well-defined: the search space is that of all possible responses to the input, and the utility function is our definition of intelligence. *Our* problem is to find (1) efficient optimal search strategies, and where that fails, (2) good heuristics. I'll admit that the general Conway analogy applies, because we are looking for heuristics with the property of giving good answers most of the time, and the math is sufficiently complicated as to be intractable in most cases. But your more recent variation, where Conway goes amiss, does not seem to be analogous? The confusion in our discussion has to do with the assumption you listed above: ...I am implicitly assuming that we have some exact definition of intelligence, so that we know what we are looking for... This is precisely what we do not have, and which we will quite possibly never have. The reason? If existing intelligent systems are complex systems, then when we look at one of them and say That is my example of what is meant by 'intelligence', we are pointing at a global property of a complex system. If anyone thinks that the intelligence of existing intelligent systems is completely independent of all complex global properties of the system, the ball is in their court: they must somehow show good reason for us to believe that this is the case - and so far in the history of philosophy, psychology and AI, nobody has ever come close to showing such a thing. In other words, nobody can give a non-circular, practical definition that is demonstrably identical to the definition of intelligence in natural systems. All the evidence (the tangled nature of the mechanisms that appear to be necessary to build an intelligence) points to the fact that intelligence is likely to be a complex global property. Now, if intelligence *is* a global property of a complex system, it will not be possible to simply write down a clear definition of it and then optimize. That is the point of the Conway analogy: we would be in the same boat that he was. So, in a way, when you wrote down that assumption, what you did was iimplictly assert that human level intelligence can definitely be achieved without needing to do it with a system that is complex. That is an extremely strong assertion, and unfortunately there is no evidence (except the intuition of some people) that this is a valid assumption. Quite the contrary, all the evidence appears to point the other way. So that one statement is really the crunch point. All the rest is downhill from that point on. Richard Loosemore On Tue, Jun 24, 2008 at 9:02 PM, Richard Loosemore [EMAIL PROTECTED] wrote: Abram Demski wrote: I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... And at that point, your lab and my lab are essentially starting to do the same thing. You need to start searching the space of possible heuristics in a systematic way, rather than just pick a hunch and go with it. The problem, though, is that you might already have gotten yourself into a You Can't Get There By Starting From Here situation. Suppose your choice of basic logical formalism, and knowledge representation format (and the knowledge acquisition methods that MUST come along with that formalism) has boxed you into a corner in which there does not exist any choice of heuristic control mechanism that will get your system up into human-level intelligence territory? If the underlying search space was sufficiently general, we are OK, there is no way to get boxed in except by the heuristic. Wait: we are not talking about the same thing here. Analogous situation. Imagine that John Horton Conway is trying to invent a cellular automaton with particular characteristics - say, he has already decided that the basic rules MUST show the global characteristic of having a thing like a glider and a thing like a glider gun. (This is equivalent to us saying that we want to build a system that has the particular characteristics that we colloquially call 'intelligence', and we will do it with a system that is
Re: [agi] Approximations of Knowledge
Derek Zahn wrote: Richard, If I can make a guess at where Jim is coming from: Clearly, intelligent systems CAN be produced. Assuming we can define intelligent system well enough to recognize it, we can generate systems at random until one is found. That is impractical, however. So, we can look at the problem as one of search optimization. Evolution produced intelligent systems through a biased search, for example, so it is at least possible to improve search over completely random generate and test. What other ways can be used to speed up search? Jim is suggesting some methods that he believes may help. If I understand what you've said about your approach, you have some very different methods than what he is proposing to focus the search. I do not understand exactly what Jim is proposing; presumably he is aiming to use his SAT solver to guide the search toward areas that contain partial solutions or promising partial models of some sort. It seems to me very difficult to define the goal formally, very difficult to develop a meta system in which a sufficiently broad class of candidate systems can be expressed, and very difficult to describe the splices or reductions or partial models in such a way to smooth the fitness landscape and thus speed up search. So I don't know how practical such a plan is. But (again assuming I understand Jim's approach) it avoids your complex system arguments because it is not making any effort to predict global behavior from the low-level system components, it's just searching through possibilities. I hear what you say here, but the crucial issue is defining this thing called intelligence. And, in the end, that is where the complex systems argument makes itself felt (so this is not really avoiding the complex systems problem, but just hiding it). Let me explain these thoughts. If we really could only define 'intelligent system' well enough to recognize it then the generate and test you are talking about would be extremely blind ... we would not make any specific design decisions, but generate completely random systems and say Is this one intelligent? each time we built one. Clearly, that would be ridiculously slow (as you point out). Even the evolutionary biassed search - in which you build simple systems and gradually elaborate them as you test them in combat - would still take a few billion years and a planet-sized computer. But then you introduce the idea of speeding up the search in some way. Ahhh... now there's the rub. To make the search more efficient, you have to have some idea of an error function: you look at the intelligence of the current best try, and you feed that into a function that suggests what kind of changes in the low-level mechanisms will give rise to a *beneficial* change in the overall intelligence (an improvement, i.e.). To do any better than random, you really must have an error function this almost the very definition of doing a search that is not random, no? You have to have some idea of how a change in design will cause a change in high level behavior, and that is the error function. If the system you are talking about is not complex, then, no problem: an error function is findable, at least in principle. But the very definition of a complex system is that such an error function cannot (absolutely cannot) be found. You cannot say, I need to improve the overall intelligence, *thus*, and THEREFORE I will make this change in the local mechanisms, because I have reason to believe that such a global change will be effected by this local change. That is the one statement about a complex system that is verboten. So it is that one quiet little statement about finding better ways to do the search that brings down the whole argument. If intelligent systems can be built without making them complex, all well and good. But if that is not possible (and the evidence indicates that it is not), then you must be very careful not to set up a research methodology in which you make the assumption that you are going to adjust the low level mechanisms in a way that will 'improve' the global performance in a desired way. If anyone does include that implicit assumption in their methodology, they are unknowingly inserting a And Then A Miracle Happens Here step. I shouold quickly add one comment about that last paragraph. AI researchers clearly do do exactly what i have just said is impossible! They frequently look at the poor performance of an AI system and say I think a change in this mechanism will improve things ... and then, sure enough, they do get an improvement. So does that mean my argument that there is a complex systems problem just wrong? No: I have clearly said (though many people have missed this point I think) that what AI researchers have been doing is implicitly using their understanding of human psychology (of their own minds, for the most part) to get ideas for how
Re: [agi] Approximations of Knowledge
- Original Message From: Richard Loosemore Jim, I'm sorry: I cannot make any sense of what you say here. I don't think you are understanding the technicalities of the argument I am presenting, because your very first sentence... But we can invent a 'mathematics' or a program that can is just completely false. In a complex system it is not possible to used analytic mathematics to predict the global behavior of the system given only the rules that determine the local mechanisms. That is the very definition of a complex system (note: this is a complex system in the technical sense of that term, which does not mean a complicated system in ordinary language). Richard Loosemore -- I don't feel that you are seriously interested in discussing the subject with me. Let me know if you ever change your mind. Jim Bromer --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
