[agi] The Smushaby of Flatway.
All of the major AI paradigms, including those that are capable of learning, are flat according to my definition. What makes them flat is that the method of decision making is minimally-structured and they funnel all reasoning through a single narrowly focused process that smushes different inputs to produce output that can appear reasonable in some cases but is really flat and lacks any structure for complex reasoning. The classic example is of course logic. Every proposition can be described as being either True or False and any collection of propositions can be used in the derivation of a conclusion regardless of whether the input propositions had any significant relational structure that would actually have made it reasonable to draw the definitive conclusion that was drawn from them. But logic didn't do the trick, so along came neural networks and although the decision making is superficially distributed and can be thought of as being comprised of a structure of layer-like stages in some variations, the methodology of the system is really just as flat. Again anything can be dumped into the neural network and a single decision making process works on the input through a minimally-structured reasoning system and output is produced regardless of the lack of appropriate relative structure in it. In fact, this lack of discernment was seen as a major breakthrough! Surprise, neural networks did not work just like the mind works in spite of the years and years of hype-work that went into repeating this slogan in the 1980's. Then came Genetic Algorithms and finally we had a system that could truly learn to improve on its previous learning and how did it do this? It used another flat reasoning method whereby combinations of data components were processed according to one simple untiring method that was used over and over again regardless of any potential to see input as being structured in more ways than one. Is anyone else starting to discern a pattern here? Finally we reach the next century to find that the future of AI has already arrived and that future is probabilistic reasoning! And how is probabilistic reasoning different? Well, it can solve problems that logic, neural networks, genetic algorithms couldn't! And how does probabilistic reasoning do this? It uses a funnel minimally-structured method of reasoning whereby any input can be smushed together with other disparate input to produce a conclusion which is only limited by the human beings who strive to program it! The very allure of minimally-structured reasoning is that it works even in some cases where it shouldn't. It's the hip hooray and bally hoo of the smushababies of Flatway. Jim Bromer --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Logic has not solved AGI because logic is a poor model of the way people think. Neural networks have not solved AGI because you would need about 10^15 bits of memory and 10^16 OPS to simulate a human brain sized network. Genetic algorithms have not solved AGI because the computational requirements are even worse. You would need 10^36 bits just to model all the world's DNA, and even if you could simulate it in real time, it took 3 billion years to produce human intelligence the first time. Probabilistic reasoning addresses only one of the many flaws of first order logic as a model of AGI. Reasoning under uncertainty is fine, but you haven't solved learning by induction, reinforcement learning, complex pattern recognition (e.g. vision), and language. If it was just a matter of writing the code, then it would have been done 50 years ago. -- Matt Mahoney, matmaho...@yahoo.com --- On Wed, 1/7/09, Jim Bromer wrote: > From: Jim Bromer > Subject: [agi] The Smushaby of Flatway. > To: agi@v2.listbox.com > Date: Wednesday, January 7, 2009, 8:23 PM > All of the major AI paradigms, including those that are > capable of > learning, are flat according to my definition. What makes > them flat > is that the method of decision making is > minimally-structured and they > funnel all reasoning through a single narrowly focused > process that > smushes different inputs to produce output that can appear > reasonable > in some cases but is really flat and lacks any structure > for complex > reasoning. > > The classic example is of course logic. Every proposition > can be > described as being either True or False and any collection > of > propositions can be used in the derivation of a conclusion > regardless > of whether the input propositions had any significant > relational > structure that would actually have made it reasonable to > draw the > definitive conclusion that was drawn from them. > > But logic didn't do the trick, so along came neural > networks and > although the decision making is superficially distributed > and can be > thought of as being comprised of a structure of layer-like > stages in > some variations, the methodology of the system is really > just as flat. > Again anything can be dumped into the neural network and a > single > decision making process works on the input through a > minimally-structured reasoning system and output is > produced > regardless of the lack of appropriate relative structure in > it. In > fact, this lack of discernment was seen as a major > breakthrough! > Surprise, neural networks did not work just like the mind > works in > spite of the years and years of hype-work that went into > repeating > this slogan in the 1980's. > > Then came Genetic Algorithms and finally we had a system > that could > truly learn to improve on its previous learning and how did > it do > this? It used another flat reasoning method whereby > combinations of > data components were processed according to one simple > untiring method > that was used over and over again regardless of any > potential to see > input as being structured in more ways than one. Is anyone > else > starting to discern a pattern here? > > Finally we reach the next century to find that the future > of AI has > already arrived and that future is probabilistic reasoning! > And how > is probabilistic reasoning different? Well, it can solve > problems > that logic, neural networks, genetic algorithms > couldn't! And how > does probabilistic reasoning do this? It uses a funnel > minimally-structured method of reasoning whereby any input > can be > smushed together with other disparate input to produce a > conclusion > which is only limited by the human beings who strive to > program it! > > The very allure of minimally-structured reasoning is that > it works > even in some cases where it shouldn't. It's the > hip hooray and bally > hoo of the smushababies of Flatway. > > Jim Bromer --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
> If it was just a matter of writing the code, then it would have been done > 50 years ago. if proving Fermat's Last theorem was just a matter of doing math, it would have been done 150 years ago ;-p obviously, all hard problems that can be solved have already been solved... ??? --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
--- On Wed, 1/7/09, Ben Goertzel wrote: >if proving Fermat's Last theorem was just a matter of doing math, it would >have been done 150 years ago ;-p > >obviously, all hard problems that can be solved have already been solved... > >??? In theory, FLT could be solved by brute force enumeration of proofs until a match to Wiles' is found. In theory, AGI could be solved by coding all the knowledge in LISP. The difference is that 50 years ago people actually expected the latter to work. Some people still believe so. AGI is an engineering and policy problem. We already have small scale neural models of learning, language, vision, and motor control. We currently lack the computing power (10^16 OPS, 10^15 bits) to implement these at human levels, but Moore's law will take care of that. But that is not the hard part of the problem. AGI is a system that eliminates our need to work, to think, and to function in the real world. Its value is USD 10^15, the value of the global economy. Once we have the hardware, we still need to extract 10^18 bits of knowledge from human brains. That is the complexity of the global economy (assuming 10^10 people x 10^9 bits per person x 0.1 fraction consisting of unique job skills). This is far bigger than the internet. The only way to extract this knowledge without new technology like brain scanning is by communication at the rate of 2 bits per second per person. The cheapest option is a system of pervasive surveillance where everything you say and do is public knowledge. AGI is too expensive for any person or group to build or own. It is a vastly improved internet, a communication system so efficient that the world's population starts to look like a single entity, and nobody notices or cares as silicon gradually replaces carbon. -- Matt Mahoney, matmaho...@yahoo.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Matt:> Logic has not solved AGI because logic is a poor model of the way people think. Neural networks have not solved AGI because you would need about 10^15 bits of memory and 10^16 OPS to simulate a human brain sized network. Genetic algorithms have not solved AGI because the computational requirements are even worse. You would need 10^36 bits just to model all the world's DNA, and even if you could simulate it in real time, it took 3 billion years to produce human intelligence the first time. Probabilistic reasoning addresses only one of the many flaws of first order logic as a model of AGI. Reasoning under uncertainty is fine, but you haven't solved learning by induction, reinforcement learning, complex pattern recognition (e.g. vision), and language. If it was just a matter of writing the code, then it would have been done 50 years ago. Matt, What then do you see as the way people *do* think? You surprise me, Matt, because both the details of your answer here and your thinking generally strike me as *very* logicomathematical - with lots of emphasis on numbers and compression - yet you seem to be acknowledging here, like Jim, the fundamental deficiencies of the logicomathematical form - and it is indeed only one form - of thinking. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
--- On Thu, 1/8/09, Mike Tintner wrote: > What then do you see as the way people *do* think? You > surprise me, Matt, because both the details of your answer > here and your thinking generally strike me as *very* > logicomathematical - with lots of emphasis on numbers and > compression - yet you seem to be acknowledging here, like > Jim, the fundamental deficiencies of the logicomathematical > form - and it is indeed only one form - of thinking. Pattern recognition in parallel, and hierarchical learning of increasingly complex patterns by classical conditioning (association), clustering in context space (feature creation), and reinforcement learning to meet evolved goals. You can't write a first order logic expression that inputs a picture and tells you whether it is a cat or a dog. Yet any child can do it. Logic is great for abstract mathematics. We regard it as the highest form of thought, the hardest thing that humans can learn, yet it is the easiest problem to solve on a computer. -- Matt Mahoney, matmaho...@yahoo.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Matt, Thanks. But how do you see these: "Pattern recognition in parallel, and hierarchical learning of increasingly complex patterns by classical conditioning (association), clustering in context space (feature creation), and reinforcement learning to meet evolved goals." as fundamentally different from logicomathematical thinking? ("Reinforcement learning" strikes me as literally extraneous and not a mode of thinking). Perhaps you need to explain why conditioned association is different. It may help if I set up a pole of comparison. I see the brain, for example, as working primarily by "free association." I can start right now with a thought - "COW" - and proceed - DOG - TAIL - CURRENT CRISIS - LOCAL VS GLOBAL THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH MORE TIME ON THIS" etc. etc. and that literally was an ad hoc and ad lib chain and form of reasoning. Free association. In no way was the whole programmed. Parts of it certainly were - my spelling of different words, use of phrases etc. but not the whole - I could have gone off at different points on very different tangents. (Try it for yourself). Also, of course, each association is indeed an *association* with and not a *logical/ necessary sequitur" from the previous idea. Now free association is clearly antithetical to logicomathematical thinking which do indeed represent forms of routines and programs. I would have thought that it is also antithetical to any kind of thinking you would advocate. Matt/MT:> What then do you see as the way people *do* think? You surprise me, Matt, because both the details of your answer here and your thinking generally strike me as *very* logicomathematical - with lots of emphasis on numbers and compression - yet you seem to be acknowledging here, like Jim, the fundamental deficiencies of the logicomathematical form - and it is indeed only one form - of thinking. Pattern recognition in parallel, and hierarchical learning of increasingly complex patterns by classical conditioning (association), clustering in context space (feature creation), and reinforcement learning to meet evolved goals. You can't write a first order logic expression that inputs a picture and tells you whether it is a cat or a dog. Yet any child can do it. Logic is great for abstract mathematics. We regard it as the highest form of thought, the hardest thing that humans can learn, yet it is the easiest problem to solve on a computer. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
RE: [agi] The Smushaby of Flatway.
