Re: Worthwhile time sinks was Re: [agi] list vs. forum
On 13/06/06, sanjay padmane [EMAIL PROTECTED] wrote: On the suggestion of creating a wiki, we already have it here http://en.wikipedia.org/wiki/Artificial_general_intelligence I wouldn't want to pollute the wiki proper with our unverified claims. , as you know, and its exposure is much wider. I feel, wiki cannot be a good format for discussions. No one would like their views edited out by a random It is not meant so much to replace our discussions on list but to display the various questions people have asked and the various answers to them in a persistant and easy to use fashion. Will --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: Worthwhile time sinks was Re: [agi] list vs. forum
On Tue, Jun 13, 2006 at 05:05:56AM +0530, sanjay padmane wrote: Even though only a few have reacted to my (somewhat threatening ;-) ) proposal to discontinue this list, it seems that people are comfortable with I would call it a troll. it, anyhow... You seem to be new to the Internet. I suggest you take it slow, and do your research instead of posting reflexively on merits of technology you're not familiar with. Someone can experiment with automated posting of all forum messages to the Hey, it was your suggestion, you do it. Just download the list manager, and hack it. It's easy, right? And don't forget automatic cathegorization, plaintext and multipart support, and a search engine, and anti-spam measures, and authentication, and to make my browser spawn my favourite editor, instead of pasting into a form, and server-side filtering, and distributed archives, and push, while you're at it. And don't forget to build a community about your project, in order to support it, and to issue security fixes for the hundreds of bugs you'll find in a new project of such complexity. Gosh, email is sure retarded, having all these features a forum doesn't have, and you'll find are absolutely trivial to implement. Get back to us when you're done, will you? list, as and when they are created. Speaking of high quality, you are the best person to do that :-). As I'm only starting in Agi etc, I've only questions and speculations to post. I've not done that because I'm afraid of sinking agi-forums to the level of agi-n00b-forums. But I'll take that risk someday, I can delete the post (unlike in a list), if it sounds too low quality. That's not a bug, that's a feature. And you can't edit my local inbox, and it won't go away when the machine with the list archives dies (trust me, eventually they all do). On the suggestion of creating a wiki, we already have it here http://en.wikipedia.org/wiki/Artificial_general_intelligence , as you know, and its exposure is much wider. I feel, wiki cannot be a good format for discussions. No one would like their views edited out by a random user. It serves the purpose best, when the knowledge is already established. -- Eugen* Leitl a href=http://leitl.org;leitl/a http://leitl.org __ ICBM: 48.07100, 11.36820http://www.ativel.com 8B29F6BE: 099D 78BA 2FD3 B014 B08A 7779 75B0 2443 8B29 F6BE --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] signature.asc Description: Digital signature
Re: Worthwhile time sinks was Re: [agi] list vs. forum
On 13/06/06, Yan King Yin [EMAIL PROTECTED] wrote: Will, I've been thinking of hosting a wiki for some time, but not sure if we have reached critical mass here. Possibly not. I may just collate my own list of questions and answers until the time does come. When we get down to the details, people's views may diverge even further. I can think of some potential points of disagreement: 0. what's the overall AGI architecture? 1. neurally based or logic based? I think this question would be better as analog or digital. While the system I am interested in uses logical operations (AND, OR etc) for running a program, I do not expect it to be constrained to be logical in the everday sense. 2. what's the view on Friendliness? 3. initially, self-improving or static? I think the distinction would need to be between static, weakly self-improving (like the human brain) and strongly self-improving. 4. open source or not? 5. commercial or not? I would also add 6. Does specialist hardware need to be made to make AGI practical? 7. Do you deal with combinatorial explosions in your AGI, if not why not? 7. Similarly for the No free lunch theorems. May be we can set up a simple poll place to see who agrees with whom?? It might be hard to keep the poll simple Will --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Mentifex AI Breakthrough on Wed.7.JUN.2006