On 6/23/08, J. Andrew Rogers [EMAIL PROTECTED] wrote: Or it could simply mean that the vast majority of programmers and software monkeys are mediocre at best such that the handful of people you will meet with deep talent won't constitute a useful sample size. Hell, even Brooks suggested as much and he was charitable. In all my years in software, I've only met a small number of people who were unambiguously wicked smart when it came to software, and while none of them could be confused with a completely mundane person they also did not have many other traits in common (though I will acknowledge they tend to rational and self-analytical to a degree that is rare in most people though this is not a trait exclusive to these people). Of course, *my* sample size is also small and so it does not count for much. I completely agree with all of the above, though it says nothing relevant to the point that I was trying to make. That point was that we and presumably our AGIs will use our experience to focus inquiry in complex situations. That these focused efforts fail more often than they succeed is good, compared with the disastrous alternative of failing 99.99% of the time because our inquiries are NOT focused. Again, as you apparently missed it on my previous email - what would you suggest as an alternative? Similarly, over the course of 100 projects... Eh? Over 100 projects? These were either very small projects or you are older than Methuselah. Both are correct. Also, I had many fewer employers, as I had a LOT of repeat business. These would sometimes bring me in for a couple of weeks of shock treatment when they felt it was needed. Steve Richfield --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Although I do suffer from an assortment of biases, I would not get worried to see any black man walking behind me at night. For example, if I saw Andrew Young or Bill Cosby walking behind me I don't think I would be too worried. Or, if I was walking out of a campus library and a young black man carrying some books was walking behind me, I would not be too worried about that either. Your statement was way over the line, and it showed some really bad judgment. Jim Bromer - Original Message From: Steve Richfield [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, June 23, 2008 10:53:07 PM Subject: Re: [agi] Approximations of Knowledge Andy, This is a PERFECT post, because it so perfectly illustrates a particular point of detachment from reality that is common among AGIers. In the real world we do certain things to achieve a good result, but when we design politically correct AGIs, we banish the very logic that allows us to function. For example, if you see a black man walking behind you at night, you rightly worry, but if you include that in your AGI design, you would be dismissed as a racist. Effectively solving VERY VERY difficult problems, like why a particular corporation is failing after other experts have failed, is a multiple-step process that starts with narrowing down the vast field of possibilities. As others have already pointed out here, this is often done in a rather summary and non-probabilistic way. Perhaps all of the really successful programmers that you have known have had long hair, so if the programming is failing and the programmer has short hair, then maybe there is an attitude issue to look into. Of course this does NOT necessarily mean that there is any linkage at all - just another of many points to focus some attention to. Similarly, over the course of 100 projects I have developed a long list of rules that help me find the problems with a tractable amount of effort. No, I don't usually tell others my poorly-formed rules because they prove absolutely NOTHING, only focus further effort. I have a special assortment of rules to apply whenever God is mentioned. After all, not everyone thinks that God has the same motivations, so SOME approach is needed to paradigm shift one person's statements to be able to be understood by another person. The posting you responded to was expressing one such rule. That having been said... On 6/22/08, J. Andrew Rogers [EMAIL PROTECTED] wrote: Somewhere in the world, there is a PhD chemist and a born-again Christian on another mailing list ...the project had hit a serious snag, and so the investors brought in a consultant that would explain why the project was broken by defectively reasoning about dubious generalizations he pulled out of his ass... Of course I don't make any such (I freely admit to dubious) generalizations to investors. However, I immediately drill down to find out exactly why THEY SAY that they didn't stop and reconsider their direction when it should have been obvious that things had gone off track. When I hear about how God just couldn't have led them astray, I quote what they said in my report and suggest that perhaps the problem is that God isn't also underwriting the investment with limitless funds. How would YOU (or your AGI) handle such situations? Would you (or your AGI) ignore past empirical evidence because of lack of proof or political incorrectness? Steve Richfield agi | Archives | Modify Your Subscription --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
And Abram said, A revised version of my argument would run something like this. As the approximation problem gets more demanding, it gets more difficult to devise logical heuristics. Increasingly, we must rely on intuitions tested by experiments. There then comes a point when making the distinction between the heuristic and the underlying search becomes unimportant; the method is all heuristic, so to speak. At this point we are simply using messy methods, I wondered if Abram was talking about the way an AI program should work or the way research into AI should work, or the way AI programs and research into AI should work? Jim Bromer The passage quoted above was intended to reflect a necessary progression as we design AIs for more and more demanding tasks, as if some hypothetical researcher started with a narrow AI and was attempting to generalize it. Of course, people on this list will be more prone to try starting at the AGI end of the spectrum without going through the progression. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... And at that point, your lab and my lab are essentially starting to do the same thing. You need to start searching the space of possible heuristics in a systematic way, rather than just pick a hunch and go with it. The problem, though, is that you might already have gotten yourself into a You Can't Get There By Starting From Here situation. Suppose your choice of basic logical formalism, and knowledge representation format (and the knowledge acquisition methods that MUST come along with that formalism) has boxed you into a corner in which there does not exist any choice of heuristic control mechanism that will get your system up into human-level intelligence territory? If the underlying search space was sufficiently general, we are OK, there is no way to get boxed in except by the heuristic. This is what the mathematics is good for. An experiment, I think, will not tell you this, since a formalism can cover almost everything but not everything. For example, is a given notation for functions Turing-complete, or merely primitive recursive? Primitive recursion is amazingly expressive, so I think it would be easy to be fooled. But a proof of Turing-completeness will suffice. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Abram Demski wrote: I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... And at that point, your lab and my lab are essentially starting to do the same thing. You need to start searching the space of possible heuristics in a systematic way, rather than just pick a hunch and go with it. The problem, though, is that you might already have gotten yourself into a You Can't Get There By Starting From Here situation. Suppose your choice of basic logical formalism, and knowledge representation format (and the knowledge acquisition methods that MUST come along with that formalism) has boxed you into a corner in which there does not exist any choice of heuristic control mechanism that will get your system up into human-level intelligence territory? If the underlying search space was sufficiently general, we are OK, there is no way to get boxed in except by the heuristic. Wait: we are not talking about the same thing here. Analogous situation. Imagine that John Horton Conway is trying to invent a cellular automaton with particular characteristics - say, he has already decided that the basic rules MUST show the global characteristic of having a thing like a glider and a thing like a glider gun. (This is equivalent to us saying that we want to build a system that has the particular characteristics that we colloquially call 'intelligence', and we will do it with a system that is complex). But now Conway boxes himself into a corner: he decides, a priori, that the cellular automaton MUST have three sexes, instead of the two sexes that we are familiar with in Game of Life. So three states for every cell. But now (we will suppose, for the sake of the argument), it just happens to be the case that there do not exist ANY 3-sex cellular automata in which there are emergent patterns equivalent to the glider and glider gun. Now, alas, Conway is up poop creek without an instrument of propulsion - he can search through the entire space of 3-sex automata until the end of the universe, and he will never build a system that satisfies his requirement. This is the boxed-in corner that I am talking about. We decide that intelligence must be built with some choice of logical formalism, plus heuristics, and we assume that we can always keep jiggling the heuristics until the system as a whole shows a significant degree of intelligence. But there is nothing in the world that says that this is possible. We could be in exactly the same system as our hypothetical Conway, trying to find a solution in a part of the space of all possible systems in which there do not exist any solutions. The real killer is that, unlike the example you mention below, mathematics cannot possibly tell you that this part of the space does not contain any solutions. That is the whole point of complex systems, n'est pas? No analysis will let you know what the global properties are without doing a brute force exploration of (simulations of) the system. Richard Loosemore This is what the mathematics is good for. An experiment, I think, will not tell you this, since a formalism can cover almost everything but not everything. For example, is a given notation for functions Turing-complete, or merely primitive recursive? Primitive recursion is amazingly expressive, so I think it would be easy to be fooled. But a proof of Turing-completeness will suffice. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Abram Demski wrote: To be honest, I am not completely satisfied with my conclusion on the post you refer to. I'm not so sure now that the fundamental split between logical/messy methods should occur at the line between perfect approximate methods. This is one type of messiness, but one only. I think you are referring to a related but different messiness: not knowing what kind of environment your AI is dealing with. Since we don't know which kinds of models will fit best with the world, we should (1) trust our intuitions to some extent, and (2) try things and see how well they work. This is as Loosemore suggests. On the other hand, I do not want to agree with Loosemore too strongly. Mathematics and mathematical proof is a very important tool, and I feel like he wants to reject it. His image of an AGI seems to be a system built up out of totally dumb pieces, with intelligence emerging unexpectedly. Mine is a system built out of somewhat smart pieces, cooperating to build somewhat smarter pieces, and so on. Each piece has provable smarts. Okay, let me try to make some kind of reply to your comments here and in your original blog post. It is very important to understand that the paper I wrote was about the methodology of AGI research, not about specific theories/models/systems within AGI. It is about the way that we come up with ideas for systems and the way that we explore those systems, not about the content of anyone's particular ideas. So, in the above text you refer to a split between logical and messy methods - now, it may well be that my paper would lead someone to embrace 'messy' methods and reject 'logical' ones, but that is a side effect of the argument, not the argument itself. It does happen to be the case that I believe that logic-based methods are mistaken, but I could be wrong about that, and it could turn out that the best way to build an AGI is with a completely logic-based AGI, along with just one small mechanism that was Complex. That would be perfectly consistent with my argument (though a little surprising, for other reasons). Similarly, you suggest that I have an image of an AGI that is built out of totally dumb pieces, with intelligence emerging unexpectedly. Some people have suggested that that is my view of AGI, but whether or not those people are correct in saying that [aside: they are not!], that does not relate to the argument I presented, because it is all about specific AGI design preferences, whereas the thing that I have called the Complex Systems Problem is fairly neutral on most design decisions. In your original blog post, also, you mention the way that AGI planning mechanisms can be built in such a way that they contain a logical substrate, but with heuristics that force the systems to make 'sub-optimal' choices. This is a specific instance of a more general design pattern: logical engines that have 'inference control mechanisms' riding on their backs, preventing them from deducing everything in the universe whilst trying to come to a simple decision. The problem is that you have portrayed the distinction between 'pure' logical mechanisms and 'messy' systems that have heuristics riding on their backs, as equivalent to a distinction that you thought I was making between non-complex and complex AGI systems. I hope you can see now that this is not what I was trying to argue. My target would be the methodologies that people use to decide such questions as which heuristics to using in a planning mechanism, whether the representation used by the planning mechanism can co-exist with the learning mechanisms, and so on. Now, having said all of that, what does the argument actually say, and does it make *any* claims at all about what sort of content to put in an AGI design? The argument says that IF intelligent systems belong to the 'complex systems' class, THEN a it would be a dreadful mistake to use a certain type of scientific or engineering approach to build intelligent systems. I tried to capture this with an analogy at one point: if you we John Horton Conway, sitting down on Day 1 of his project to find a cellular automaton with certain global properties, you would not be able to use any standard scientific, engineering or mathematical tools to discover the rules that should go into your system - you would, in fact, have no option but to try rules at random until you found rules that gave the global behavior that you desired. My point was that a modified form of that same problem (that inability to use our scientific intuitions to just go from a desired global behavior to the mechanisms that will generate that global behavior) could apply to the question of building an AGI. I do not suggest that the problem will manifest itself in exactly the same way (it is not that we would make zero progress with current techniques, and have to use completely random trial and error, like Conway had to), but
Re: [agi] Approximations of Knowledge
Since combinatorial search problems are so common to artificial intelligence, it has obvious applications. If such an algorithm can be made, it seems like it could be used *everywhere* inside an AGI: deduction (solve for cases consistent with constraints), induction (search for the best model), planning... Particularly if there is a generalization to soft constraint problems. On 6/22/08, Jim Bromer [EMAIL PROTECTED] wrote: Abram, I did not group you with probability buffs. One of the errors I feel that writers make when their field is controversial is that they begin representing their own opinions from the vantage of countering critics. Unfortunately, I am one of those writers, (or perhaps I am just projecting). But my comment about the probability buffs wasn't directed toward you, I was just using it as an exemplar (of something or another). Your comments seem to make sense to me although I don't know where you are heading. You said: what should be hoped for is convergence to (nearly) correct models of (small parts of) the universe. So I suppose that rather than asking for meaning in a fuzzy logic, I should be asking for clear accounts of convergence properties... When you have to find a way to tie together components of knowledge together you typically have to achieve another kind of convergence. Even if these 'components' of knowledge are reliable, they cannot usually be converged easily due to the complexity that their interrelations with other kinds of knowledge (other 'components' of knowledge) will cause. To follow up on what I previously said, if my logic program works it will mean that I can combine and test logical formulas of up to a few hundred distinct variables and find satisfiable values for these combinations in a relatively short period of time. I think this will be an important method to test whether AI can be advanced by advancements in handling complexity even though some people do not feel that logical methods are appropriate to use on multiple source complexity. As you seem to appreciate, logic can still be brought to to the field even though it is not a purely logical game that is to be played. When I begin to develop some simple theories about a subject matter, I will typically create hundreds of minor variations concerning those theories over a period of time. I cannot hold all those variations of the conjecture in consciousness at any one moment, but I do feel that they can come to mind in response to a set of conditions for which that particular set of variations was created for. So while a simple logical theory (about some subject) may be expressible with only a few terms, when you examine all of the possible variations that can be brought into conscious consideration in response to a particular set of stimuli, I think you may find that the theories could be more accurately expressed using hundreds of distinct logical values. If this conjecture of mine turns out to be true, and if I can actually get my new logical methods to work, then I believe that this new range of logical methods may show whether advancements in complexity can make a difference to AI even if its application does not immediately result in human level of intelligence. Jim Bromer - Original Message From: Abram Demski [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Sunday, June 22, 2008 4:38:02 PM Subject: Re: [agi] Approximations of Knowledge Well, since you found my blog, you probably are grouping me somewhat with the probability buffs. I have stated that I will not be interested in any other fuzzy logic unless it is accompanied by a careful account of the meaning of the numbers. You have stated that it is unrealistic to expect a logical model to reflect the world perfectly. The intuition behind this seems clear. Instead, what should be hoped for is convergence to (nearly) correct models of (small parts of) the universe. So I suppose that rather than asking for meaning in a fuzzy logic, I should be asking for clear accounts of convergence properties... but my intuition says that from clear meaning, everything else follows. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Thanks for the comments. My replies: It does happen to be the case that I believe that logic-based methods are mistaken, but I could be wrong about that, and it could turn out that the best way to build an AGI is with a completely logic-based AGI, along with just one small mechanism that was Complex. Logical methods are quite Complex. This was part of my point. Logical deduction in any sufficiently complicated formalism satisfies both types of global-local disconnect that I mentioned (undecidability, and computational irreducibility). If this were not the case, it seems your argument would be much less appealing. (In particular, there would be one less argument for the mind being complex; we could not say logic has some subset of the mind's capabilities; a brute-force theorem prover is a complex system; therefore the mind is probably a complex system.) Similarly, you suggest that I have an image of an AGI that is built out of totally dumb pieces, with intelligence emerging unexpectedly. Some people have suggested that that is my view of AGI, but whether or not those people are correct in saying that [aside: they are not!] Apologies. But your arguments do appear to point in that direction. In your original blog post, also, you mention the way that AGI planning The problem is that you have portrayed the distinction between 'pure' logical mechanisms and 'messy' systems that have heuristics riding on their backs, as equivalent to a distinction that you thought I was making between non-complex and complex AGI systems. I hope you can see now that this is not what I was trying to argue. You are right, this characterization is quite bad. I think that is part of what was making me uneasy about my conclusion. My intention was not that approximation should always equal a logical search with messy heuristics stacked upon it. In fact, I had two conflicting images in mind:use -A logical search with logical heuristics (such as greedy methods for NP-complete problems, which are guaranteed to be fairly near optimal) -A messy method (such as a neural net or swarm) that somehow gives you an answer without precise logic A revised version of my argument would run something like this. As the approximation problem gets more demanding, it gets more difficult to devise logical heuristics. Increasingly, we must rely on intuitions tested by experiments. There then comes a point when making the distinction between the heuristic and the underlying search becomes unimportant; the method is all heuristic, so to speak. At this point we are simply using messy methods. I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... Finally, I should mention one general misunderstanding about mathematics. This argument has a superficial similarity to Godel's theorem, but you should not be deceived by that. Godel was talking about formal deductive systems, and the fact that there are unreachable truths within such systems. My argument is about the feasibility of scientific discovery, when applied to systems of different sorts. These are two very different domains. I think it is fair to say that I accounted for this. In particular, I said: It's this second kind of irreducibility, computational irreducibility, that I see as more relevant to AI. (Actually, I do see Godel's theorem as relevant to AI; I should have been more specific and said relevant to AI's global-local disconnect.) --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Loosemore