human level AGI, the computation need be no more "smushed" than it is in the human brain. So I think your allegations of "smushing" are over generalized, and that to the extent they have any validity, the hardware and the software approaches to AGI that will start dominating within 3 to 10 years will have made their relevance largely historical. Ed Porter -Original Message- From: Jim Bromer [mailto:jimbro...@gmail.com] Sent: Wednesday, January 07, 2009 8:24 PM To: agi@v2.listbox.com Subject: [agi] The Smushaby of Flatway. All of the major AI paradigms, including those that are capable of learning, are flat according to my definition. What makes them flat is that the method of decision making is minimally-structured and they funnel all reasoning through a single narrowly focused process that smushes different inputs to produce output that can appear reasonable in some cases but is really flat and lacks any structure for complex reasoning. The classic example is of course logic. Every proposition can be described as being either True or False and any collection of propositions can be used in the derivation of a conclusion regardless of whether the input propositions had any significant relational structure that would actually have made it reasonable to draw the definitive conclusion that was drawn from them. But logic didn't do the trick, so along came neural networks and although the decision making is superficially distributed and can be thought of as being comprised of a structure of layer-like stages in some variations, the methodology of the system is really just as flat. Again anything can be dumped into the neural network and a single decision making process works on the input through a minimally-structured reasoning system and output is produced regardless of the lack of appropriate relative structure in it. In fact, this lack of discernment was seen as a major breakthrough! Surprise, neural networks did not work just like the mind works in spite of the years and years of hype-work that went into repeating this slogan in the 1980's. Then came Genetic Algorithms and finally we had a system that could truly learn to improve on its previous learning and how did it do this? It used another flat reasoning method whereby combinations of data components were processed according to one simple untiring method that was used over and over again regardless of any potential to see input as being structured in more ways than one. Is anyone else starting to discern a pattern here? Finally we reach the next century to find that the future of AI has already arrived and that future is probabilistic reasoning! And how is probabilistic reasoning different? Well, it can solve problems that logic, neural networks, genetic algorithms couldn't! And how does probabilistic reasoning do this? It uses a funnel minimally-structured method of reasoning whereby any input can be smushed together with other disparate input to produce a conclusion which is only limited by the human beings who strive to program it! The very allure of minimally-structured reasoning is that it works even in some cases where it shouldn't. It's the hip hooray and bally hoo of the smushababies of Flatway. Jim Bromer --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?&; Powered by Listbox: http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
IFrom: Jim Bromer [mailto:jimbro...@gmail.com] Sent: Wednesday, January 07, 2009 8:24 PM All of the major AI paradigms, including those that are capable of learning, are flat according to my definition. What makes them flat is that the method of decision making is minimally-structured and they funnel all reasoning through a single narrowly focused process that smushes different inputs to produce output that can appear reasonable in some cases but is really flat and lacks any structure for complex reasoning. Consider a wave machine made of oil and color water. Technically speaking the information is flat even under chaos stimulation because the sum of the top oil and the bottom water remains constant within the limits of the power parameters of the system. This is a pure 3D correlational wavelet opponent processing machine. The system is globally entangled to new information but the response time is globally slow. Now insert floating needles locked into a mao location that go up and down from the modulations. Let the needles make contact with a parallel processor. The on and off switching is read with a constant Paul rf trap and protected in parallel modulating string pulses. The information is sent to another wave machine and the flowing needles electromagnetically can be make to move up and down duplicating the pure gaussian memory of the first wave machine with some lost of noise. Noise is not noise, it is the declining value of previous information. The system makes calculations in a relative zero energy value or opponent process. Noise is important for creative thought and intelligent behavior. Now let see this process phase locked or a snap shot picture. The information is globally flat because it is a parallel opponent process but contains reciprocal Eigenfunction to produce the opponent process summation interference if the picture was reversed and both added together. The new picture would be a flat gray. The brain and a good AGI would have trouble keeping up with the data flow at a particular location just like the wave machine but over a slow gaussian reference rf trap the summation would approach zero. A good AGI machine would have a slow integration time or oscillon output picture or http://www.youtube.com/watch?v=hvTzeWXCqXQ . Now consider a self programming electronic wave machine with two systems - a object map system and an action map system. Example http://oolong.co.uk/resonata.htm locked into the forth harmonic. The two systems are Eigenfunction. Example a child says loudly MILK!. Milk as a stimulus means at the same time when it hits the dual memory map the object milk and it is entangled with its Eigenfunction for action map - get MILK now. The program get milk now is turned on. Because the action program is turned on it does a data input into the gaussian data base for milk. That is what entangled memory means. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com <> <>
Re: [agi] The Smushaby of Flatway.