Hi, Well, let me waste a little bit of time: Distinguish homonyms from context? I believe so, because the current AI uses ASCII characters, not phonemes. Hilarious. Represent the concept of a homonym? At this stage, I am not sure. Which shows how sure you are about the fact that it's really intelligent. Can it handle deixis? Since I have a degree in ancient Greek and briefly attended U Cal Berkeley graduate school in classics, I know that deixis from deiknumi means pointing or showing, and so I must admit that the AI is not far enough along to show things. It is an implementation of the simplest thinking that I can muster -- a proof of concept program. Since I have hands and know how to use a search engine, I can point you to these pages: http://dictionary.reference.com/browse/deixis http://en.wikipedia.org/wiki/Deixis It would most likely be extremely difficult if not impossible to port Mind.Forth into circa 1982 Sinclair Spectrum BASIC. Why, because of memory issues? Sarcastic regards, Ricardo Barreira --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: Worthwhile time sinks was Re: [agi] list vs. forum
On 6/13/06, William Pearson [EMAIL PROTECTED] wrote: It is not meant so much to replace our discussions on list but todisplay the various questions people have asked and the variousanswers to them in a persistant and easy to use fashion. Will Well I'm not sure if this requires group effort. If someone is really interested, one can start by compiling the material scattered in the list.Sanjay To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
[agi] How the Brain Represents Abstract Knowledge
Hi all, Well, this list seems more active than it has been for a while, but unfortunately this increased activity does not seem to be correlated with a more profound intellectual content ;-) So, I'm going to make a brazen attempt to change the subject, and start a conversation about an issue that perplexes me. The issue is: how might NNs effectively represent abstract knowledge? [Note that I do not pick a discussion topic related to my own Novamente AGI project. That is because at the present time there is nothing about Novamente that really perplexes me... we are in a phase of (too slowly, due to profound understaffing) implementing our design and experimenting with it, and at the present time don't see any need to re-explore the basic concepts underlying the system. Perhaps experimentation will reveal such a need in time...] There are a number of reasons that I chose to use a largely logic-based knowledge representation in the Novamente system: 1) This will make it easier to import knowledge from DBs or from the output of rule-based NLP systems, when the system is at an intermediate stage of development. [When the Novamente system is mature, it will be able to read DB's and NLP itself without help; and now when it is very young and incomplete it would be counterproductive to feed it DB or NLP knowledge, as it lacks the experientially learned conceptual habit-patterns required to interpret this knowledge for itself.] 2) While I considered using a more centrally neural net based knowledge representation, I got stuck on the problem of how to represent abstract knowledge using neural nets. So, Novamente's KR has the following aspects: -- explicit logic-type representation of knowledge -- knowledge-items and their components are tagged with numbers indicating importance levels, which act slightly like time-averages of Hopfield net activations -- implicit knowledge can be represented as patterns of activity/importance across the network This is all very well for Novamente -- which is not intended to be brainlike -- BUT, I am still perplexed by the question of how the brain (or a brain-emulating formal neural net architecture) represents abstract knowledge. So far as I know none of the brain-emulating would-be-AGI architectures I have seen address this issue very well. Hawkins' architecture, for instance, doesn't really tell you how to represent and manipulate an abstract function with variables... Say, a category like people who have the property that there is exactly one big scary thing they are afraid of. How does the brain represent this? How would a useful formal neural net model represent this? I am aware that this is in principle representable using neural net mathematics, as McCullough and Pitts showed long about that simple binary NNs are Turing-complete. But this is not the issue. The issue is how such knowledge can/should be represented in NNs in a way that supports flexible learning and reasoning... It seems to me that simple probabilistic logical inference can be seen as parallel to Hebbian learning, for instance A implies B B implies C |- A implies C is a lot like Hebbian learning which given the connections A -- B -- C may cause the reinforcement of A -- C But I know of no similarly natural mapping from the logic of more complex (e.g. quantified) predicates into neural-net structures and operations. Anyone have any special knowledge, or any interesting ideas, on this topic? -- Ben G --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
[agi] How the Brain Represents Abstract Knowledge
