Re: [agi] breaking the small hardware mindset
My mistake --- the previous email was meant to be private, though I was too tired to remember that I shouldn't use "reply". :-( Anyway, I don't mind to share this paper, but please don't post it on the Web. Pei On 10/4/07, Pei Wang <[EMAIL PROTECTED]> wrote: > Mike, > > Attached is the paper (for your personal use only). Comments are welcome. > > Pei > > On 10/4/07, mike ramsey <[EMAIL PROTECTED]> wrote: > > If permissible, I to would be interested in the JoETAI version of your > > paper. > > > > Thanks, > > Mike Ramsey > > > > > > On 10/4/07, Edward W. Porter < [EMAIL PROTECTED]> wrote: > > > > > > > > > > > > > > > In response to Pei Wang's post of 10/4/2007 3:13 PM > > > > > > Thanks for giving us a pointer so such inside info. > > > > > > Googling for the article you listed I found > > > > > > > > > 1. The Logic of Categorization, by PeiWang at > > http://nars.wang.googlepages.com/wang.categorization.pdf > > FOR FREE; and > > > > > > 2. A logic of categorization Authors: Wang, Pei; Hofstadter, Douglas; > > Source: Journal of Experimental & Theoretical Artificial Intelligence, > > Volume 18, Number 2, June 2006 , pp. 193-213(21) FOR $46.92 > > > > > > Is the free one roughly as good as the $46.92 one, and, if not, are you > > allowed to send me a copy of the better one for free? > > > > > > Edward W. Porter > > > Porter & Associates > > > 24 String Bridge S12 > > > Exeter, NH 03833 > > > (617) 494-1722 > > > Fax (617) 494-1822 > > > [EMAIL PROTECTED] > > > > > > > > > > > > > > > -Original Message- > > > From: Pei Wang [ mailto:[EMAIL PROTECTED] > > > Sent: Thursday, October 04, 2007 3:13 PM > > > To: [email protected] > > > Subject: Re: [agi] breaking the small hardware mindset > > > > > > > > > On 10/4/07, Edward W. Porter <[EMAIL PROTECTED]> wrote: > > > > > > > > > > > > > > > > Josh, > > > > > > > > (Talking of "breaking the small hardware mindset," thank god for the > > > > company with the largest hardware mindset -- or at least the largest > > > > physical embodiment of one-- Google. Without them I wouldn't have > > > > known what "FARG" meant, and would have had to either (1) read your > > > > valuable response with less than the understanding it deserves or (2) > > > > embarrassed myself by admitting ignorance and asking for a > > > > clarification.) > > > > > > > > With regard to your answer, copied below, I thought the answer would > > > > be something like that. > > > > > > > > So which of the below types of "representational problems" are the > > > > reasons why their basic approach is not automatically extendable? > > > > > > > > > > > > 1. They have no general purpose representation that can represent > > > > almost anything in a sufficiently uniform representational scheme to > > > > let their analogy net matching algorithm be universally applied > > > > without requiring custom patches for each new type of thing to be > > > > represented. > > > > > > > > 2. They have no general purpose mechanism for determining what are > > > > relevant similarities and generalities across which to allow slippage > > > > for purposes of analogy. > > > > > > > > 3. They have no general purpose mechanism for automatically finding > > > > which compositional patterns map to which lower level representations, > > > > and which of those compositional patterns are similar to each other in > > > > a way appropriate for slippages. > > > > > > > > 4. They have no general purpose mechanism for automatically > > > > determining what would be appropriately coordinated slippages in > > > > semantic hyperspace. > > > > > > > > 5. Some reason not listed above. > > > > > > > > I don't know the answer. There is no reason why you should. But if > > > > you -- or any other interested reader – do, or if you have any good > > > > thoughts on the subject, please tell me. > > > > > > I guess I do know more on this topic, but it is a long story for w
RE: [agi] breaking the small hardware mindset