On Jan 8, 2009, at 10:29 AM, Ronald C. Blue wrote: ...Noise is not noise... Speaking of noise, was that ghastly HTML formatting really necessary? It made the email nearly unreadable. J. Andrew Rogers --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
--- On Thu, 1/8/09, Mike Tintner wrote: > Matt, > > Thanks. But how do you see these: > > "Pattern recognition in parallel, and hierarchical > learning of increasingly complex patterns by classical > conditioning (association), clustering in context space > (feature creation), and reinforcement learning to meet > evolved goals." > > as fundamentally different from logicomathematical > thinking? ("Reinforcement learning" strikes me as > literally extraneous and not a mode of thinking). Perhaps > you need to explain why conditioned association is > different. Free association is the basic way of recalling memories. If you experience A followed by B, then the next time you experience A you will think of (or predict) B. Pavlov demonstrated this type of learning in animals in 1927. Hebb proposed a neural model in 1949 which has since been widely accepted. The model is unrelated to first order logic. It is a strengthening of the connections from neuron A to neuron B. -- Matt Mahoney, matmaho...@yahoo.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Matt:Free association is the basic way of recalling memories. If you experience A followed by B, then the next time you experience A you will think of (or predict) B. Pavlov demonstrated this type of learning in animals in 1927. Matt, You're not thinking your argument through. Look carefully at my spontaneous "COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS GLOBAL THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH MORE TIME ON THIS" etc. etc" that's not A-B association. That's 1. A-B-C then 2. Gamma-Delta then 3. Languages then 4. Number of Lines in Letters. IOW the brain is typically not only freely associating *ideas* but switching freely across, and connecting, radically different *domains* in any given chain of association. [e.g above from Animals to Economics/Politics to Weather to Personal Timetable] It can do this partly because a) single ideas have multiple, often massively mutiple, idea/domain connections in the human brain, and allow one to go off in any of multiple tangents/directions b) humans have many things - and therefore multiple domains - on their mind at the same time concurrently - and can switch as above from the immediate subject to some other pressing subject domain (e.g. from economics/politics (local vs global) to the weather (what a nice day). If your "A-B, everything-is-memory-recall" thesis were true, our chains-of-thought-association would be largely repetitive, and the domain switches inevitable.. In fact, our chains (or networks) of free association and domain-switching are highly creative, and each one is typically, from a purely technical POV, novel and surprising. (I have never connected TAIL and CURRENT CRISIS before - though Animals and Politics yes. Nor have I connected LOCAL VS GLOBAL THINKING before with WHAT A NICE DAY and the weather). IOW I'm suggesting, the natural mode of human thought - and our continuous streams of association - are creative. And achieving such creativity is the principal problem/goal of AGI. So maybe it's worth taking 20 secs. of time - producing your own chain-of-free-association starting say with "MAHONEY" and going on for another 10 or so items - and trying to figure out how the result could.possibly be the narrow kind of memory-recall you're arguing for. It's an awful lot to ask for, but could you possibly try it, analyse it and report back? [Ben claims to have heard every type of argument I make before, (somewhat like your A-B memory claim), so perhaps he can tell me where he's read before about the Freely Associative, Freely Domain Switching nature of human thought - I'd be interested to follow up on it]. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
That email had really nice images, but I don't know why gmail viewed them automatically! On 1/8/09, Mike Tintner wrote: > Matt:Free association is the basic way of recalling memories. If you > experience A followed by B, then the next time you experience A you will > think of (or predict) B. Pavlov demonstrated this type of learning in > animals in 1927. > > Matt, > > You're not thinking your argument through. Look carefully at my spontaneous > > "COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS GLOBAL > THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH MORE TIME ON > THIS" etc. etc" > > that's not A-B association. > > That's 1. A-B-C then 2. Gamma-Delta then 3. Languages then 4. Number of > Lines in Letters. > > IOW the brain is typically not only freely associating *ideas* but switching > freely across, and connecting, radically different *domains* in any given > chain of association. [e.g above from Animals to Economics/Politics to > Weather to Personal Timetable] > > It can do this partly because > > a) single ideas have multiple, often massively mutiple, idea/domain > connections in the human brain, and allow one to go off in any of multiple > tangents/directions > b) humans have many things - and therefore multiple domains - on their mind > at the same time concurrently - and can switch as above from the immediate > subject to some other pressing subject domain (e.g. from > economics/politics (local vs global) to the weather (what a nice day). > > If your "A-B, everything-is-memory-recall" thesis were true, our > chains-of-thought-association would be largely repetitive, and the domain > switches inevitable.. > > In fact, our chains (or networks) of free association and domain-switching > are highly creative, and each one is typically, from a purely technical POV, > novel and surprising. (I have never connected TAIL and CURRENT CRISIS > before - though Animals and Politics yes. Nor have I connected LOCAL VS > GLOBAL THINKING before with WHAT A NICE DAY and the weather). > > IOW I'm suggesting, the natural mode of human thought - and our continuous > streams of association - are creative. And achieving such creativity is the > principal problem/goal of AGI. > > So maybe it's worth taking 20 secs. of time - producing your own > chain-of-free-association starting say with "MAHONEY" and going on for > another 10 or so items - and trying to figure out how the result > could.possibly be the narrow kind of memory-recall you're arguing for. It's > an awful lot to ask for, but could you possibly try it, analyse it and > report back? > > [Ben claims to have heard every type of argument I make before, (somewhat > like your A-B memory claim), so perhaps he can tell me where he's read > before about the Freely Associative, Freely Domain Switching nature of human > thought - I'd be interested to follow up on it]. > > > > > --- > agi > Archives: https://www.listbox.com/member/archive/303/=now > RSS Feed: https://www.listbox.com/member/archive/rss/303/ > Modify Your Subscription: > https://www.listbox.com/member/?&; > Powered by Listbox: http://www.listbox.com > --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Mike, Your own thought processes only seem mysterious because you can't predict what you will think without actually thinking it. It's not just a property of the human brain, but of all Turing machines. No program can non-trivially model itself. (By model, I mean that P models Q if for any input x, P can compute the output Q(x). By non-trivial, I mean that P does something else besides just model Q. (Every program trivially models itself). The proof is that for P to non-trivially model Q requires K(P) > K(Q), where K is Kolmogorov complexity, because P needs a description of Q plus whatever else it does to make it non-trivial. It is obviously not possible for K(P) > K(P)). So if you learned the associations A-B and B-C, then A will predict C. That is called "reasoning". Also, each concept is associated with thousands of other concepts, not just A-B. If you pick the strongest associated concept not previously activated, you get the semi-random thought chain you describe. You can demonstrate this with a word-word matrix M from a large text corpus, where M[i,j] is the degree to which the i'th word in the vocabulary is associated with the j'th word, as measured by the probability of finding both words near each other in the corpus. Thus, M[rain,wet] and M[wet,water] have high values because the words often appear in the same paragraph. Traversing related words in M gives you something similar to your free association chain like rain-wet-water-... -- Matt Mahoney, matmaho...@yahoo.com --- On Thu, 1/8/09, Mike Tintner wrote: > From: Mike Tintner > Subject: Re: [agi] The Smushaby of Flatway. > To: agi@v2.listbox.com > Date: Thursday, January 8, 2009, 3:54 PM > Matt:Free association is the basic way of recalling > memories. If you experience A followed by B, then the next > time you experience A you will think of (or predict) B. > Pavlov demonstrated this type of learning in animals in > 1927. > > Matt, > > You're not thinking your argument through. Look > carefully at my spontaneous > > "COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS > GLOBAL > THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH > MORE TIME ON > THIS" etc. etc" > > that's not A-B association. > > That's 1. A-B-C then 2. Gamma-Delta then 3. > Languages then 4. Number of Lines in Letters. > > IOW the brain is typically not only freely associating > *ideas* but switching freely across, and connecting, > radically different *domains* in any given chain of > association. [e.g above from Animals to Economics/Politics > to Weather to Personal Timetable] > > It can do this partly because > > a) single ideas have multiple, often massively mutiple, > idea/domain connections in the human brain, and allow one to > go off in any of multiple tangents/directions > b) humans have many things - and therefore multiple domains > - on their mind at the same time concurrently - and can > switch as above from the immediate subject to some other > pressing subject domain (e.g. from economics/politics > (local vs global) to the weather (what a nice day). > > If your "A-B, everything-is-memory-recall" thesis > were true, our chains-of-thought-association would be > largely repetitive, and the domain switches inevitable.. > > In fact, our chains (or networks) of free association and > domain-switching are highly creative, and each one is > typically, from a purely technical POV, novel and > surprising. (I have never connected TAIL and CURRENT CRISIS > before - though Animals and Politics yes. Nor have I > connected LOCAL VS GLOBAL THINKING before with WHAT A NICE > DAY and the weather). > > IOW I'm suggesting, the natural mode of human thought - > and our continuous streams of association - are creative. > And achieving such creativity is the principal problem/goal > of AGI. > > So maybe it's worth taking 20 secs. of time - producing > your own chain-of-free-association starting say with > "MAHONEY" and going on for another 10 or so items > - and trying to figure out how the result could.possibly be > the narrow kind of memory-recall you're arguing for. > It's an awful lot to ask for, but could you possibly try > it, analyse it and report back? > > [Ben claims to have heard every type of argument I make > before, (somewhat like your A-B memory claim), so perhaps > he can tell me where he's read before about the Freely > Associative, Freely Domain Switching nature of human thought > - I'd be interested to follow up on it]. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
RE: [agi] The Smushaby of Flatway.