Ben The issue is: how might NNs effectively represent abstract Ben knowledge? ... Ben So far as I know none of the brain-emulating would-be-AGI Ben architectures I have seen address this issue very well. Hawkins' Ben architecture, for instance, doesn't really tell you how to Ben represent and manipulate an abstract function with variables... Ben Say, a category like people who have the property that there is Ben exactly one big scary thing they are afraid of. How does the Ben brain represent this? How would a useful formal neural net model Ben represent this? Ben, I'd point you to Les Valiant's book Circuits of the Mind for a serious attempt to answer precisely such questions. It's been years since I read it, and my recollection is hazy, so I won't attempt much of a summary. The book posits units of several (hundred?) neurons called neuroids that act as finite state machines with various properties, and then gives algorithms by which the whole system could be programmed to learn, for example, concepts of exactly the type you ask. --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
Hi, I just found that Les has several new papers on the subject and related subjects at http://people.deas.harvard.edu/~valiant/ Ben, I'd point you to Les Valiant's book Circuits of the Mind for a serious attempt to answer precisely such questions. It's been years since I read it, and my recollection is hazy, so I won't attempt much of a summary. The book posits units of several (hundred?) neurons called neuroids that act as finite state machines with various properties, and then gives algorithms by which the whole system could be programmed to learn, for example, concepts of exactly the type you ask. Ben Thanks, I will check it out... Ben Ben Ben --- To unsubscribe, change your address, or temporarily Ben deactivate your subscription, please go to Ben http://v2.listbox.com/member/[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
Ben Goertzel wrote: Hi all, Well, this list seems more active than it has been for a while, but unfortunately this increased activity does not seem to be correlated with a more profound intellectual content ;-) So, I'm going to make a brazen attempt to change the subject, and start a conversation about an issue that perplexes me. The issue is: how might NNs effectively represent abstract knowledge? [Note that I do not pick a discussion topic related to my own Novamente AGI project. That is because at the present time there is nothing about Novamente that really perplexes me... we are in a phase of (too slowly, due to profound understaffing) implementing our design and experimenting with it, and at the present time don't see any need to re-explore the basic concepts underlying the system. Perhaps experimentation will reveal such a need in time...] There are a number of reasons that I chose to use a largely logic-based knowledge representation in the Novamente system: 1) This will make it easier to import knowledge from DBs or from the output of rule-based NLP systems, when the system is at an intermediate stage of development. [When the Novamente system is mature, it will be able to read DB's and NLP itself without help; and now when it is very young and incomplete it would be counterproductive to feed it DB or NLP knowledge, as it lacks the experientially learned conceptual habit-patterns required to interpret this knowledge for itself.] 2) While I considered using a more centrally neural net based knowledge representation, I got stuck on the problem of how to represent abstract knowledge using neural nets. So, Novamente's KR has the following aspects: -- explicit logic-type representation of knowledge -- knowledge-items and their components are tagged with numbers indicating importance levels, which act slightly like time-averages of Hopfield net activations -- implicit knowledge can be represented as patterns of activity/importance across the network This is all very well for Novamente -- which is not intended to be brainlike -- BUT, I am still perplexed by the question of how the brain (or a brain-emulating formal neural net architecture) represents abstract knowledge. So far as I know none of the brain-emulating would-be-AGI architectures I have seen address this issue very well. Hawkins' architecture, for instance, doesn't really tell you how to represent and manipulate an abstract function with variables... Say, a category like people who have the property that there is exactly one big scary thing they are afraid of. How does the brain represent this? How would a useful formal neural net model represent this? I am aware that this is in principle representable using neural net mathematics, as McCullough and Pitts showed long about that simple binary NNs are Turing-complete. But this is not the issue. The issue is how such knowledge can/should be represented in NNs in a way that supports flexible learning and reasoning... It seems to me that simple probabilistic logical inference can be seen as parallel to Hebbian learning, for instance A implies B B implies C |- A implies C is a lot like Hebbian learning which given the connections A -- B -- C may cause the reinforcement of A -- C But I know of no similarly natural mapping from the logic of more complex (e.g. quantified) predicates into neural-net structures and operations. Anyone have any special knowledge, or