Mike, I think the concept of image schema is a very good one. Among my many computer drawings are ones showing multiple simplified drawings of different, but at different semantic levels, similar events for the purpose of helping me to understand how a system can naturally extract appropriate generalizations from such images. For example, multiple different types of "hitting:". Balls hitting balls. Ball hitting walls. Bats hitting balls. Multiple pictures of Harry hitting Bill and Bill hitting Harry. Etc. So you are preaching to the choir. I have no idea how new the idea is. When Schank was talking about scripts I have a hunch the types of computers he had couldn't even begin to do the level of image recognition necessary do the type of generalization I think we are both interested in. The Serre article, a link to which I sent you earlier today, and the hierarchical memory architecture it provides an example of, make such automatic generalization from images much easier. So learning directly from video, to the extent it is not already here (and some surprising forms of it are already here), will be coming soon, and that learning will definitely include things you could properly call image schemas. Edward W. Porter Porter & Associates 24 String Bridge S12 Exeter, NH 03833 (617) 494-1722 Fax (617) 494-1822 [EMAIL PROTECTED] -Original Message- From: Mike Tintner [mailto:[EMAIL PROTECTED] Sent: Thursday, October 04, 2007 4:03 PM To: [email protected] Subject: Re: [agi] breaking the small hardware mindset Edward You talk about the Cohen article I quoted as perhaps leading to a major > paradigm shift, but actually much of its central thrust is similar to > ideas that have been around for decades. Cohens gists are > surprisingly similar to the scripts Schank was talking about circa > 1980. Josh: And his "static image schemas" are Minsky's frames. No doubt. But image schemas, as used by the school of Lakoff/Johnson/Turner/Fauconnier, are definitely a significant step towards a major paradigm shift in cognitive science - are very influential in cognitive linguistics, have helped found cognitive semantics - and are backed by an evergrowing body of experimental science. So that's why I was just a little (and definitely no more) excited by seeing them being used in AGI, however inadequately. I had already casually predicted elsewhere that they would be influential, and I think you'll see more of them. Neither Minsky nor any other AGI person, to my knowledge, uses image schemas as set out by Mark Johnson in "The Body in the Mind" - or could do, if my understanding is correct, on digital computers. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50135051-e3911e
RE: [agi] breaking the small hardware mindset
Josh, Again a good reply. So it appears the problem is they don't have good automatic learning of semantics. But, of course, that's vertually impossible to do in small systems except, perhaps, about trivial domains. It becomes much easier in tera-machines. So if my interpretation of what you are saying is true, it bodes well for the ease of overcoming this problem in the coming years with the coming hardware. I look forward to reading Pei's article on this subject. It may shed some new light on my understanding of the subject. But it may take me some time. I read and understand symbolic logic slowly. Edward W. Porter Porter & Associates 24 String Bridge S12 Exeter, NH 03833 (617) 494-1722 Fax (617) 494-1822 [EMAIL PROTECTED] -Original Message- From: J Storrs Hall, PhD [mailto:[EMAIL PROTECTED] Sent: Thursday, October 04, 2007 4:30 PM To: [email protected] Subject: Re: [agi] breaking the small hardware mindset Let me answer with an anecdote. I was just in the shop playing with some small robot motors and I needed a punch to remove a pin holding a gearbox onto one of them. I didn't have a purpose-made punch, so I cast around in the toolbox until Aha! an object close enough to use. (It was a small rattail file) Now the file and a true punch have many things in common and many other things different. Among the common things that were critical are the fact that the hardened steel of the file wouldn't bend and wedge beside the pin, and I could hammer on the other end of it. These semantic aspects of the file had to match the same ones of the punch before I could see it as one. Where did these semantic aspects come from? Somehow I've learned enough about punches and files to know what a punch needs (i.e. which of its properties are necessary for it to work) and what a file gives. In Copycat, the idea is to build up an interpretation of an object (analogy as perception) under pressures from what it has to match. So far, well and good -- that's what I was doing. But in Copycat (and tabletop and ...) the semantics is built in and ad hoc. And there isn't really all that much of an analogy net matching algorithm without the semantics (codelets). In my case, I have lots of experience misusing tools, so I have built up an internal theory of which properties are likely to matter and which aren't. I think this most closely matches your even-numbered