A picture is like an instant 1000 words and you will remind a picture almost 70 years but not 1000 words. -Original Message- From: "J. Andrew Rogers" To: agi@v2.listbox.com Sent: 1/8/09 1:59 PM Subject: Re: [agi] The Smushaby of Flatway. On Jan 8, 2009, at 10:29 AM, Ronald C. Blue wrote: > ...Noise is not noise... Speaking of noise, was that ghastly HTML formatting really necessary? It made the email nearly unreadable. J. Andrew Rogers --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?&; Powered by Listbox: http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
On Fri, Jan 9, 2009 at 12:19 AM, Matt Mahoney wrote: > Mike, > > Your own thought processes only seem mysterious because you can't predict > what you will think without actually thinking it. It's not just a property of > the human brain, but of all Turing machines. No program can non-trivially > model itself. (By model, I mean that P models Q if for any input x, P can > compute the output Q(x). By non-trivial, I mean that P does something else > besides just model Q. (Every program trivially models itself). The proof is > that for P to non-trivially model Q requires K(P) > K(Q), where K is > Kolmogorov complexity, because P needs a description of Q plus whatever else > it does to make it non-trivial. It is obviously not possible for K(P) > K(P)). > Matt, please stop. I even constructed an explicit counterexample to this pseudomathematical assertion of yours once. You don't pay enough attention to formal definitions: what this "has a description" means, and which reference TMs specific Kolmogorov complexities are measured in. -- Vladimir Nesov robot...@gmail.com http://causalityrelay.wordpress.com/ --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Ronald C. Blue wrote: [snip] [snip] ... chaos stimulation because ... correlational wavelet opponent > processing machine ... globally entangled ... Paul rf trap ... parallel > modulating string pulses ... a relative zero energy value or opponent process ... phase locked ... parallel opponent process ... reciprocal Eigenfunction ... opponent process ... summation interference ... gaussian reference rf trap ... > oscillon output picture ... locked into the forth harmonic ... > ... entangled with its Eigenfunction .. [snip] That is what entangled memory means. Okay, I got that. But how can it dequark the tachyon antimatter containment field? Richard Loosemore --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
--- On Thu, 1/8/09, Vladimir Nesov wrote: > On Fri, Jan 9, 2009 at 12:19 AM, Matt Mahoney > wrote: > > Mike, > > > > Your own thought processes only seem mysterious > because you can't predict what you will think without > actually thinking it. It's not just a property of the > human brain, but of all Turing machines. No program can > non-trivially model itself. (By model, I mean that P models > Q if for any input x, P can compute the output Q(x). By > non-trivial, I mean that P does something else besides just > model Q. (Every program trivially models itself). The proof > is that for P to non-trivially model Q requires K(P) > > K(Q), where K is Kolmogorov complexity, because P needs a > description of Q plus whatever else it does to make it > non-trivial. It is obviously not possible for K(P) > > K(P)). > > > > Matt, please stop. I even constructed an explicit > counterexample to > this pseudomathematical assertion of yours once. You > don't pay enough > attention to formal definitions: what this "has a > description" means, > and which reference TMs specific Kolmogorov complexities > are measured > in. Your earlier counterexample was a trivial simulation. It simulated itself but did nothing else. If P did something that Q didn't, then Q would not be simulating P. This applies regardless of your choice of universal TM. I suppose I need to be more precise. I say "P simulates Q" if for all x, P("what is Q(x)?") = "Q(x)=y" iff Q(x)=y (where x and y are arbitrary strings). When I say that P does something else, I mean that it accepts at least one input not of the form "what is Q(x)?". I claim that K(P) > K(Q) because any description of P must include a description of Q plus a description of what P does for at least one other input. -- Matt Mahoney, matmaho...@yahoo.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
On Fri, Jan 9, 2009 at 6:04 AM, Matt Mahoney wrote: > > Your earlier counterexample was a trivial simulation. It simulated itself but > did > nothing else. If P did something that Q didn't, then Q would not be > simulating P. My counterexample also bragged, outside the input format that requested simulation. ;-) > > This applies regardless of your choice of universal TM. > > I suppose I need to be more precise. I say "P simulates Q" if for all x, > P("what is Q(x)?") = "Q(x)=y" iff Q(x)=y (where x and y are arbitrary > strings). > When I say that P does something else, I mean that it accepts at least one > input not of the form "what is Q(x)?". This is a step in the right direction. What does it mean for P to NOT accept some input? Must it hang? What it P outputs "I understand you perfectly" for each input not in the form "what is Q(x)?"? (Which was my counterexample IIRC.) > I claim that K(P) > K(Q) because any description of P must include > a description of Q plus a description of what P does for at least one other > input. > Even if you somehow must represent P as concatenation of Q and something else (you don't need to), it's not true that always K(P)>K(Q). It's only true that length(P)>length(Q), and longer strings can easily have smaller programs that output them. If P is 10^(10^10) symbols X, and Q is some random number of X smaller than 10^(10^10), it's probably K(P)http://causalityrelay.wordpress.com/ --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Ronald: I didn't have to choose 'Display images' to see your attached picture again. What are you doing? It's fun, but scary. On 1/9/09, Ronald C. Blue wrote: >> But how can it dequark the tachyon antimatter containment field? >> Richard Loosemore >> > A model that can answer all questions is defective precisely because it can > do so. > > But in your case matter does not exist except at certain time phases as a > standing opponent process informational system from a zero point energy > point of view. An example is the negative phase oscillon in the matter > picture surrounded by electrons oscilating in and out of existence. > > Oscillon pairs with opposite waves form bonding are very stable. This is > like the Pauli exculsion principle. Only electron pairs with opposite spins > can be in orbit together. This is also true for shaddow matter or the > nucleus of an atom. > > > Emotionally I like the idea that anti-matter is matter moving into the past. > But due to vortex > of energy it looks like negative time but it is just like as an old wagon > wheel in a black and white movie looking like it is > colorized and going backwards. 3D is an illusion. > > The above picture supports Anyons and "topological charge" proposed by > Frank Wilczek. > > ((Recommended reading from New Scientist. > Anyons: The breakthrough quantum computing needs? > a.. 01 October 2008 by Don Monroe > b.. Magazine issue 2676. Subscribe and get 4 free issues. > c.. For similar stories, visit the Quantum World Topic Guide > Read full article > Continue reading page |1 |2 |3 > WE SHOULD have known there was something in it when Microsoft got involved. > Back in 2003, the software giant began sponsoring a small research effort > with an interest in an abstruse area of physics known as the fractional > quantum Hall effect. The effect, which has been the subject of two Nobel > prizes, involves the delicate manipulation of electrons inside semiconductor > crystals. What could a software company like Microsoft hope to gain from > funding this research? > > The answer is now clear. This year, we have seen the first indications that > this strange and abstract phenomenon could bring us a revolution in > computing. "We have good reason to believe that, if we can do anything [with > this], we can do a lot," says Michael Freedman of Microsoft-sponsored > Station Q research group in Santa Barbara, California. > > Microsoft is interested because an ability to manipulate the fractional > quantum Hall effect promises a unique and powerful way to process > information using the resources of the subatomic world. Down at the level of > photons, electrons, protons and atoms, matter behaves very differently from > what we are used to. These quantum objects can be in two places at once, for > example, or spin clockwise and anticlockwise at the same time. This > phenomenon, known as superposition, is entirely foreign to the way things > work in the ordinary "classical" world. > > It was realised years ago that superposition provides an opportunity for > information processing, and researchers have been working for decades to > build a "quantum computer" that exploits it. Encode a 0 as the clockwise > spin of an electron and 1 as the anticlockwise spin, for example, and > superposition gives you a kind of "buy one, get one free" special offer, > with both of these binary digits appearing on the same particle. Process one > of these quantum bits, or "qubits", and you get two answers. If you could > create an array of electrons in superposition, it would be possible to use > this phenomenon for superfast processing. In principle, qubits enable huge > sequences of binary digits to be encoded and processed with much less > computational effort than would be needed in the classical world. > > The thing is, while theorists drew up the blueprint for a quantum computer > more than two decades ago, we still don't have one. That is largely because > of a problem called decoherence. Quantum superpositions are notoriously > delicate. If the electron in a superposition state is disturbed - by > something in its environment such as a little heat or a stray > electromagnetic field, say - the superposition will collapse and lose the > double helping of information it was carrying. > > Follow the trail > This is where the fractional quantum Hall effect can help. Quantum particles > are conventionally divided into two types: fermions, such as the electron; > and bosons, such as the photon. Then, about 25 years ago, researchers such > as Frank Wilczek of the Massachusetts Institute of Technology began to > realise there might be a third type. > > The idea came from considering whether you can tell two identical particles > apart from each other. Imagine a quantum version of the magic cup game much > beloved by dodgy street magicians. Two photons, marked A and B, are hidden > under two cups sitting on a table. The magician swaps the cups around on the
Re: [agi] The Smushaby of Flatway.