any interesting ideas, on this topic? Yes! Very much so. (And thanks for asking a question that raises the level of discussion so dramatically). Back in the early connectionist days (1986/7) - when McClelland and Rumelhart had just released their two PDP books - there was a lot of variation in how the neural net idea was interpreted. In particular, you will find in the PDP books some discussion of the concept of a neurally inspired architecture was very much on everyone's mind: in other words, we don't have to take the simulated neurons too literally, because what was really important was having systems that worked in the general way that NNs seemed to work: lots of parallelism, redundancy, distributed information in the connections, active computing units, relaxation, etc. More importantly, there were some (Don Norman's name comes to mind: I think he wrote the concluding chapter of the PDP boks) who specifically cautioned against ignoring some important issues that seemed problematic for simple neural nets. For example, how does a neural net represent multiple copies of things, and how does it distinguish instances of things from generic concepts? These are particularly thorny for distributed representations of course: can't get two concepts in one of those at the same time, so how can we represent anything structured? What happened after that, in my opinion, was that *because* some types of neural net (backprop,
Re: [agi] How the Brain Represents Abstract Knowledge
On 6/13/06, Ben Goertzel [EMAIL PROTECTED] wrote: The issue is: how might NNs effectively represent abstract knowledge? With difficulty! Okay, to put it in a less facetious-sounding way: It is worth bearing in mind that biological neural nets are _very bad_ at syntactic symbol manipulation; consider the mindboggling sophistication and computing power in a dolphin's brain, for example, and note that it is completely incapable of doing any such thing. Even humans aren't particularly good at it: our present slow, simple, crude computers can do things like symbolic differentiation millions of times faster and more accurately than we can. The point being, we tend to try to answer how questions by looking for simple, efficient methods - but biology suggests (albeit doesn't prove) that the reason we can't see a simple, efficient way for NNs to handle syntactic knowledge is that there isn't one; that researchers trying to use NNs or the like for AGI may have to bite the bullet and look for complex, expensive solutions to this problem. (My own reaction to this is the same as yours, incidentally: to go straight for symbolic mechanisms as fundamental components in the belief that this plays better to the strengths of digital hardware. That doesn't mean NNs can't succeed, but it does suggest that they'll have to hit this problem head-on and resign themselves to throwing a lot of resources at it, in somewhat the same way that we on the symbolic side of the fence will have to resign ourselves to throwing a lot of resources at problems like visual perception.) To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
On Tue, Jun 13, 2006 at 04:15:35PM +0100, Russell Wallace wrote: Okay, to put it in a less facetious-sounding way: It is worth bearing in mind that biological neural nets are _very bad_ at syntactic symbol manipulation; consider the mindboggling sophistication and computing power in a dolphin's brain, for example, and note that it is completely incapable Representing and manipulating formal system is a very recent component in the fitness function, and hence not well-optimized. of doing any such thing. Even humans aren't particularly good at it: our present slow, simple, crude computers can do things like symbolic differentiation millions of times faster and more accurately than we can. And how little it does help them to navigate reality. The point being, we tend to try to answer how questions by looking for simple, efficient methods - but biology suggests (albeit doesn't prove) that the reason we can't see a simple, efficient way for NNs to handle syntactic knowledge is that there isn't one; that researchers trying to use NNs or the like for AGI may have to bite the bullet and look for complex, expensive solutions to this problem. The world is complicated. There are no simple solutions that work over all domains in the real word. (My own reaction to this is the same as yours, incidentally: to go straight for symbolic mechanisms as fundamental components in the belief that this plays better to the strengths of digital hardware. That doesn't mean NNs What are the strenghts of digital hardware, in your opinion? can't succeed, but it does suggest that they'll have to hit this problem head-on and resign themselves to throwing a lot of resources at it, in somewhat the same way that we on the symbolic side of the fence will have to resign ourselves to throwing a lot of resources at problems like visual perception.) Human resources, or computational resources? If computational resources, which architecture? -- Eugen* Leitl a href=http://leitl.org;leitl/a http://leitl.org __ ICBM: 48.07100, 11.36820http://www.ativel.com 8B29F6BE: 099D 78BA 2FD3 B014 B08A 7779 75B0 2443 8B29 F6BE --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] signature.asc Description: Digital signature