said, It is very important to understand that the paper I wrote was about the methodology of AGI research, not about specific theories/models/systems within AGI. It is about the way that we come up with ideas for systems and the way that we explore those systems, not about the content of anyone's particular ideas. And Abram said, A revised version of my argument would run something like this. As the approximation problem gets more demanding, it gets more difficult to devise logical heuristics. Increasingly, we must rely on intuitions tested by experiments. There then comes a point when making the distinction between the heuristic and the underlying search becomes unimportant; the method is all heuristic, so to speak. At this point we are simply using messy methods, I wondered if Abram was talking about the way an AI program should work or the way research into AI should work, or the way AI programs and research into AI should work? Jim Bromer - Original Message From: Abram Demski [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, June 23, 2008 3:11:16 PM Subject: Re: [agi] Approximations of Knowledge Thanks for the comments. My replies: It does happen to be the case that I believe that logic-based methods are mistaken, but I could be wrong about that, and it could turn out that the best way to build an AGI is with a completely logic-based AGI, along with just one small mechanism that was Complex. Logical methods are quite Complex. This was part of my point. Logical deduction in any sufficiently complicated formalism satisfies both types of global-local disconnect that I mentioned (undecidability, and computational irreducibility). If this were not the case, it seems your argument would be much less appealing. (In particular, there would be one less argument for the mind being complex; we could not say logic has some subset of the mind's capabilities; a brute-force theorem prover is a complex system; therefore the mind is probably a complex system.) Similarly, you suggest that I have an image of an AGI that is built out of totally dumb pieces, with intelligence emerging unexpectedly. Some people have suggested that that is my view of AGI, but whether or not those people are correct in saying that [aside: they are not!] Apologies. But your arguments do appear to point in that direction. In your original blog post, also, you mention the way that AGI planning The problem is that you have portrayed the distinction between 'pure' logical mechanisms and 'messy' systems that have heuristics riding on their backs, as equivalent to a distinction that you thought I was making between non-complex and complex AGI systems. I hope you can see now that this is not what I was trying to argue. You are right, this characterization is quite bad. I think that is part of what was making me uneasy about my conclusion. My intention was not that approximation should always equal a logical search with messy heuristics stacked upon it. In fact, I had two conflicting images in mind:use -A logical search with logical heuristics (such as greedy methods for NP-complete problems, which are guaranteed to be fairly near optimal) -A messy method (such as a neural net or swarm) that somehow gives you an answer without precise logic A revised version of my argument would run something like this. As the approximation problem gets more demanding, it gets more difficult to devise logical heuristics. Increasingly, we must rely on intuitions tested by experiments. There then comes a point when making the distinction between the heuristic and the underlying search becomes unimportant; the method is all heuristic, so to speak. At this point we are simply using messy methods. I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... Finally, I should mention one general misunderstanding about mathematics. This argument has a superficial similarity to Godel's theorem, but you should not be deceived by that. Godel was talking about formal deductive systems, and the fact that there are unreachable truths within such systems. My argument is about the feasibility of scientific discovery, when applied to systems of different sorts. These are two very different domains. I think it is fair to say that I accounted for this. In particular, I said: It's this second kind of irreducibility, computational irreducibility, that I see as more relevant to AI. (Actually, I do see Godel's theorem as relevant to AI; I should have been more specific and said relevant to AI's global-local disconnect.) --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member
Re: [agi] Approximations of Knowledge
Abram Demski wrote: Thanks for the comments. My replies: It does happen to be the case that I believe that logic-based methods are mistaken, but I could be wrong about that, and it could turn out that the best way to build an AGI is with a completely logic-based AGI, along with just one small mechanism that was Complex. Logical methods are quite Complex. This was part of my point. Logical deduction in any sufficiently complicated formalism satisfies both types of global-local disconnect that I mentioned (undecidability, and computational irreducibility). If this were not the case, it seems your argument would be much less appealing. (In particular, there would be one less argument for the mind being complex; we could not say logic has some subset of the mind's capabilities; a brute-force theorem prover is a complex system; therefore the mind is probably a complex system.) Okay, I made a mistake in my choice of words (I knew it when I wrote them, but neglected to go back and correct!). I did not mean to imply that I *require* some complexity in an AGI formalism, and that finding some complexity would be a good thing, end of story, problem solved, etc. So for example, you are correct to point out that most 'logical' systems do exhibit complexity, provided they do something realistically approximating intelligence. Instead, what I meant to say was that we are not setting up our research procedures to cope with the complexity. So, it might turn out that a good, robust AGI can be built with something like a regular logic-based formalism, BUT with just a few small aspects that are complex but unfortunately we are currently not able to discover what those complex parts should be like, because our current methodology is to use blind hunch and intuition (i.e. heuristics that look as though the will work). Going back to your planning system example, it might be the case that only one choice of heuristic control mechanism will actually make a given logical formalism converge on fully intelligent behavior, but there might be 10^100 choices of possible control mechanism, and our current method for searching through the possibilities is to use intuition to pick likely candidates. The point here is that a small amount of the factors that give rise to complexity can actualy have a massive effect on the behavior of the system, but people are today acting as if a small amount of complexity-inducing characteristics means a small amount of unpredictability in the behavior. This is simply not the case. Similarly, you suggest that I have an image of an AGI that is built out of totally dumb pieces, with intelligence emerging unexpectedly. Some people have suggested that that is my view of AGI, but whether or not those people are correct in saying that [aside: they are not!] Apologies. But your arguments do appear to point in that direction. In your original blog post, also, you mention the way that AGI planning The problem is that you have portrayed the distinction between 'pure' logical mechanisms and 'messy' systems that have heuristics riding on their backs, as equivalent to a distinction that you thought I was making between non-complex and complex AGI systems. I hope you can see now that this is not what I was trying to argue. You are right, this characterization is quite bad. I think that is part of what was making me uneasy about my conclusion. My intention was not that approximation should always equal a logical search with messy heuristics stacked upon it. In fact, I had two conflicting images in mind:use -A logical search with logical heuristics (such as greedy methods for NP-complete problems, which are guaranteed to be fairly near optimal) -A messy method (such as a neural net or swarm) that somehow gives you an answer without precise logic A revised version of my argument would run something like this. As the approximation problem gets more demanding, it gets more difficult to devise logical heuristics. Increasingly, we must rely on intuitions tested by experiments. There then comes a point when making the distinction between the heuristic and the underlying search becomes unimportant; the method is all heuristic, so to speak. At this point we are simply using messy methods. Ah, I agree completely here. We are taling about a Wag The Dog scenario, where everyone focusses on the pristine beauty of the logical formalism, but turns a blind eye to the (assumed-to-be) trivial heuristic control mechanisms but in the end it is the heuristic control mechanism that is responsible for almost all of the actual behavior. I'm still not really satisfied, though, because I would personally stop at the stage when the heuristic started to get messy, and say, The problem is starting to become AI-complete, so at this point I should include a meta-level search to find a good heuristic for me, rather than trying to hard-code one... And at that point,
Re: [agi] Approximations of Knowledge