points below :-) Perhaps more succinctly, they have a general purpose representation but it's snippets of hand-written lisp code, and no way to automatically generate more like it. Josh On Thursday 04 October 2007 02:59:38 pm, Edward W. Porter wrote: > Josh, > > (Talking of breaking the small hardware mindset, thank god for the > company with the largest hardware mindset -- or at least the largest > physical embodiment of one-- Google. Without them I wouldnt have > known what FARG meant, and would have had to either (1) read your > valuable response with less than the understanding it deserves or (2) > embarrassed myself by admitting ignorance and asking for a > clarification.) > > With regard to your answer, copied below, I thought the answer would > be something like that. > > So which of the below types of representational problems are the > reasons why their basic approach is not automatically extendable? > > 1. They have no general purpose representation that can represent > almost anything in a sufficiently uniform representational scheme to > let their analogy net matching algorithm be universally applied > without requiring custom patches for each new type of thing to be > represented. > > 2. They have no general purpose mechanism for determining what are > relevant similarities and generalities across which to allow slippage > for purposes of analogy. > > 3. They have no general purpose mechanism for > automatically finding which compositional patterns map to which lower > level representations, and which of those compositional patterns are > similar to each other in a way appropriate for slippages. > > 4. They have no general purpose mechanism for > automatically determining what would be appropriately coordinated > slippages in semantic hyperspace. > > 5. Some reason not listed above. > > I dont know the answer. There is no reason why you should. But if > you > -- or any other interested reader do, or if you have any good thoughts > on the subject, please tell me. > > I may be naïve. I may be overly big-hardware optimistic. But based > on the architecture I have in mind, I think a Novamente-type system, > if it is not already architected to do so, could be modified to handle > all of these problems (except perhaps 5, if there is a 5) and, thus, > provide p
Re: [agi] breaking the small hardware mindset
Let me answer with an anecdote. I was just in the shop playing with some small robot motors and I needed a punch to remove a pin holding a gearbox onto one of them. I didn't have a purpose-made punch, so I cast around in the toolbox until Aha! an object close enough to use. (It was a small rattail file) Now the file and a true punch have many things in common and many other things different. Among the common things that were critical are the fact that the hardened steel of the file wouldn't bend and wedge beside the pin, and I could hammer on the other end of it. These semantic aspects of the file had to match the same ones of the punch before I could see it as one. Where did these semantic aspects come from? Somehow I've learned enough about punches and files to know what a punch needs (i.e. which of its properties are necessary for it to work) and what a file gives. In Copycat, the idea is to build up an interpretation of an object (analogy as perception) under pressures from what it has to match. So far, well and good -- that's what I was doing. But in Copycat (and tabletop and ...) the semantics is built in and ad hoc. And there isn't really all that much of an analogy net matching algorithm without the semantics (codelets). In my case, I have lots of experience misusing tools, so I have built up an internal theory of which properties are likely to matter and which aren't. I think this most closely matches your even-numbered points below :-) Perhaps more succinctly, they have a general purpose representation but it's snippets of hand-written lisp code, and no way to automatically generate more like it. Josh On Thursday 04 October 2007 02:59:38 pm, Edward W. Porter wrote: > Josh, > > (Talking of breaking the small hardware mindset, thank god for the > company with the largest hardware mindset -- or at least the largest > physical embodiment of one-- Google. Without them I wouldnt have known > what FARG meant, and would have had to either (1) read your valuable > response with less than the understanding it deserves or (2) embarrassed > myself by admitting ignorance and asking for a clarification.) > > With regard to your answer, copied below, I thought the answer would