But how can it dequark the tachyon antimatter containment field? Richard, You missed Mike Tintner's explanation . . . . You're not thinking your argument through. Look carefully at my spontaneous "COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS GLOBAL THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH MORE TIME ON THIS" etc. etc" It can do this partly because a) single ideas have multiple, often massively mutiple, idea/domain connections in the human brain, and allow one to go off in any of multiple tangents/directions b) humans have many things - and therefore multiple domains - on their mind at the same time concurrently - and can switch as above from the immediate subject to some other pressing subject domain (e.g. from economics/politics (local vs global) to the weather (what a nice day). So maybe it's worth taking 20 secs. of time - producing your own chain-of-free-association starting say with "MAHONEY" and going on for another 10 or so items - and trying to figure out how - Original Message - From: "Richard Loosemore" To: Sent: Thursday, January 08, 2009 8:05 PM Subject: Re: [agi] The Smushaby of Flatway. Ronald C. Blue wrote: [snip] [snip] ... chaos stimulation because ... correlational wavelet opponent processing machine ... globally entangled ... Paul rf trap ... parallel > modulating string pulses ... a relative zero energy value or opponent process ... phase locked ... parallel opponent process ... reciprocal Eigenfunction ... opponent process ... summation interference ... gaussian reference rf trap ... > oscillon output picture ... locked into the forth harmonic ... > ... entangled with its Eigenfunction .. [snip] That is what entangled memory means. Okay, I got that. But how can it dequark the tachyon antimatter containment field? Richard Loosemore --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?&; Powered by Listbox: http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Ronald C. Blue wrote: [snip] [snip] ... chaos stimulation because ... correlational wavelet opponent processing machine ... globally entangled ... Paul rf trap ... parallel modulating string pulses ... a relative zero energy value or opponent process ... phase locked ... parallel opponent process ... reciprocal Eigenfunction ... opponent process ... summation interference ... gaussian reference rf trap ... oscillon output picture ... locked into the forth harmonic ... ... entangled with its Eigenfunction .. [snip] That is what entangled memory means. Okay, I got that. But how can it dequark the tachyon antimatter containment field? Richard Loosemore Mark Waser wrote: But how can it dequark the tachyon antimatter containment field? Richard, You missed Mike Tintner's explanation . . . . You're not thinking your argument through. Look carefully at my spontaneous "COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS GLOBAL THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH MORE TIME ON THIS" etc. etc" It can do this partly because a) single ideas have multiple, often massively mutiple, idea/domain connections in the human brain, and allow one to go off in any of multiple tangents/directions b) humans have many things - and therefore multiple domains - on their mind at the same time concurrently - and can switch as above from the immediate subject to some other pressing subject domain (e.g. from economics/politics (local vs global) to the weather (what a nice day). So maybe it's worth taking 20 secs. of time - producing your own chain-of-free-association starting say with "MAHONEY" and going on for another 10 or so items - and trying to figure out how Mark, Right So you think maybe what we've got here is a radical influx of globally entangled free-association bosons? Richard Loosemore --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
iativity and unconnected to the real world, have no way of seeing and otherwise sensing this - or of "having a fresh look" at things.. Matt/Mike, > > Your own thought processes only seem mysterious because you can't predict > what you will think without actually thinking it. It's not just a property > of the human brain, but of all Turing machines. No program can > non-trivially model itself. (By model, I mean that P models Q if for any > input x, P can compute the output Q(x). By non-trivial, I mean that P does > something else besides just model Q. (Every program trivially models > itself). The proof is that for P to non-trivially model Q requires K(P) > > K(Q), where K is Kolmogorov complexity, because P needs a description of Q > plus whatever else it does to make it non-trivial. It is obviously not > possible for K(P) > K(P)). > > So if you learned the associations A-B and B-C, then A will predict C. > That is called "reasoning". > > Also, each concept is associated with thousands of other concepts, not > just A-B. If you pick the strongest associated concept not previously > activated, you get the semi-random thought chain you describe. You can > demonstrate this with a word-word matrix M from a large text corpus, where > M[i,j] is the degree to which the i'th word in the vocabulary is > associated with the j'th word, as measured by the probability of finding > both words near each other in the corpus. Thus, M[rain,wet] and > M[wet,water] have high values because the words often appear in the same > paragraph. Traversing related words in M gives you something similar to > your free association chain like rain-wet-water-... > > -- Matt Mahoney, matmaho...@yahoo.com > > > --- On Thu, 1/8/09, Mike Tintner wrote: > >> From: Mike Tintner >> Subject: Re: [agi] The Smushaby of Flatway. >> To: agi@v2.listbox.com >> Date: Thursday, January 8, 2009, 3:54 PM >> Matt:Free association is the basic way of recalling >> memories. If you experience A followed by B, then the next >> time you experience A you will think of (or predict) B. >> Pavlov demonstrated this type of learning in animals in >> 1927. >> >> Matt, >> >> You're not thinking your argument through. Look >> carefully at my spontaneous >> >> "COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS >> GLOBAL >> THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH >> MORE TIME ON >> THIS" etc. etc" >> >> that's not A-B association. >> >> That's 1. A-B-C then 2. Gamma-Delta then 3. >> Languages then 4. Number of Lines in Letters. >> >> IOW the brain is typically not only freely associating >> *ideas* but switching freely across, and connecting, >> radically different *domains* in any given chain of >> association. [e.g above from Animals to Economics/Politics >> to Weather to Personal Timetable] >> >> It can do this partly because >> >> a) single ideas have multiple, often massively mutiple, >> idea/domain connections in the human brain, and allow one to >> go off in any of multiple tangents/directions >> b) humans have many things - and therefore multiple domains >> - on their mind at the same time concurrently - and can >> switch as above from the immediate subject to some other >> pressing subject domain (e.g. from economics/politics >> (local vs global) to the weather (what a nice day). >> >> If your "A-B, everything-is-memory-recall" thesis >> were true, our chains-of-thought-association would be >> largely repetitive, and the domain switches inevitable.. >> >> In fact, our chains (or networks) of free association and >> domain-switching are highly creative, and each one is >> typically, from a purely technical POV, novel and >> surprising. (I have never connected TAIL and CURRENT CRISIS >> before - though Animals and Politics yes. Nor have I >> connected LOCAL VS GLOBAL THINKING before with WHAT A NICE >> DAY and the weather). >> >> IOW I'm suggesting, the natural mode of human thought - >> and our continuous streams of association - are creative. >> And achieving such creativity is the principal problem/goal >> of AGI. >> >> So maybe it's worth taking 20 secs. of time - producing >> your own chain-of-free-association starting say with >> "MAHONEY" and going on for another 10 or so items >> - and trying to figure out how the result could.possibly be >> the narrow kind of memory-recall you're arguing for. >> It's an awful lot to ask for, but could you possibly try >> it, analyse it and report back? >> >> [Ben claims to have heard every type of argument I make >> before, (somewhat like your A-B memory claim), so perhaps >> he can tell me where he's read before about the Freely >> Associative, Freely Domain Switching nature of human thought >> - I'd be interested to follow up on it]. > --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Mike, after a sequence of free associations, you drift from the original domain. How is that incompatible with the model I described? I use A, B, C, as variables to represent arbitrary thoughts. -- Matt Mahoney, matmaho...