Jim Bromer wrote: Loosemore said, It is very important to understand that the paper I wrote was about the methodology of AGI research, not about specific theories/models/systems within AGI. It is about the way that we come up with ideas for systems and the way that we explore those systems, not about the content of anyone's particular ideas. And Abram said, A revised version of my argument would run something like this. As the approximation problem gets more demanding, it gets more difficult to devise logical heuristics. Increasingly, we must rely on intuitions tested by experiments. There then comes a point when making the distinction between the heuristic and the underlying search becomes unimportant; the method is all heuristic, so to speak. At this point we are simply using messy methods, I wondered if Abram was talking about the way an AI program should work or the way research into AI should work, or the way AI programs and research into AI should work? Jim Bromer I interpreted him (see parallel post) to be referring still to the question of how to deal with planning systems, where there is a formalism (the logic substructure) which cannot be allowed to run its methods to completion (because they would take too long) and which therefore has to use approximation methods, or heuristics, to guess which are the most likely best planning choices. When the system is required to do more real-world-type performance (as in an AGI, rather than a narrow AI) it's behavior will be dominated by the heuristics. He then went on to talk about methodology: do we just use intuitions to pick heuristics, or do we make the methodology more systematic by engaging in automatic searches of the space of possible heuristics? My perspective on that question would back up one step: if it is a complex system we are dealing with, we should have been using systematic, automatic searches of the design space BEFORE, when we were choosing whether or not to do planning with a Logic+Heuristics design! But of course, that would be wildly, extravagantly infeasible. So, instead, I propose to start from a basic design that is as similar as possible to the human design, and then do our systematic, automatic search (of the space of mechanism-designs) in an outward direction from that human-cognition baseline. If intelligence involves even a small amount of complexity, it could well be that this is the only feasible way to ever get an intelligence up and running. Treat it, in other words, as a calculus of variations problem. 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Andy, This is a PERFECT post, because it so perfectly illustrates a particular point of detachment from reality that is common among AGIers. In the real world we do certain things to achieve a good result, but when we design politically correct AGIs, we banish the very logic that allows us to function. For example, if you see a black man walking behind you at night, you rightly worry, but if you include that in your AGI design, you would be dismissed as a racist. Effectively solving VERY VERY difficult problems, like why a particular corporation is failing after other experts have failed, is a multiple-step process that starts with narrowing down the vast field of possibilities. As others have already pointed out here, this is often done in a rather summary and non-probabilistic way. Perhaps all of the really successful programmers that you have known have had long hair, so if the programming is failing and the programmer has short hair, then maybe there is an attitude issue to look into. Of course this does NOT necessarily mean that there is any linkage at all - just another of many points to focus some attention to. Similarly, over the course of 100 projects I have developed a long list of rules that help me find the problems with a tractable amount of effort. No, I don't usually tell others my poorly-formed rules because they prove absolutely NOTHING, only focus further effort. I have a special assortment of rules to apply whenever God is mentioned. After all, not everyone thinks that God has the same motivations, so SOME approach is needed to paradigm shift one person's statements to be able to be understood by another person. The posting you responded to was expressing one such rule. That having been said... On 6/22/08, J. Andrew Rogers [EMAIL PROTECTED] wrote: Somewhere in the world, there is a PhD chemist and a born-again Christian on another mailing list ...the project had hit a serious snag, and so the investors brought in a consultant that would explain why the project was broken by defectively reasoning about dubious generalizations he pulled out of his ass... Of course I don't make any such (I freely admit to dubious) generalizations to investors. However, I immediately drill down to find out exactly why THEY SAY that they didn't stop and reconsider their direction when it should have been obvious that things had gone off track. When I hear about how God just couldn't have led them astray, I quote what they said in my report and suggest that perhaps the problem is that God isn't also underwriting the investment with limitless funds. How would YOU (or your AGI) handle such situations? Would you (or your AGI) ignore past empirical evidence because of lack of proof or political incorrectness? Steve Richfield --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
On Jun 23, 2008, at 7:53 PM, Steve Richfield wrote: Andy, The use of diminutives is considered rude in many parts of anglo- culture if the individual does not use it to identify themselves, though I realize it is common practice in some regions of the US. When in doubt, use the given form. This is a PERFECT post, because it so perfectly illustrates a particular point of detachment from reality that is common among AGIers. In the real world we do certain things to achieve a good result, but when we design politically correct AGIs, we banish the very logic that allows us to function. For example, if you see a black man walking behind you at night, you rightly worry, but if you include that in your AGI design, you would be dismissed as a racist. You have clearly confused me with someone else. Effectively solving VERY VERY difficult problems, like why a particular corporation is failing after other experts have failed, is a multiple-step process that starts with narrowing down the vast field of possibilities. As others have already pointed out here, this is often done in a rather summary and non-probabilistic way. Perhaps all of the really successful programmers that you have known have had long hair, so if the programming is failing and the programmer has short hair, then maybe there is an attitude issue to look into. Of course this does NOT necessarily mean that there is any linkage at all - just another of many points to focus some attention to. Or it could simply mean that the vast majority of programmers and software monkeys are mediocre at best such that the handful of people you will meet with deep talent won't constitute a useful sample size. Hell, even Brooks suggested as much and he was charitable. In all my years in software, I've only met a small number of people who were unambiguously wicked smart when it came to software, and while none of them could be confused with a completely mundane person they also did not have many other traits in common (though I will acknowledge they tend to rational and self-analytical to a degree that is rare in most people though this is not a trait exclusive to these people). Of course, *my* sample size is also small and so it does not count for much. Similarly, over the course of 100 projects... Eh? Over 100 projects? These were either very small projects or you are older than Methuselah. I've worked on a lot of projects, but nowhere near 100 and I was a consultant for many years. 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Abram Demski said: To be honest, I am not completely satisfied with my conclusion on the post you refer to. I'm not so sure now that the fundamental split between logical/messy methods should occur at the line between perfect approximate methods. This is one type of messiness, but one only. I think you are referring to a related but different messiness: not knowing what kind of environment your AI is dealing with. Since we don't know which kinds of models will fit best with the world, we should (1) trust our intuitions to some extent, and (2) try things and see how well they work... Mathematics and mathematical proof is a very important tool... Mine is a system built out of somewhat smart pieces, cooperating to build somewhat smarter pieces, and so on. Each piece has provable smarts. Mathematics can be extended to include new kinds of relations and systems. One of the problems I have had with AI-probability buffs is that there are other ways to deal with knowledge that is only partially understood and this kind of complexity can be extended to measurable quantities as well. Notice that economics is not just probability. There are measurable quantities in economics that are not based solely on the economics of money. We cannot make perfect decisions. However, we can often make fairly good decisions even when based on partial knowledge. A conclusion however, should not be taken as a reliable rule unless it has withstood numerous tests. These empirical tests of a conclusion usually cause them to be modified. Even a good conclusion will typically be modified by conditional variations after be extensively tested. That is the nature of expertise. Our conclusions are often only approximations, but they can contain unarticulated links to other possibilities that may indicate other ways of looking at the data or conditional variations to the base conclusion. Jim Bromer --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
On 6/21/08, I wrote: The major problem I have is that writing a really really complicated computer program is really really difficult. -- Steve Richfield replied: Jim, The ONLY rational approach to this (that I know of) is to construct an engine that develops and applies machine knowledge, wisdom, or whatever, and NOT write code yourself that actually deals with articles of knowledge/wisdom. - I agree with that, (assuming that I understand what you meant). -- Steve wrote: REALLY complex systems may require multi-level interpreters, where a low-level interpreter provides a pseudo-machine on which to program a really smart high-level interpreter, on which you program your AGI. In ~1970 I wrote an ALGOL/FORTRAN/BASIC compiler that ran in just 16K bytes this way. At the bottom was a pseudo-computer whose primitives were fundamental to compiling. That pseudo-machine was then fed a program to read BNF and make compilers, which was then fed a BNF description of my compiler, with the output being my compiler in pseudo-machine code. One feature of this approach is that for anything to work, everything had to work, so once past initial debugging, it worked perfectly! Contrast this with modern methods that consume megabytes and never work quite right. -- A compiler may be a useful tool to use in an advanced AI program (just as we all use compilers in our programming), but I don't feel that a compiler is a good basis for or a good metaphor for advanced AI. -- Steve wrote: The more complex the software, the better the design must be, and the more protected the execution must be. You can NEVER anticipate everything that might go into a program, so they must fail ever so softly. Much of what I have been challenging others on this form for came out of the analysis and design of Dr. Eliza. The real world definitely has some interesting structure, e.g. the figure 6 shape of cause-and-effect chains, and that problems are a phenomenon that exists behind people's eyeballs and NOT otherwise in the real world. Ignoring such things and diving in and hoping that machine intelligence will resolve all (as many/most here seem to believe) IMHO is a rookie error that leads nowhere useful. Steve Richfield --- I don't think that most people in this group think that machine intelligence will resolve all the remaining problems in designing artificial intelligence, although I have talked to people who feel that way, and the lack of discussion about resolving some of the complexity issues does seem curious to me. Where are they coming from? I don't know. I think most of the people feel that once they get their basic programs working, that they will be able to figure out the rest on the fly. This method hasn't worked yet, but as I mentioned I do think it