be > something like that. > > So which of the below types of representational problems are the reasons > why their basic approach is not automatically extendable? > > 1. They have no general purpose representation that can > represent almost anything in a sufficiently uniform representational > scheme to let their analogy net matching algorithm be universally applied > without requiring custom patches for each new type of thing to be > represented. > > 2. They have no general purpose mechanism for determining > what are relevant similarities and generalities across which to allow > slippage for purposes of analogy. > > 3. They have no general purpose mechanism for > automatically finding which compositional patterns map to which lower > level representations, and which of those compositional patterns are > similar to each other in a way appropriate for slippages. > > 4. They have no general purpose mechanism for > automatically determining what would be appropriately coordinated > slippages in semantic hyperspace. > > 5. Some reason not listed above. > > I dont know the answer. There is no reason why you should. But if you > -- or any other interested reader do, or if you have any good thoughts > on the subject, please tell me. > > I may be naïve. I may be overly big-hardware optimistic. But based on > the architecture I have in mind, I think a Novamente-type system, if it is > not already architected to do so, could be modified to handle all of these > problems (except perhaps 5, if there is a 5) and, thus, provide powerful > analogy drawing across virtually all domains. > > Edward W. Porter > Porter & Associates > 24 String Bridge S12 > Exeter, NH 03833 > (617) 494-1722 > Fax (617) 494-1822 > [EMAIL PROTECTED] > - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50116032-96886d
Re: [agi] breaking the small hardware mindset
On 10/4/07, J Storrs Hall, PhD <[EMAIL PROTECTED]> wrote: > On Thursday 04 October 2007 11:52:01 am, Vladimir Nesov wrote: > > Analogy-making can be reformulated as other problems, so even if it's > > not named this way it's still associated with many approaches to > > learning. Recalling relevant knowledge is about the same thing as > > analogy-making, and in lifelong learning almost all knowledge comes > > from past experience, so perception of current scene consists of > > recalling refined elements of this experience. > > > > So, could you elucidate on why do you specifically address analogy-making? > > If I have the primitive "make an analogy between A and B" I can use it as a > subroutine in "recall the memory that makes the best analogy to X" and it > seems simpler than trying to do it the other way around. > Somewhat, but requirement to search in huge long term memory can be important for algorithm choice. Apart from this use case, you may want to find recurring patterns within a given scene, which is equivalent to finding the best analogy to one part of the scene in the rest of the scene (and with right representation you don't even need to do that). Anyway, my point was not that view on analogy-making as recall is 'better', but that analogy-making problem lives in that incarnation, so absence of explicitly stated analogy-making research doesn't mean that problem is neglected. -- Vladimir Nesovmailto:[EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50115516-e0d3df
Re: [agi] breaking the small hardware mindset
Edward You talk about the Cohen article I quoted as perhaps leading to a major paradigm shift, but actually much of its central thrust is similar to ideas that have been around for decades. Cohens gists are surprisingly similar to the scripts Schank was talking about circa 1980. Josh: And his "static image schemas" are Minsky's frames. No doubt. But image schemas, as used by the school of Lakoff/Johnson/Turner/Fauconnier, are definitely a significant step towards a major paradigm shift in cognitive science - are very influential in cognitive linguistics, have helped found cognitive semantics - and are backed by an evergrowing body of experimental science. So that's why I was just a little (and definitely no more) excited by seeing them being used in AGI, however inadequately. I had already casually predicted elsewhere that they would be influential, and I think you'll see more of them. Neither Minsky nor any other AGI person, to my knowledge, uses image schemas as set out by Mark Johnson in "The Body in the Mind" - or could do, if my understanding is correct, on digital computers. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50095094-ffe2be