@yahoo.com --- On Fri, 1/9/09, Mike Tintner wrote: From: Mike Tintner Subject: Re: [agi] The Smushaby of Flatway. To: agi@v2.listbox.com Date: Friday, January 9, 2009, 10:08 AM I _filtered #yiv455060292 { font-family:Courier;} _filtered #yiv455060292 { font-family:Tms Rmn;} _filtered #yiv455060292 {margin:1.0in 77.95pt 1.0in 77.95pt;} #yiv455060292 P.MsoNormal { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 LI.MsoNormal { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 DIV.MsoNormal { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 H1 { FONT-WEIGHT:normal;FONT-SIZE:12pt;MARGIN:12pt 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 H2 { FONT-WEIGHT:normal;FONT-SIZE:12pt;MARGIN:6pt 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 H3 { FONT-WEIGHT:normal;FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 H4 { FONT-WEIGHT:normal;FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 H5 { FONT-WEIGHT:normal;FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 H6 { FONT-WEIGHT:normal;FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 P.MsoHeading7 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 LI.MsoHeading7 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 DIV.MsoHeading7 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 P.MsoHeading8 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 LI.MsoHeading8 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 DIV.MsoHeading8 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 P.MsoHeading9 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 LI.MsoHeading9 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 DIV.MsoHeading9 { FONT-SIZE:12pt;MARGIN:0in 0in 0pt;FONT-FAMILY:Courier;} #yiv455060292 P.MsoNormalIndent { FONT-SIZE:12pt;MARGIN:0in 0in 0pt 0.5in;FONT-FAMILY:Courier;} #yiv455060292 LI.MsoNormalIndent { FONT-SIZE:12pt;MARGIN:0in 0in 0pt 0.5in;FONT-FAMILY:Courier;} #yiv455060292 DIV.MsoNormalIndent { FONT-SIZE:12pt;MARGIN:0in 0in 0pt 0.5in;FONT-FAMILY:Courier;} #yiv455060292 A:link { COLOR:blue;TEXT-DECORATION:underline;} #yiv455060292 SPAN.MsoHyperlink { COLOR:blue;TEXT-DECORATION:underline;} #yiv455060292 A:visited { COLOR:purple;TEXT-DECORATION:underline;} #yiv455060292 SPAN.MsoHyperlinkFollowed { COLOR:purple;TEXT-DECORATION:underline;} #yiv455060292 P.MsoPlainText { FONT-SIZE:10pt;MARGIN:0in 0in 0pt;FONT-FAMILY:"Courier New";} #yiv455060292 LI.MsoPlainText { FONT-SIZE:10pt;MARGIN:0in 0in 0pt;FONT-FAMILY:"Courier New";} #yiv455060292 DIV.MsoPlainText { FONT-SIZE:10pt;MARGIN:0in 0in 0pt;FONT-FAMILY:"Courier New";} #yiv455060292 DIV.Section1 { } Matt, I mainly want to lay down a marker here for a future discussion. What you have done is what all AGI-ers/AI-ers do. Faced with the problem of domain-switching - (I pointed out that the human brain and human thought are * freely domain-switching*), - you have simply ignored it - and, I imagine, are completely unaware that you have done so. And this, remember, is *the* problem of AGI - what should be the central focus of all discussion here. If you look at your examples, you will find that they are all *intra-domain* and do not address domain-switching at all - a. "if you learned the associations A-B and B-C, then A will predict C. > That is called "reasoning" b) a word-word matrix M from a large text corpus, ..gives you something similar to > your free association chain like rain-wet-water-... No domain-switching there. Compare these with my b) domain-switching chain -"COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS >> GLOBAL >> THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH >> MORE TIME ON >> THIS" (switching between the domains of - Animals - Politics/Economics - Weather - Personal Timetable) a) your (extremely limited) idea of (logical) reasoning is also entirely intra-domain - the domain of the Alphabet, (A-B-C). But my creative and similar creative chains are analogous to switching from say an Alphabet domain (A-B-C) to a Foreign Languages domain (alpha - omega) to a Semiotics one (symbol - sign - representation) to a Fonts one (Courier - Times Roman) etc. etc. - i.e. we could all easily and spontaneously form such a domain-switching chain. Your programs and all the programs ever written are still incapable of doing this - switching domains. This, it bears repeating, is the problem of AGI. Because you're ignor
Re: [agi] The Smushaby of Flatway.
--- On Thu, 1/8/09, Vladimir Nesov wrote: > > I claim that K(P) > K(Q) because any description of P must include > > a description of Q plus a description of what P does for at least one other > > input. > > > > Even if you somehow must represent P as concatenation of Q and > something else (you don't need to), it's not true that always > K(P)>K(Q). It's only true that length(P)>length(Q), and longer strings > can easily have smaller programs that output them. If P is > 10^(10^10) symbols X, and Q is some random number of X smaller > than 10^(10^10), it's probably K(P) substring of P. Well, it is true that you can find |P| < |Q| for some cases of P nontrivially simulating Q depending on the choice of language. However, it is not true on average. It is also not possible for P to nontrivially simulate itself because it is a contradiction to say that P does everything that Q does and at least one thing that Q doesn't do if P = Q. -- Matt Mahoney, matmaho...@yahoo.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
On Fri, Jan 9, 2009 at 6:34 PM, Matt Mahoney wrote: > > Well, it is true that you can find |P| < |Q| for some cases of P nontrivially > simulating Q depending on the choice of language. However, it is not true on > average. It is also not possible for P to nontrivially simulate itself > because it is > a contradiction to say that P does everything that Q does and at least one > thing > that Q doesn't do if P = Q. > What you write above is a separate note unrelated to one about complexity. P simulating P and doing something else is well-defined according to your definition of simulation in the previous message (that includes a special format for request for simulation), no contradictions, and you've got an example. -- Vladimir Nesov --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Richard, You missed Mike Tintner's explanation . . . . Mark, Right So you think maybe what we've got here is a radical influx of globally entangled free-association bosons? Richard, Q.E.D. Well done. Now tell me how you connected my "ridiculous" [or however else you might want to style it] argument with your argument re "bosons" - OTHER than by free association? What *prior* set of associations in your mind, or "prior, preprogrammed set of rules, what logicomathematical thinking enabled you to form that connection? (And it would be a good idea to apply it to your previous joke re Blue - because they must be *generally applicable* principles) And what prior principles enabled you to spontaneously and creatively form the precise association of "radical influx of globally entagled free-association bosons" - to connect RADICAL INFLUX with GLOBALLY ENTANGLED ..and FREE ASSOCIATION and BOSONS. You were being v. funny, right? But humour is domain-switching (which you do multiple times above) and that's what you/AGI can't do or explain computationally. *** Ironically, before I saw your post I had already written (and shelved) a P.S. Here it is: "P.S. Note BTW - because I'm confident you're probably still thinking "what's that weird nutter on about? what's this got to do with AGI?" - the very best evidence for my claim. That claim is now that the brain is * potentially infinitely domain-switching on both a) a basic level, and b) a meta-level - i.e. capable of forming endless new connections/associations on a higher level too and so, forming infinite new modes of reasoning, ( new *ways* of associating ideas as well as new association) The very best evidence are *logic and mathematics themselves*. For logic and mathematics ceaselessly produce new branches of themselves. New logics. New numbers, New kinds of geometry. *New modes of reasoning.* And an absolutely major problem for logic and mathematics (and current computation) is that they *cannot explain themselves* - cannot explain how these new modes of reasoning are generated/ There are no logical and mathematical or other formal ways of explaining these new branches. Rational numbers cannot be used to deduce irrational numbers and thence imaginary numbers. Trigonometry cannot be used to deduce calculus. Euclidean geometry cannot be used to deduce riemannian to deduce topology. And so on. Aristotelian logic cannot explain fuzzy logic cannot explain PLN. Logicomathematical modes of reasoning are *not* generated logicomathematically.but creatively-as both Ben, I think, and certainly Franklin have acknowledged. And clearly the brain is capable of forming infinitely new logics and mathematics - infinite new forms of reasoning - by *non-logicomathematical*/*nonformal* means. By, I suggest, free association among other means. It's easy to make cheap, snide comments. But can either of you actually engage directly with the problem of domain-switching, and argue constructively about particular creative problems and thinking - using actual evidence? I've seen literally no instances from either of you (or indeed, though this may at first seem surprising and may need a little explanation - anyone in the AI community). let's take an actual example of good creative thinking happening on the fly - and what I've called directed free association - It's by one Richard Loosemore. You as well as others thought pretty creatively about the problem of the engram a while back. Here's the transcript of that thinking - as I said, good creative thinking, really trying to have new ideas (as opposed to just being snide here).: Now perhaps you can tell me what prior *logic* or programming produced the flow of your own ideas here? How do you get from one to the next? "Richard: Now you're just trying to make me think ;-). 1. Okay, try this. 2. [heck, you don't have to: I am just playing with ideas here...] 3. The methylation pattern has not necessarily been shown to *only* store information in a distributed pattern of activation - the jury's out on that one (correct me if I'm wrong). 4.5 Suppose that the methylation end caps are just being used as a way station for some mechanism whose *real* goal is to make modifications to some patterns in the junk DNA. 6. So, here I am suggesting that the junk DNA of any particular neuron is being used to code for large numbers of episodic memories (one memory per DNA strand, say), with each neuron being used as a redundant store of many episodes. 7. The same episode is stored in multiple neurons, but each copy is complete. 8. When we observe changes in the methylation patterns, perhaps these are just part of the transit mechanism, not the final destination for the pattern. 9. To put it in the language that Greg Bear would use, the endcaps were just part of the "radio" system. (http://www.gregbear.c
RE: [agi] The Smushaby of Flatway.