has something to do with the difficulty of writing complicated computer programs. I know that you are one of the outspoken critics of faith-based programming, so at least there is some consistency in your comments. I mention this because, I (seriously) believe that that the Lord may have indicated that my algorithm to solve the logical satisfiability problem will work, and if this is true, then that may mean that the algorithm may help resolve some lesser logical complexity problems. Although we cannot use pure logic to represent knowable knowledge, I can use logic to represent theory-like relations between references to knowable components of knowledge. (By the way, please note that I did not claim that I presently have a polynomial time solution to SAT, and I did not say that I was absolutely certain that God pronounced my SAT algorithm to be workable. I have carefully qualified my statements about this. I would also suggest that you think about the fact that we have to use different kinds of reasoning with different kinds of questions. Regardless of your own beliefs, the topic about the necessity of using different kinds of reasoning for different kinds of question is very relevant to discussions about advanced AI.) What do you mean by the figure 6 shape of cause-and-effect chains. It must refer to some kind of feedback-like effect. Jim Bromer --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Well, since you found my blog, you probably are grouping me somewhat with the probability buffs. I have stated that I will not be interested in any other fuzzy logic unless it is accompanied by a careful account of the meaning of the numbers. You have stated that it is unrealistic to expect a logical model to reflect the world perfectly. The intuition behind this seems clear. Instead, what should be hoped for is convergence to (nearly) correct models of (small parts of) the universe. So I suppose that rather than asking for meaning in a fuzzy logic, I should be asking for clear accounts of convergence properties... but my intuition says that from clear meaning, everything else follows. On Sun, Jun 22, 2008 at 9:45 AM, Jim Bromer [EMAIL PROTECTED] wrote: Abram Demski said: To be honest, I am not completely satisfied with my conclusion on the post you refer to. I'm not so sure now that the fundamental split between logical/messy methods should occur at the line between perfect approximate methods. This is one type of messiness, but one only. I think you are referring to a related but different messiness: not knowing what kind of environment your AI is dealing with. Since we don't know which kinds of models will fit best with the world, we should (1) trust our intuitions to some extent, and (2) try things and see how well they work... Mathematics and mathematical proof is a very important tool... Mine is a system built out of somewhat smart pieces, cooperating to build somewhat smarter pieces, and so on. Each piece has provable smarts. Mathematics can be extended to include new kinds of relations and systems. One of the problems I have had with AI-probability buffs is that there are other ways to deal with knowledge that is only partially understood and this kind of complexity can be extended to measurable quantities as well. Notice that economics is not just probability. There are measurable quantities in economics that are not based solely on the economics of money. We cannot make perfect decisions. However, we can often make fairly good decisions even when based on partial knowledge. A conclusion however, should not be taken as a reliable rule unless it has withstood numerous tests. These empirical tests of a conclusion usually cause them to be modified. Even a good conclusion will typically be modified by conditional variations after be extensively tested. That is the nature of expertise. Our conclusions are often only approximations, but they can contain unarticulated links to other possibilities that may indicate other ways of looking at the data or conditional variations to the base conclusion. Jim Bromer agi | Archives | Modify Your Subscription --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Jim, On 6/22/08, Jim Bromer [EMAIL PROTECTED] wrote: A compiler may be a useful tool to use in an advanced AI program (just as we all use compilers in our programming), but I don't feel that a compiler is a good basis for or a good metaphor for advanced AI. A compiler is just another complicated computer program. The sorts of methods I described are applicable to ALL complicated programs. I know of no exceptions. -- Steve wrote: The more complex the software, the better the design must be, and the more protected the execution must be. You can NEVER anticipate everything that might go into a program, so they must fail ever so softly. Much of what I have been challenging others on this form for came out of the analysis and design of Dr. Eliza. The real world definitely has some interesting structure, e.g. the figure 6 shape of cause-and-effect chains, and that problems are a phenomenon that exists behind people's eyeballs and NOT otherwise in the real world. Ignoring such things and diving in and hoping that machine intelligence will resolve all (as many/most here seem to believe) IMHO is a rookie error that leads nowhere useful. Steve Richfield --- I don't think that most people in this group think that machine intelligence will resolve all the remaining problems in designing artificial intelligence, although I have talked to people who feel that way, and the lack of discussion about resolving some of the complexity issues does seem curious to me. I simply attribute this to rookie error - but many of the people on this forum are definitely NOT rookies. Hmmm. Where are they coming from? I don't know. I think most of the people feel that once they get their basic programs working, that they will be able to figure out the rest on the fly. This method hasn't worked yet, but as I mentioned I do think it has something to do with the difficulty of writing complicated computer programs. I know that you are one of the outspoken critics of faith-based programming, YES - and you said it even better than I have! so at least there is some consistency in your comments. I mention this because, I (seriously) believe that that the Lord may have indicated that my algorithm to solve the logical satisfiability problem will work, and if this is true, then that may mean that the algorithm may help resolve some lesser logical complexity problems. Most of my working career has been as a genuine consultant (and not just an unemployed programmer). I am typically hired by a major investor. My specialty is resurrecting projects that are in technological trouble. At the heart of the most troubled projects. I typically find either a born-again Christian or a PhD Chemist. These people make the same bad decisions from faith. The Christian's faith is that God wouldn't lead them SO astray, so abandoning the project would in effect be abandoning their faith in God - which of course leads straight to Hell. The Chemist has heard all of the stories of perseverance leading to breakthrough discoveries, and if you KNOW that the solution is there just waiting to be found, then just keep on plugging away. These both lead to projects that stumble on and on long after any sane person would have found another better way. Christians tend to make good programmers, but really awful project managers. Although we cannot use pure logic to represent knowable knowledge, I can use logic to represent theory-like relations between references to knowable components of knowledge. (By the way, please note that I did not claim that I presently have a polynomial time solution to SAT, and I did not say that I was absolutely certain that God pronounced my SAT algorithm to be workable. Are you waiting for me to make such a pronouncement?! I have carefully qualified my statements about this. I would also suggest that you think about the fact that we have to use different kinds of reasoning with different kinds of questions. Regardless of your own beliefs, the topic about the necessity of using different kinds of reasoning for different kinds of question is very relevant to discussions about advanced AI.) What do you mean by the figure 6 shape of cause-and-effect chains. It must refer to some kind of feedback-like effect. EVERYTHING works by cause and effect - even God's work, because he is responding to what he sees, and therefore HE is but another link. Where things are dynamically changing, there is little opportunity to run over to your computer and inquire about what to do about things you don't like. However, where things appear to be both stable and undesirable, there is probably a looped cause-and-effect chain that is at least momentarily running in a circle. Of course, there must have been a causal cause-and-effect chain that led to this loop, so drawing the root cause at the top, a chain that bends do the
Re: [agi] Approximations of Knowledge
Steve:Most of my working career has been as a genuine consultant (and not just an unemployed programmer). I am typically hired by a major investor. My specialty is resurrecting projects that are in technological trouble. At the heart of the most troubled projects. I typically find either a born-again Christian or a PhD Chemist. These people make the same bad decisions from faith. The Christian's faith is that God wouldn't lead them SO astray, so abandoning the project would in effect be abandoning their faith in God - which of course leads straight to Hell. The Chemist has heard all of the stories of perseverance leading to breakthrough discoveries, and if you KNOW that the solution is there just waiting to be found, then just keep on plugging away. These both lead to projects that stumble on and on long after any sane person would have found another better way. Christians tend to make good programmers, but really awful project managers. V. interesting. The thing that amazes me - I don't know whether this relates to your experience - is that so many AGI-ers don't seem to realise that if you're going to commit to a creative project, you must have at least one big, central creative idea to start with. Especially if investors are to be involved. I find the pathologies of how would-be creatives fail to see this fascinating - you have possible examples above. Another obvious example is how many people think that they are being creative simply by going into a new area, even though they have no real new ideas or approaches to 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Abram I am pressed for time right now, but just to let you know that, now that I am aware of your post, I will reply soon. I think that many of your concerns are a result of seeing a different message in the paper than the one I intended. Richard Loosemore Abram Demski wrote: To be honest, I am not completely satisfied with my conclusion on the post you refer to. I'm not so sure now that the fundamental split between logical/messy methods should occur at the