Re: [agi] breaking the small hardware mindset
Well, the two papers have similar central ideas, though the second one is much longer and also reflects Hofstadter's opinions --- so it is not free. ;-) I'll send you (and the others who have asked) a softcopy in private email. Pei On 10/4/07, Edward W. Porter <[EMAIL PROTECTED]> wrote: > > > > In response to Pei Wang's post of 10/4/2007 3:13 PM > > Thanks for giving us a pointer so such inside info. > > Googling for the article you listed I found > > > 1. The Logic of Categorization, by PeiWang at > http://nars.wang.googlepages.com/wang.categorization.pdf > FOR FREE; and > > 2. A logic of categorization Authors: Wang, Pei; Hofstadter, Douglas; > Source: Journal of Experimental & Theoretical Artificial Intelligence, > Volume 18, Number 2, June 2006 , pp. 193-213(21) FOR $46.92 > > Is the free one roughly as good as the $46.92 one, and, if not, are you > allowed to send me a copy of the better one for free? > > Edward W. Porter > Porter & Associates > 24 String Bridge S12 > Exeter, NH 03833 > (617) 494-1722 > Fax (617) 494-1822 > [EMAIL PROTECTED] > > > > > -Original Message----- > From: Pei Wang [mailto:[EMAIL PROTECTED] > Sent: Thursday, October 04, 2007 3:13 PM > To: [email protected] > Subject: Re: [agi] breaking the small hardware mindset > > > On 10/4/07, Edward W. Porter <[EMAIL PROTECTED]> wrote: > > > > > > > > Josh, > > > > (Talking of "breaking the small hardware mindset," thank god for the > > company with the largest hardware mindset -- or at least the largest > > physical embodiment of one-- Google. Without them I wouldn't have > > known what "FARG" meant, and would have had to either (1) read your > > valuable response with less than the understanding it deserves or (2) > > embarrassed myself by admitting ignorance and asking for a > > clarification.) > > > > With regard to your answer, copied below, I thought the answer would > > be something like that. > > > > So which of the below types of "representational problems" are the > > reasons why their basic approach is not automatically extendable? > > > > > > 1. They have no general purpose representation that can represent > > almost anything in a sufficiently uniform representational scheme to > > let their analogy net matching algorithm be universally applied > > without requiring custom patches for each new type of thing to be > > represented. > > > > 2. They have no general purpose mechanism for determining what are > > relevant similarities and generalities across which to allow slippage > > for purposes of analogy. > > > > 3. They have no general purpose mechanism for automatically finding > > which compositional patterns map to which lower level representations, > > and which of those compositional patterns are similar to each other in > > a way appropriate for slippages. > > > > 4. They have no general purpose mechanism for automatically > > determining what would be appropriately coordinated slippages in > > semantic hyperspace. > > > > 5. Some reason not listed above. > > > > I don't know the answer. There is no reason why you should. But if > > you -- or any other interested reader – do, or if you have any good > > thoughts on the subject, please tell me. > > I guess I do know more on this topic, but it is a long story for which I > don't have the time to tell. Hopefully the following paper can answer some > of the questions: > > A logic of categorization > Pei Wang and Douglas Hofstadter > Journal of Experimental & Theoretical Artificial Intelligence, Vol.18, No.2, > Pages 193-213, 2006 > > Pei > > > I may be naïve. I may be overly big-hardware optimistic. But based > > on the architecture I have in mind, I think a Novamente-type system, > > if it is not already architected to do so, could be modified to handle > > all of these problems (except perhaps 5, if there is a 5) and, thus, > > provide powerful analogy drawing across virtually all domains. > > > > Edward W. Porter > > Porter & Associates > > 24 String Bridge S12 > > Exeter, NH 03833 > > (617) 494-1722 > > Fax (617) 494-1822 > > [EMAIL PROTECTED] > > > > > > > > -Original Message- > > From: J Storrs Hall, PhD [mailto:[EMAIL PROTECTED] > > Sent: Thursday, October 04, 2007 1:44 PM > > To: [email protected] > > Subject: Re: [agi] breaking the small hardware mindset > > > > > > > > On Thursday 04 O
Re: [agi] breaking the small hardware mindset