In outlook express change format to html and insert picture. Generally this safer than an attachment. -Original Message- From: "Eric Burton" To: agi@v2.listbox.com Sent: 1/9/09 8:03 AM Subject: Re: [agi] The Smushaby of Flatway. Ronald: I didn't have to choose 'Display images' to see your attached picture again. What are you doing? It's fun, but scary. On 1/9/09, Ronald C. Blue wrote: >> But how can it dequark the tachyon antimatter containment field? >> Richard Loosemore >>>>>>>>>>>>>> > A model that can answer all questions is defective precisely because it can > do so. > > But in your case matter does not exist except at certain time phases as a > standing opponent process informational system from a zero point energy > point of view. An example is the negative phase oscillon in the matter > picture surrounded by electrons oscilating in and out of existence. > > Oscillon pairs with opposite waves form bonding are very stable. This is > like the Pauli exculsion principle. Only electron pairs with opposite spins > can be in orbit together. This is also true for shaddow matter or the > nucleus of an atom. > > > Emotionally I like the idea that anti-matter is matter moving into the past. > But due to vortex > of energy it looks like negative time but it is just like as an old wagon > wheel in a black and white movie looking like it is > colorized and going backwards. 3D is an illusion. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway.
Mike, What is the evidence, if any, that it would be difficult for a sophisticated Novamente-like AGI to switch domains? In fact, much of valuable AGI thinking would involve patterns and mental behaviors that extended across different domains. Human natural language understanding is believed to use multiple domains of knowledge in the brain when necessary, such as visual imagination, to help in understanding what is being said or what is to be said. The OpenCog WikiBook describes multiple procedures for controlling, and automatically learning to control inference, activation, and procedure execution. This could be used to accomplish sophisticated interaction of knowledge from different domains, much as the human brain does. Brain studies conducted by Wolf Singer indicate that the brain synchronies can be used to interconnect portions of the brain with different areas of expertise when performing a job that requires one of those areas to tune into information coming from the other. It would be easy to make an AGI do something equivalent. In fact, in routine tasks, the synchronies are often set up in advance of there being an activation in some of the regions connected by them, because the brain has learned from prior inferencing patterns to expect such activations to arise given the task being performed. Ed Porter --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com <>
Re: [agi] The Smushaby of Flatway.
On Thu, Jan 8, 2009 at 10:41 AM, Ed Porter wrote: > Ed Porter> > > This is certainly not true of a Novamente-type system, at least as I > conceive of it being built on the type of massively parallel, highly > interconnected hardware that will be available to AI within 3-7 years. Such > a system would be hierarchical in both the compositional and > generalizational dimensions, and the computation would be taking place by > importance weighted probabilisitic spreading activation, constraint > relaxation, and k-winner take all competition across multiple layers of > these hierarchies, so the decision making would not "funnel all reasoning > through a single narrowly focused process" any more that human though > processes do. > > > If a decision is to be made, it makes computational sense to have some > selection process that focuses attention on a selected one of multiple > possible candidate actions or > > though. If that is the type of "funneling" that you object to, you are > largely objecting to decision making itself. I have been busy and I just started reading the remarks on this thread. I want to reply to Ed's comment since his remarks seemed to be focused in on what I said. (And I was able to understand what he was talking about!) Parallel methods do not in of themselves constitute what I call structural reasoning. I object to the funneling and flat methods of reasoning itself. Although I do not have any new alternatives to add to logic, fuzzy logic, probability, genetic algorithms and various network decision processes, my objection is directed toward the narrow focus on the fundamentals of those decision making processes, or to the creative (but somewhat dubious) steps taken to force the data to conform to the inadequacies of (what I called) flat decision processes. For instance, when it is discovered that probabilistic reasoning isn't quite good enough for advanced nlp, many hopefuls will rediscover the creative 'solution' of using orthogonal multidimensional 'measures' of semantic distance. Instead of following their intuition and coming up with ways to make the reasoning seem more natural, they first turn toward a more fanciful method by which they try to force the corpus of natural language to conform to their previously decision to use a simple metric. My recommendation would be to first try to begin thinking about how natural reasoning might be better structured to solve those problems before you start distorting the data. For an example, reasons are often used in natural reasoning. A reason can be good or bad. A reason can provide causal information about the reasoning but even a good reason may only shed light on information incidental to the reasoning. The value of a reason can be relative to both the reasoning and the nature of the supplied reason itself. My point here is that the relation of reason to reasoning is significant (especially when they work) although it can be very complicated. But even though the use of a reason is not simple, notice how natural and familiar it seems. Example: 'I do this because I want to!' Not a good reason to explain why I am doing something unless you are (for instance) curious about the emotional issues behind my actions. Another example: "I advocate this theory because it seems natural!" A much better reason for the advocacy. It tells you something about what is motivating me to make the advocacy but it also tells you something about the theory as it is being advocated. There are other kinds of structures to reasoning that can be considered as well. This was only one. I realized during the past few days, that most reasoning in a contemporary AGI program would be ongoing and so yes the reasoning would be more structured than I originally thought. (I wouldn't have written my original message at all except that I was a little more off than usual that night for some reason.) However, even though ongoing reasoning does represent some additional complexity to the process of reasoning, the fact that structural reasoning itself is not being discussed means that it is being downplayed and even ignored. So you have the curious situation where the less natural metric of semantic distance being enthusiastically offered while a more complete examination of the potential of using natural reasons in reasoning is almost totally ignored. So while I believe that modifications and extensions of logic, categorical systems, probability, and network decision processes will be used to eventually create more powerful AGI programs, I don't think the contemporary efforts to produce such advanced AGI will be successful without the conscious consideration and use of structural reasoning. Jim Bromer --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=1
Re: [agi] The Smushaby of Flatway.