line between perfect approximate methods. This is one type of messiness, but one only. I think you are referring to a related but different messiness: not knowing what kind of environment your AI is dealing with. Since we don't know which kinds of models will fit best with the world, we should (1) trust our intuitions to some extent, and (2) try things and see how well they work. This is as Loosemore suggests. On the other hand, I do not want to agree with Loosemore too strongly. Mathematics and mathematical proof is a very important tool, and I feel like he wants to reject it. His image of an AGI seems to be a system built up out of totally dumb pieces, with intelligence emerging unexpectedly. Mine is a system built out of somewhat smart pieces, cooperating to build somewhat smarter pieces, and so on. Each piece has provable smarts. On Sat, Jun 21, 2008 at 6:54 AM, Jim Bromer [EMAIL PROTECTED] wrote: I just read Abram Demski's comments about Loosemore's, Complex Systems, Artificial Intelligence and Theoretical Psychology, at http://dragonlogic-ai.blogspot.com/2008/03/i-recently-read-article-called-complex.html I thought Abram's comments were interesting. I just wanted to make a few criticisms. One is that a logical or rational approach to AI does not necessarily mean that it would be a fully constrained logical - mathematical method. My point of view is that if you use a logical or a rational method with an unconstrained inductive system (open and not monotonic) then the logical system will, for any likely use, act like a rational-non-rational system no matter what you do. So when, I for example, start thinking about whether or not I will be able to use my SAT system (logical satisfiability) for an AGI program, I am not thinking of an implementation of a pure Aristotelian-Boolean system of knowledge. The system I am currently considering would use logic to study theories and theory-like relations that refer to concepts about the natural universe and the universe of thought, but without the expectation that those theories could ever constitute a sound strictly logical or rational model of everything. Such ideas are so beyond the pale that I do not even consider the possibility to be worthy of effort. No one in his right mind would seriously think that he could write a computer program that could explain everything perfectly without error. If anyone seriously talked like that I would take it as a indication of some significant psychological problem. I also take it as a given that AI would suffer from the problem of computational irreducibility if it's design goals were to completely comprehend all complexity using only logical methods in the strictest sense. However, many complex ideas may be simplified and these simplifications can be used wisely in specific circumstances. My belief is that many interrelated layers of simplification, if they are used insightfully, can effectively represent complex ideas that may not be completely understood, just as we use insightful simplifications while trying to discuss something that is completely understood, like intelligence. My problem with developing an AI program is not that I cannot figure out how to create complex systems of insightful simplifications, but that I do not know how to develop a computer program capable of sufficient complexity to handle the load that the system would produce. So while I agree with Demski's conclusion that, there is a way to salvage Loosemore's position, ...[through] shortcutting an irreducible computation by compromising, allowing the system to produce less-than-perfect results, and, ...as we tackle harder problems, the methods must become increasingly approximate, I do not agree that the contemporary problem is with logic or with the complexity of human knowledge. I feel that the major problem I have is that writing a really really complicated computer program is really really difficult. The problem I have with people who talk about ANNs or probability nets as if their paradigm of choice were the inevitable solution to complexity is that they never discuss how their approach might actually handle complexity. Most advocates of ANNs or probability deal with the problem of complexity as if it were a problem that either does not exist or has already been solved by whatever tired paradigm they are advocating. I don't get that. The major problem I have is that writing a really really complicated computer program is really really difficult.
Re: [agi] Approximations of Knowledge
On Jun 22, 2008, at 1:37 PM, Steve Richfield wrote: At the heart of the most troubled projects. I typically find either a born-again Christian or a PhD Chemist. These people make the same bad decisions from faith. The Christian's faith is that God wouldn't lead them SO astray, so abandoning the project would in effect be abandoning their faith in God - which of course leads straight to Hell. The Chemist has heard all of the stories of perseverance leading to breakthrough discoveries, and if you KNOW that the solution is there just waiting to be found, then just keep on plugging away. These both lead to projects that stumble on and on long after any sane person would have found another better way. Christians tend to make good programmers, but really awful project managers. Somewhere in the world, there is a PhD chemist and a born-again Christian on another mailing list ...the project had hit a serious snag, and so the investors brought in a consultant that would explain why the project was broken by defectively reasoning about dubious generalizations he pulled out of his ass... 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Abram, I did not group you with probability buffs. One of the errors I feel that writers make when their field is controversial is that they begin representing their own opinions from the vantage of countering critics. Unfortunately, I am one of those writers, (or perhaps I am just projecting). But my comment about the probability buffs wasn't directed toward you, I was just using it as an exemplar (of something or another). Your comments seem to make sense to me although I don't know where you are heading. You said: what should be hoped for is convergence to (nearly) correct models of (small parts of) the universe. So I suppose that rather than asking for meaning in a fuzzy logic, I should be asking for clear accounts of convergence properties... When you have to find a way to tie together components of knowledge together you typically have to achieve another kind of convergence. Even if these 'components' of knowledge are reliable, they cannot usually be converged easily due to the complexity that their interrelations with other kinds of knowledge (other 'components' of knowledge) will cause. To follow up on what I previously said, if my logic program works it will mean that I can combine and test logical formulas of up to a few hundred distinct variables and find satisfiable values for these combinations in a relatively short period of time. I think this will be an important method to test whether AI can be advanced by advancements in handling complexity even though some people do not feel that logical methods are appropriate to use on multiple source complexity. As you seem to appreciate, logic can still be brought to to the field even though it is not a purely logical game that is to be played. When I begin to develop some simple theories about a subject matter, I will typically create hundreds of minor variations concerning those theories over a period of time. I cannot hold all those variations of the conjecture in consciousness at any one moment, but I do feel that they can come to mind in response to a set of conditions for which that particular set of variations was created for. So while a simple logical theory (about some subject) may be expressible with only a few terms, when you examine all of the possible variations that can be brought into conscious consideration in response to a particular set of stimuli, I think you may find that the theories could be more accurately expressed using hundreds of distinct logical values. If this conjecture of mine turns out to be true, and if I can actually get my new logical methods to work, then I believe that this new range of logical methods may show whether advancements in complexity can make a difference to AI even if its application does not immediately result in human level of intelligence. Jim Bromer - Original Message From: Abram Demski [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Sunday, June 22, 2008 4:38:02 PM Subject: Re: [agi] Approximations of Knowledge Well, since you found my blog, you probably are grouping me somewhat with the probability buffs. I have stated that I will not be interested in any other fuzzy logic unless it is accompanied by a careful account of the meaning of the numbers. You have stated that it is unrealistic to expect a logical model to reflect the world perfectly. The intuition behind this seems clear. Instead, what should be hoped for is convergence to (nearly) correct models of (small parts of) the universe. So I suppose that rather than asking for meaning in a fuzzy logic, I should be asking for clear accounts of convergence properties... but my intuition says that from clear meaning, everything else follows. --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
Jim, On 6/21/08, Jim Bromer [EMAIL PROTECTED] wrote: The major problem I have is that writing a really really complicated computer program is really really difficult. The ONLY rational approach to this (that I know of) is to construct an engine that develops and applies machine knowledge, wisdom, or whatever, and NOT write code yourself that actually deals with articles of knowledge/wisdom. That engine itself will still be a bit complex, so you must write it in Visual Basic or .NET that provides a protected execution environment, and NOT write it in C/C++ that makes it ever so easy to inadvertently hide really nasty bugs. REALLY complex systems may require multi-level interpreters, where a low-level interpreter provides a pseudo-machine on which to program a really smart high-level interpreter, on which you program your AGI. In ~1970 I wrote an ALGOL/FORTRAN/BASIC compiler that ran in just 16K bytes this way. At the bottom was a pseudo-computer whose primitives were fundamental to compiling. That pseudo-machine was then fed a program to read BNF and make compilers, which was then fed a BNF description of my compiler, with the output being my compiler in pseudo-machine code. One feature of this approach is that for anything to work, everything had to work, so once past initial debugging, it worked perfectly! Contrast this with modern methods that consume megabytes and never work quite right. I wrote Dr, Eliza over the course of a year. I developed a daily workflow, that started with answering my email while I woke up. Then came the most creative work - module design. Then came programming, and finally came debugging and testing. Obviously, you need a solid plan to start with to complete such an effort. I spent another year developing my plan, an effort that also involved going to computer conferences and bending the ear of anyone who might have some applicable expertise. On a scale of complexity, Dr. Eliza is MUCH simpler than many of the proposals being made here. However, it does have one salient feature - it actually works in a real-world useful way. The more complex the software, the better the design must be, and the more protected the execution must be. You can NEVER anticipate everything that might go into a program, so they must fail ever so softly. Much of what I have been challenging others on this form for came out of the analysis and design of Dr. Eliza. The real world definitely has some interesting structure, e.g. the figure 6 shape of cause-and-effect chains, and that problems are a phenomenon that exists behind people's eyeballs and NOT otherwise in the real world. Ignoring such things and diving in and hoping that machine intelligence will resolve all (as many/most here seem to believe) IMHO is a rookie error that leads nowhere useful. Steve Richfield --- 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=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Approximations of Knowledge