Re: [agi] How the Brain Represents Abstract Knowledge
On 6/13/06, Eugen Leitl [EMAIL PROTECTED] wrote: Representing and manipulating formal system is a very recent componentin the fitness function, and hence not well-optimized. True; but I will claim that no matter how much you optimize a biological neural net, it will always have characteristics such as being slow at serial computation, and relatively imprecise. The world is complicated. There are no simple solutions that work overall domains in the real word. Yep. What are the strenghts of digital hardware, in your opinion? Fast serial calculation. Very high precision. Extreme flexibility in choice of operations and instant rewiring of data structures. Human resources, or computational resources? Both. If computational resources,which architecture? I don't understand the question, please clarify? To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
On Tue, Jun 13, 2006 at 04:38:49PM +0100, Russell Wallace wrote: Representing and manipulating formal system is a very recent component in the fitness function, and hence not well-optimized. True; but I will claim that no matter how much you optimize a biological neural net, it will always have characteristics such as being slow at serial computation, and relatively imprecise. No disagreement. But you don't have to use live cells to build a computational network. As to imprecise, with scaling down geometry and ramping up switching speed digital is no longer well-defined. With many small switches you're also getting reliability problems, so noise begins to creep in at the hardware layer. Fast serial calculation. In comparison to biological neurons, yes. Very high precision. Extreme flexibility in choice I don't see why an automaton network can't use many bits to represent things. There's also some question for what you need very high precision. Cryptography is a candidate, another one is physical modelling doing it like a mathematician. I think there is a very distinct bias, almost an agnosia if you want to do it not like a mathematician. of operations and instant rewiring of data structures. You can't actually rewire the circuit, so you have to switch state which reprsents the circuit. It's easier if you embrace the model of dynamically traced out circuitry in a computational substrate. Very few things are instant in a current memory-bottlenecked digital computers. If you want to widen that bottleneck, you first get a massively parallel box, and eventually a cellular/mosaic architecture of simple computational elements. If computational resources, which architecture? I don't understand the question, please clarify? If you want to build a robot capable of playing tennis in a heavy hail, how would you do it? -- Eugen* Leitl a href=http://leitl.org;leitl/a http://leitl.org __ ICBM: 48.07100, 11.36820http://www.ativel.com 8B29F6BE: 099D 78BA 2FD3 B014 B08A 7779 75B0 2443 8B29 F6BE --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] signature.asc Description: Digital signature
[agi] Architecture
On 6/13/06, Eugen Leitl [EMAIL PROTECTED] wrote: You can't actually rewire the circuit, so you haveto switch state which reprsents the circuit. It's easierif you embrace the model of dynamically traced outcircuitry in a computational substrate. Very fewthings are instant in a current memory-bottlenecked digital computers. If you want to widen that bottleneck,you first get a massively parallel box, and eventuallya cellular/mosaic architecture of simple computationalelements. Sure, ultimate computronium might plausibly look like that. Right now human brains and Opteron chips are the best hardware we have, and it seems to me that smart software optimized for the latter shouldn't be a very close copy of smart software optimized for the former. If you want to build a robot capable of playing tennisin a heavy hail, how would you do it? Well if that was _all_ I wanted it to do I'd just write the code in C++ :) But for the general problem of AI, I think the best approach is roughly along the same lines as Novamente. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