Mike Tintner wrote: Richard, You missed Mike Tintner's explanation . . . . Mark, Right So you think maybe what we've got here is a radical influx of globally entangled free-association bosons? Richard, Q.E.D. Well done. Now tell me how you connected my "ridiculous" [or however else you might want to style it] argument with your argument re "bosons" - OTHER than by free association? What *prior* set of associations in your mind, or "prior, preprogrammed set of rules, what logicomathematical thinking enabled you to form that connection? (And it would be a good idea to apply it to your previous joke re Blue - because they must be *generally applicable* principles) And what prior principles enabled you to spontaneously and creatively form the precise association of "radical influx of globally entagled free-association bosons" - to connect RADICAL INFLUX with GLOBALLY ENTANGLED ..and FREE ASSOCIATION and BOSONS. You were being v. funny, right? But humour is domain-switching (which you do multiple times above) and that's what you/AGI can't do or explain computationally. *** Ironically, before I saw your post I had already written (and shelved) a P.S. Here it is: "P.S. Note BTW - because I'm confident you're probably still thinking "what's that weird nutter on about? what's this got to do with AGI?" - the very best evidence for my claim. That claim is now that the brain is * potentially infinitely domain-switching on both a) a basic level, and b) a meta-level - i.e. capable of forming endless new connections/associations on a higher level too and so, forming infinite new modes of reasoning, ( new *ways* of associating ideas as well as new association) The very best evidence are *logic and mathematics themselves*. For logic and mathematics ceaselessly produce new branches of themselves. New logics. New numbers, New kinds of geometry. *New modes of reasoning.* And an absolutely major problem for logic and mathematics (and current computation) is that they *cannot explain themselves* - cannot explain how these new modes of reasoning are generated/ There are no logical and mathematical or other formal ways of explaining these new branches. Rational numbers cannot be used to deduce irrational numbers and thence imaginary numbers. Trigonometry cannot be used to deduce calculus. Euclidean geometry cannot be used to deduce riemannian to deduce topology. And so on. Aristotelian logic cannot explain fuzzy logic cannot explain PLN. Logicomathematical modes of reasoning are *not* generated logicomathematically.but creatively-as both Ben, I think, and certainly Franklin have acknowledged. And clearly the brain is capable of forming infinitely new logics and mathematics - infinite new forms of reasoning - by *non-logicomathematical*/*nonformal* means. By, I suggest, free association among other means. It's easy to make cheap, snide comments. But can either of you actually engage directly with the problem of domain-switching, and argue constructively about particular creative problems and thinking - using actual evidence? I've seen literally no instances from either of you (or indeed, though this may at first seem surprising and may need a little explanation - anyone in the AI community). let's take an actual example of good creative thinking happening on the fly - and what I've called directed free association - It's by one Richard Loosemore. You as well as others thought pretty creatively about the problem of the engram a while back. Here's the transcript of that thinking - as I said, good creative thinking, really trying to have new ideas (as opposed to just being snide here).: Now perhaps you can tell me what prior *logic* or programming produced the flow of your own ideas here? How do you get from one to the next? "Richard: Now you're just trying to make me think ;-). 1. Okay, try this. 2. [heck, you don't have to: I am just playing with ideas here...] 3. The methylation pattern has not necessarily been shown to *only* store information in a distributed pattern of activation - the jury's out on that one (correct me if I'm wrong). 4.5 Suppose that the methylation end caps are just being used as a way station for some mechanism whose *real* goal is to make modifications to some patterns in the junk DNA. 6. So, here I am suggesting that the junk DNA of any particular neuron is being used to code for large numbers of episodic memories (one memory per DNA strand, say), with each neuron being used as a redundant store of many episodes. 7. The same episode is stored in multiple neurons, but each copy is complete. 8. When we observe changes in the methylation patterns, perhaps these are just part of the transit mechanism, not the final destination for the pattern. 9. To put it in the language that Greg Bear would use, the endcaps were just part of the "radio" system.
Re: [agi] The Smushaby of Flatway.
On Sat, Jan 10, 2009 at 3:47 PM, Jim Bromer wrote: > For instance, when it is discovered that probabilistic reasoning isn't > quite good enough for advanced nlp, many hopefuls will rediscover the > creative 'solution' of using orthogonal multidimensional 'measures' of > semantic distance. Instead of following their intuition and coming up > with ways to make the reasoning seem more natural, they first turn > toward a more fanciful method by which they try to force the corpus of > natural language to conform to their previously decision to use a > simple metric. > > My recommendation would be to first try to begin thinking about how > natural reasoning might be better structured to solve those problems > before you start distorting the data. > > For an example, reasons are often used in natural reasoning. A reason > can be good or bad. A reason can provide causal information about the > reasoning but even a good reason may only shed light on information > incidental to the reasoning. The value of a reason can be relative to > both the reasoning and the nature of the supplied reason itself. My > point here is that the relation of reason to reasoning is significant > (especially when they work) although it can be very complicated. But > even though the use of a reason is not simple, notice how natural and > familiar it seems. I realized after I wrote this that the invented metric of semantic distance can be used to 'solve' a semantic problem using mathematical means. In my suggestion that more highly structured methods of reasoning should be considered before distorting the data with some artifice I pointed out that reasons that are naturally used in decision making could be included in the structure of reasoning . But the problem is, of course, that examining the reasons for a conclusion does not immediately -solve- the programming problem the way numerical metrics and mathematical methods can. Ok, but you can still create artificial methods to test structural reasoning if you are eager to start programming. I am going to try this out because I believe that a somewhat extensible GOFAI model can be derived from a use of structured reasoning (and some other ideas I have) even though I would have to first supply simplistic 'solutions' for the program to use. I am saying that before you start creating elaborate artifices to jump start your project you should first use your intuition to see if more natural ways of dealing with the problem exist. This might not make the problem look easier. But even though I would have to create some simplistic solutions for my first model, I believe that the concept of more highly structured reasoning should help me keep these artifices to a minimum. Jim Bromer --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=126863270-d7b0b0 Powered by Listbox: http://www.listbox.com
Re: [agi] The Smushaby of Flatway...PS
PS I should have said "the fundamental deficiencies of the PURELY logicomathematical form of thinking". It's not deficient in itself - only if you think like so many AGIers that it's the only form of thinking, or able to accommodate the entirety of human thinking. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
Free Association, Creativity and AGI (was RE: [agi] The Smushaby of Flatway.)
Hi Mike (Tintner), You've often made bold claims about what "all AGIers" do or don't do. This is despite the fact that you haven't met me in person and I haven't revealed many of my own long term plans on this list (and I'm sure I'm not the only one): you're making bold claims about *all* of us, without actually knowing what we're *all* doing. When you first joined the group, I tried to point out that many AGI and AI people are trying to do the very thing that you claim we aren't doing (and many others have similar done likewise). Please don't talk about "all AGIers" until you have met every single one. Anyway, for the point of discussion I thought I'd give your "ideas" a moment and actually try your suggestions. You sometimes you talk about the grand goals of AGI and complex human behaviours, as though you're the only one who sees this. This isn't necessary, most of us share such goals - I can see this in the work of any researcher in the area. These grand goals, however, are quite difficult and it will take time to get there. What we need is a plan on how to get there, and some kind of easier-to-reach stepping stones along the way. These stepping stones are what characterizes most current research... steps, that I believe clearly point towards the long term objective. You seem to think that these steps have nothing to do with the real problem. It appears that you view artistic acts as the crucial problem of intelligence. So let us look at free association, as you have recently done. I found your free association lists silly and nonsensical. For example, in one list you "free associate" nose with Afghanistan and oxygen with eyes. They seem silly because the association depends on some hidden steps (that you only explained later). I think the lists would be a lot better if you made the steps explicit. (e.g., replace oxygen-eyes with something like oxygen-invisible-eyes or oxygen-everywhere-visible-eyes, or whatever it was that you were thinking). Okay. So, let's keep it simple. Let's do free association where each step has to make some kind of sense, and where we only deal with single words. Surely this is a sensible stepping stone to AGI? Well, as Matt said, this actually turns out to be quite simple. I've put together a "free association" machine. Give it a fairly common word, and it will free-associate from there to create a list of 15 words. http://www.comirit.com/freeassoc/ Every single list will be unique. Every single list combines randomness with structure. Every list crosses domains, and if you compare the first word to the last word (in light of the words in-between) you see that a very original kind of analogy has apparently taken place. This is, as far as I can tell, what you've been talking about. But this isn't AGI. This isn't even interesting AI. I hope that you're also ready to give your own argument for why it isn't AGI. The thing is, however, that something like this free association machine seems to be the very thing that you're pointing to. A similar approach can be used to generate somewhat-structured and somewhat-unstructured drawings like on that imagination3 site that you thought could be the basis of a mathematical formalization. (I'm not going to tell you how it works - it uses a very dirty trick - the point is, though, that it gives the appearance of intelligence and seems to do what you want it to do) It didn't take me long to put this together - in fact, the hardest bit was just working out how to upload it to my server. I think creativity and artistic expression are poor choices for exploring AGI, they are too subjective to be measured and it seems easier to fool people into thinking a pattern looks creative and artistic than it is to create a pattern that solves some measurable problem. However, when I begin to speculate what I would need to do to improve the free association machine to make it into an interesting piece of AI, I find that logics, probabilistic logics, evolutionary learning, search, complex systems, structure mapping, neural networks would all jump out as interesting avenues to explore. In other words, creativity and artistic expression bring us to EXACTLY the same core problems; but in a domain that seems to me to be less amenable to productive, measurable or even profit-generating research. It certainly isn't a given that creativity and art is the only approach to AGI. In fact, after we get over that very first hurdle of making something appear to be artistic, we're at exactly the same problems that are encountered in every other problem domain: problems of learning and building problem-solving representations automatically - the very problems that motivate AGI researchers every day. So, I tried your suggestion. After getting past that first step of writing the version-zero free associator, I found myself in exactly the same place as I was before and facing exactly the same problems, but in a problem domain that is less useful that what