To be honest, I am not completely satisfied with my conclusion on the post you refer to. I'm not so sure now that the fundamental split between logical/messy methods should occur at the line between perfect approximate methods. This is one type of messiness, but one only. I think you are referring to a related but different messiness: not knowing what kind of environment your AI is dealing with. Since we don't know which kinds of models will fit best with the world, we should (1) trust our intuitions to some extent, and (2) try things and see how well they work. This is as Loosemore suggests. On the other hand, I do not want to agree with Loosemore too strongly. Mathematics and mathematical proof is a very important tool, and I feel like he wants to reject it. His image of an AGI seems to be a system built up out of totally dumb pieces, with intelligence emerging unexpectedly. Mine is a system built out of somewhat smart pieces, cooperating to build somewhat smarter pieces, and so on. Each piece has provable smarts. On Sat, Jun 21, 2008 at 6:54 AM, Jim Bromer [EMAIL PROTECTED] wrote: I just read Abram Demski's comments about Loosemore's, Complex Systems, Artificial Intelligence and Theoretical Psychology, at http://dragonlogic-ai.blogspot.com/2008/03/i-recently-read-article-called-complex.html I thought Abram's comments were interesting. I just wanted to make a few criticisms. One is that a logical or rational approach to AI does not necessarily mean that it would be a fully constrained logical - mathematical method. My point of view is that if you use a logical or a rational method with an unconstrained inductive system (open and not monotonic) then the logical system will, for any likely use, act like a rational-non-rational system no matter what you do. So when, I for example, start thinking about whether or not I will be able to use my SAT system (logical satisfiability) for an AGI program, I am not thinking of an implementation of a pure Aristotelian-Boolean system of knowledge. The system I am currently considering would use logic to study theories and theory-like relations that refer to concepts about the natural universe and the universe of thought, but without the expectation that those theories could ever constitute a sound strictly logical or rational model of everything. Such ideas are so beyond the pale that I do not even consider the possibility to be worthy of effort. No one in his right mind would seriously think that he could write a computer program that could explain everything perfectly without error. If anyone seriously talked like that I would take it as a indication of some significant psychological problem. I also take it as a given that AI would suffer from the problem of computational irreducibility if it's design goals were to completely comprehend all complexity using only logical methods in the strictest sense. However, many complex ideas may be simplified and these simplifications can be used wisely in specific circumstances. My belief is that many interrelated layers of simplification, if they are used insightfully, can effectively represent complex ideas that may not be completely understood, just as we use insightful simplifications while trying to discuss something that is completely understood, like intelligence. My problem with developing an AI program is not that I cannot figure out how to create complex systems of insightful simplifications, but that I do not know how to develop a computer program capable of sufficient complexity to handle the load that the system would produce. So while I agree with Demski's conclusion that, there is a way to salvage Loosemore's position, ...[through] shortcutting an irreducible computation by compromising, allowing the system to produce less-than-perfect results, and, ...as we tackle harder problems, the methods must become increasingly approximate, I do not agree that the contemporary problem is with logic or with the complexity of human knowledge. I feel that the major problem I have is that writing a really really complicated computer program is really really difficult. The problem I have with people who talk about ANNs or probability nets as if their paradigm of choice were the inevitable solution to complexity is that they never discuss how their approach might actually handle complexity. Most advocates of ANNs or probability deal with the problem of complexity as if it were a problem that either does not exist or has already been solved by whatever tired paradigm they are advocating. I don't get that. The major problem I have is that writing a really really complicated computer program is really really difficult. But perhaps Abram's idea could be useful here. As the program has to deal with more complicated collections of simple insights that concern some hard subject matter, it could tend to rely more on approximations to manage those complexes of
Re: [agi] Approximations of Knowledge
Abram, A useful midpoint between views is to decide what knowledge must distill down to, to be able to relate it together and do whatever you want to do. I did this with Dr. Eliza and realized that I had to have a column in my DB that contained what people typically say to indicate the presence of various symptoms (of various cause-and-effect chain links). I now realize that ignorance of the operation of various processes itself is also a condition with its own symptoms, each with their own common expressions of ignorance. OK, so just where was my column going to come from? This information is NOT on the Internet, Wikipedia, etc., yet any expert can rattle this information off in a heartbeat. The only obvious answer was to have experts hand code this information. I am STILL listening to anyone who claims to have another/better way, but I have yet to hear ANY other functional proposal. Of course, this simple realization dooms all of the several efforts now underway to mine the Internet and Wikipedia for knowledge from which to solve problems, yet no one seems to be interested in this simple gotcha, while these doomed efforts continue. I believe that ALL of the ongoing disputes here on this forum are born of a lack of analysis. While the contents of a knowledge base may be very complex and interrelated, the structure of that DB should be relatively simple. This discussion should start with a proposal for structure, and continue as the flaws in that proposal are each identified and addressed. Note in passing that the value of any problem solving system lies in its ability to solve problems with an absolute minimum of information. Hence, systems that require the most information are worth the least, and systems that require all information are completely worthless. Dr. Eliza was designed to operate right at the (currently believed to be) absolute minimum. I completely agree with others here that Dr. Eliza is NOT an AGI as currently envisioned. However, for many of the projected problem-solving functions of a future AGI, it appears to be absolutely unbeatable. People need to either target other functionality for a *useful* future AGI, or else develop designs that won't be predictably inferior to Dr. Eliza. For this, they would do well to fully understand the operation of Dr. Eliza, which should be no problem since it is conceptually pretty simple. Most of the code goes to support speech I/O, the USENET interface, etc., and NOT its core problem solving ability. Steve Richfield === On 6/21/08, Abram Demski [EMAIL PROTECTED] wrote: To be honest, I am not completely satisfied with my conclusion on the post you refer to. I'm not so sure now that the fundamental split between logical/messy methods should occur at the line between perfect approximate methods. This is one type of messiness, but one only. I think you are referring to a related but different messiness: not knowing what kind of environment your AI is dealing with. Since we don't know which kinds of models will fit best with the world, we should (1) trust our intuitions to some extent, and (2) try things and see how well they work. This is as Loosemore suggests. On the other hand, I do not want to agree with Loosemore too strongly. Mathematics and mathematical proof is a very important tool, and I feel like he wants to reject it. His image of an AGI seems to be a system built up out of totally dumb pieces, with intelligence emerging unexpectedly. Mine is a system built out of somewhat smart pieces, cooperating to build somewhat smarter pieces, and so on. Each piece has provable smarts. On Sat, Jun 21, 2008 at 6:54 AM, Jim Bromer [EMAIL PROTECTED] wrote: I just read Abram Demski's comments about Loosemore's, Complex Systems, Artificial Intelligence and Theoretical Psychology, at http://dragonlogic-ai.blogspot.com/2008/03/i-recently-read-article-called-complex.html I thought Abram's comments were interesting. I just wanted to make a few criticisms. One is that a logical or rational approach to AI does not necessarily mean that it would be a fully constrained logical - mathematical method. My point of view is that if you use a logical or a rational method with an unconstrained inductive system (open and not monotonic) then the logical system will, for any likely use, act like a rational-non-rational system no matter what you do. So when, I for example, start thinking about whether or not I will be able to use my SAT system (logical satisfiability) for an AGI program, I am not thinking of an implementation of a pure Aristotelian-Boolean system of knowledge. The system I am currently considering would use logic to study theories and theory-like relations that refer to concepts about the natural universe and the universe of thought, but without the expectation that those theories could ever constitute a sound strictly logical or rational model of everything. Such ideas are so