If permissible, I to would be interested in the JoETAI version of your paper. Thanks, Mike Ramsey On 10/4/07, Edward W. Porter <[EMAIL PROTECTED]> wrote: > > In response to Pei Wang's post of 10/4/2007 3:13 PM > > Thanks for giving us a pointer so such inside info. > > Googling for the article you listed I found > >1. The Logic of Categorization, by PeiWang at *** > > http://nars.wang.googlepages.com/wang.categorization.pdf*<http://nars.wang.googlepages.com/wang.categorization.pdf> > FOR >FREE; and > >2. A logic of categorization Authors: Wang, Pei; Hofstadter, >Douglas; Source: Journal of Experimental & Theoretical Artificial >Intelligence <http://www.ingentaconnect.com/content/tandf/teta>, >Volume 18, Number 2, June 2006 , pp. 193-213(21) FOR $46.92 > > Is the free one roughly as good as the $46.92 one, and, if not, are you > allowed to send me a copy of the better one for free? > > Edward W. Porter > Porter & Associates > 24 String Bridge S12 > Exeter, NH 03833 > (617) 494-1722 > Fax (617) 494-1822 > [EMAIL PROTECTED] > > > -Original Message- > From: Pei Wang [*mailto:[EMAIL PROTECTED] <[EMAIL PROTECTED]>] > Sent: Thursday, October 04, 2007 3:13 PM > To: [email protected] > Subject: Re: [agi] breaking the small hardware mindset > > On 10/4/07, Edward W. Porter <[EMAIL PROTECTED]> wrote: > > > > > > > > Josh, > > > > (Talking of "breaking the small hardware mindset," thank god for the > > company with the largest hardware mindset -- or at least the largest > > physical embodiment of one-- Google. Without them I wouldn't have > > known what "FARG" meant, and would have had to either (1) read your > > valuable response with less than the understanding it deserves or (2) > > embarrassed myself by admitting ignorance and asking for a > > clarification.) > > > > With regard to your answer, copied below, I thought the answer would > > be something like that. > > > > So which of the below types of "representational problems" are the > > reasons why their basic approach is not automatically extendable? > > > > > > 1. They have no general purpose representation that can represent > > almost anything in a sufficiently uniform representational scheme to > > let their analogy net matching algorithm be universally applied > > without requiring custom patches for each new type of thing to be > > represented. > > > > 2. They have no general purpose mechanism for determining what are > > relevant similarities and generalities across which to allow slippage > > for purposes of analogy. > > > > 3. They have no general purpose mechanism for automatically finding > > which compositional patterns map to which lower level representations, > > and which of those compositional patterns are similar to each other in > > a way appropriate for slippages. > > > > 4. They have no general purpose mechanism for automatically > > determining what would be appropriately coordinated slippages in > > semantic hyperspace. > > > > 5. Some reason not listed above. > > > > I don't know the answer. There is no reason why you should. But if > > you -- or any other interested reader – do, or if you have any good > > thoughts on the subject, please tell me. > > I guess I do know more on this topic, but it is a long story for which I > don't have the time to tell. Hopefully the following paper can answer some > of the questions: > > A logic of categorization > Pei Wang and Douglas Hofstadter > Journal of Experimental & Theoretical Artificial Intelligence, Vol.18, > No.2, Pages 193-213, 2006 > > Pei > > > I may be naïve. I may be overly big-hardware optimistic. But based > > on the architecture I have in mind, I think a Novamente-type system, > > if it is not already architected to do so, could be modified to handle > > all of these problems (except perhaps 5, if there is a 5) and, thus, > > provide powerful analogy drawing across virtually all domains. > > > > Edward W. Porter > > Porter & Associates > > 24 String Bridge S12 > > Exeter, NH 03833 > > (617) 494-1722 > > Fax (617) 494-1822 > > [EMAIL PROTECTED] > > > > > > > > -Original Message- > > From: J Storrs Hall, PhD [*mailto:[EMAIL PROTECTED] <[EMAIL PROTECTED]> > ] > > Sent: Thursday, October 04, 2007 1:44 PM > > To: [email protected] > > Subject: Re: [agi] breaking the small hardware mindset > >
RE: [agi] breaking the small hardware mindset