This thread has completely missed Ben's original point, surely. It has nothing to do with whether neurons are faster/better/whatever than digital circuits, it has to do with the way that artificial neurons are used in current NN systems to represent information. The fact that neurons are slower than digital systems is a trivial difference between them. That doesn't make them inherently less capable of doing syntax, for example. Richard Loosemore. Eugen Leitl wrote: On Tue, Jun 13, 2006 at 04:38:49PM +0100, Russell Wallace wrote: Representing and manipulating formal system is a very recent component in the fitness function, and hence not well-optimized. True; but I will claim that no matter how much you optimize a biological neural net, it will always have characteristics such as being slow at serial computation, and relatively imprecise. No disagreement. But you don't have to use live cells to build a computational network. As to imprecise, with scaling down geometry and ramping up switching speed digital is no longer well-defined. With many small switches you're also getting reliability problems, so noise begins to creep in at the hardware layer. Fast serial calculation. In comparison to biological neurons, yes. Very high precision. Extreme flexibility in choice I don't see why an automaton network can't use many bits to represent things. There's also some question for what you need very high precision. Cryptography is a candidate, another one is physical modelling doing it like a mathematician. I think there is a very distinct bias, almost an agnosia if you want to do it not like a mathematician. of operations and instant rewiring of data structures. You can't actually rewire the circuit, so you have to switch state which reprsents the circuit. It's easier if you embrace the model of dynamically traced out circuitry in a computational substrate. Very few things are instant in a current memory-bottlenecked digital computers. If you want to widen that bottleneck, you first get a massively parallel box, and eventually a cellular/mosaic architecture of simple computational elements. If computational resources, which architecture? I don't understand the question, please clarify? If you want to build a robot capable of playing tennis in a heavy hail, how would you do it? - This message was sent using Endymion MailMan. http://www.endymion.com/products/mailman/ --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
On 6/13/06, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: This thread has completely missed Ben's original point, surely. It diverged certainly, which is why I changed the subject heading for my latest reply. It has nothing to do with whether neurons are faster/better/whatever thandigital circuits, it has to do with the way that artificial neurons are used in current NN systems to represent information.The fact that neurons are slower than digital systems is a trivialdifference between them.That doesn't make them inherently less capable ofdoing syntax, for example. Sure; the bit about wetware being slower than silicon was in reply to a different question. My reason for thinking artificial neural nets will have an uphill job doing syntax is a different one; and I think it is indeed about how they represent information. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
Eric, Thanks for this. I just read his paper, A quantitative theory of neural computation, and its quite good. It is particularly nice that he uses human cognition as a basis for defining (and defending) his models, but also generalizes the models so that they could apply to non-human-like neural concept systems... Mike On 6/13/06, Eric Baum [EMAIL PROTECTED] wrote: Hi, I just found that Les has several new papers on the subject and related subjects at http://people.deas.harvard.edu/~valiant/ Ben, I'd point you to Les Valiant's book Circuits of the Mind for a serious attempt to answer precisely such questions. It's been years since I read it, and my recollection is hazy, so I won't attempt much of a summary. The book posits units of several (hundred?) neurons called neuroids that act as finite state machines with various properties, and then gives algorithms by which the whole system could be programmed to learn, for example, concepts of exactly the type you ask. Ben Thanks, I will check it out... Ben Ben Ben --- To unsubscribe, change your address, or temporarily Ben deactivate your subscription, please go to Ben http://v2.listbox.com/member/[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
Russell Wallace wrote: On 6/13/06, [EMAIL PROTECTED] mailto:[EMAIL PROTECTED]* [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] wrote: This thread has completely missed Ben's original point, surely. It diverged certainly, which is why I changed the subject heading for my latest reply. It has nothing to do with whether neurons are faster/better/whatever than digital circuits, it has to do with the way that artificial neurons are used in current NN systems to represent information. The fact that neurons are slower than digital systems is a trivial difference between them. That doesn't make them inherently less capable of doing syntax, for example. What I said in my previous reply was that something very like neural nets (with all the beneficial features for which people got interested in NNs in the first place) *can* do syntax, and all forms of abstract representation. I do not think it is fair to say that they can't, only that the particularly restrictive interpretation of NN that prevails in the literature can't. Richard Loosemore - This message was sent using Endymion MailMan. http://www.endymion.com/products/mailman/ --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
On 6/13/06, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: What I said in my previous reply was that something very like neural nets(with all the beneficial features for which people got interested in NNs inthe first place) *can* do syntax, and all forms of abstract representation. Clearly they can - we're an existence proof of that - my claim being only that it won't be easy. Has anyone yet made an artificial NN or anything like one handle syntax? To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
What I said in my previous reply was that something very like neural nets (with all the beneficial features for which people got interested in NNs in the first place) *can* do syntax, and all forms of abstract representation. I do not think it is fair to say that they can't, only that the particularly restrictive interpretation of NN that prevails in the literature can't. Hi Richard I have to agree that NN can represent all forms of knowledge, since our brainsareNNs. But figuring out how to do that in artificial systems must be pretty difficult. I should also mention Ron Sun's work, he has longtried to reconcile neural and symbolic processing. I studied NNs/ANNs for some time, but I recently switched camp to the more symbolic side. Onequestion is whether there is some definite advantage to using NNs instead of say, predicate logic. Can you give an example of a thought, or a line of inference, etc, thatthe NN-type representation is particularly suited? And that has a advantage over the predicate logic representation? John McCarthyproposed that predicate logic can represent 'almost' everything. If NN-type representationis not necessarily required, then we should naturally use symbolic/logic representations since they are so much more convenient to program and to run on von Neumann hardware. YKY To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
[agi] Advantages Disadvantages... How the Brain Represents Abstract Knowledge
What are the advantages and distadvantages to predicate logic and NNs? Dan Goe From : Yan King Yin [EMAIL PROTECTED] To : agi@v2.listbox.com Subject : Re: [agi] How the Brain Represents Abstract Knowledge Date : Wed, 14 Jun 2006 04:28:36 +0800 What I said in my previous reply was that something very like neural nets (with all the beneficial features for which people got interested in NNs in the first place) *can* do syntax, and all forms of abstract representation. I do not think it is fair to say that they can't, only that the particularly restrictive interpretation of NN that prevails in the literature can't. Hi Richard I have to agree that NN can represent all forms of knowledge, since our brains are NNs. But figuring out how to do that in artificial systems must be pretty difficult. I should also mention Ron Sun's work, he has long tried to reconcile neural and symbolic processing. I studied NNs/ANNs for some time, but I recently switched camp to the more symbolic side. One question is whether there is some definite advantage to using NNs instead of say, predicate logic. Can you give an example of a thought, or a line of inference, etc, that the NN-type representation is particularly suited? And that has a advantage over the predicate logic representation? John McCarthy proposed that predicate logic can represent 'almost' everything. If NN-type representation is not necessarily required, then we should naturally use symbolic/logic representations since they are so much more convenient to program and to run on von Neumann hardware. YKY --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
Russell Wallace wrote: On 6/13/06, [EMAIL PROTECTED] mailto:[EMAIL PROTECTED]* [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] wrote: What I said in my previous reply was that something very like neural nets (with all the beneficial features for which people got interested in NNs in the first place) *can* do syntax, and all forms of abstract representation. Clearly they can - we're an existence proof of that - my claim being only that it won't be easy. Has anyone yet made an artificial NN or anything like one handle syntax? Uhhh: did you read my first post on this thread? Richard Loosemore - This message was sent using Endymion MailMan. http://www.endymion.com/products/mailman/ --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] How the Brain Represents Abstract Knowledge
On 6/14/06, [EMAIL PROTECTED]@pop.lightlink.com [EMAIL PROTECTED]@pop.lightlink.com wrote: Russell Wallace wrote: Has anyone yet made an artificial NN or anything like one handle syntax?Uhhh:did you read my first post on this thread? Yes; you appear to be saying that as far as you know nobody has yet made NNs or similar do syntax, but that's because they went off into the dead end of back propagation, and you believe it should be possible to create something like NNs that do syntax and other such things, but you haven't yet implemented any such. Do I understand you correctly? To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]