In response to Pei Wangs post of 10/4/2007 3:13 PM Thanks for giving us a pointer so such inside info. Googling for the article you listed I found 1. The Logic of Categorization, by PeiWang at http://nars.wang.googlepages.com/wang.categorization.pdf FOR FREE; and 2. A logic of categorization Authors: Wang, Pei; Hofstadter, Douglas; Source: Journal of Experimental & Theoretical Artificial Intelligence <http://www.ingentaconnect.com/content/tandf/teta> , Volume 18, Number 2, June 2006 , pp. 193-213(21) FOR $46.92 Is the free one roughly as good as the $46.92 one, and, if not, are you allowed to send me a copy of the better one for free? Edward W. Porter Porter & Associates 24 String Bridge S12 Exeter, NH 03833 (617) 494-1722 Fax (617) 494-1822 [EMAIL PROTECTED] -Original Message- From: Pei Wang [mailto:[EMAIL PROTECTED] Sent: Thursday, October 04, 2007 3:13 PM To: [email protected] Subject: Re: [agi] breaking the small hardware mindset On 10/4/07, Edward W. Porter <[EMAIL PROTECTED]> wrote: > > > > Josh, > > (Talking of "breaking the small hardware mindset," thank god for the > company with the largest hardware mindset -- or at least the largest > physical embodiment of one-- Google. Without them I wouldn't have > known what "FARG" meant, and would have had to either (1) read your > valuable response with less than the understanding it deserves or (2) > embarrassed myself by admitting ignorance and asking for a > clarification.) > > With regard to your answer, copied below, I thought the answer would > be something like that. > > So which of the below types of "representational problems" are the > reasons why their basic approach is not automatically extendable? > > > 1. They have no general purpose representation that can represent > almost anything in a sufficiently uniform representational scheme to > let their analogy net matching algorithm be universally applied > without requiring custom patches for each new type of thing to be > represented. > > 2. They have no general purpose mechanism for determining what are > relevant similarities and generalities across which to allow slippage > for purposes of analogy. > > 3. They have no general purpose mechanism for automatically finding > which compositional patterns map to which lower level representations, > and which of those compositional patterns are similar to each other in > a way appropriate for slippages. > > 4. They have no general purpose mechanism for automatically > determining what would be appropriately coordinated slippages in > semantic hyperspace. > > 5. Some reason not listed above. > > I don't know the answer. There is no reason why you should. But if > you -- or any other interested reader do, or if you have any good > thoughts on the subject, please tell me. I guess I do know more on this topic, but it is a long story for which I don't have the time to tell. Hopefully the following paper can answer some of the questions: A logic of categorization Pei Wang and Douglas Hofstadter Journal of Experimental & Theoretical Artificial Intelligence, Vol.18, No.2, Pages 193-213, 2006 Pei > I may be naïve. I may be overly big-hardware optimistic. But based > on the architecture I have in mind, I think a Novamente-type system, > if it is not already architected to do so, could be modified to handle > all of these problems (except perhaps 5, if there is a 5) and, thus, > provide powerful analogy drawing across virtually all domains. > > Edward W. Porter > Porter & Associates > 24 String Bridge S12 > Exeter, NH 03833 > (617) 494-1722 > Fax (617) 494-1822 > [EMAIL PROTECTED] > > > > -Original Message- > From: J Storrs Hall, PhD [mailto:[EMAIL PROTECTED] > Sent: Thursday, October 04, 2007 1:44 PM > To: [email protected] > Subject: Re: [agi] breaking the small hardware mindset > > > > On Thursday 04 October 2007 10:56:59 am, Edward W. Porter wrote: > > You appear to know more on the subject of current analogy drawing > > research than me. So could you please explain to me what are the > > major current problems people are having in trying figure out how to > > draw analogies using a structure mapping approach that has a > > mechanism for coordinating similarity slippage, an approach somewhat > > similar to Hofstadter approach in Copycat? > > > Lets say we want a system that could draw analogies in real time > > when generating natural language output at the level people can, > > assuming there is some roughly semantic-net like representation of > > world knowledge, and lets say we have roughly brain level hardware, > > what ever that is. What are the c
Re: [agi] breaking the small hardware mindset
On 10/4/07, Edward W. Porter <[EMAIL PROTECTED]> wrote: > > > > Josh, > > (Talking of "breaking the small hardware mindset," thank god for the company > with the largest hardware mindset -- or at least the largest physical > embodiment of one-- Google. Without them I wouldn't have known what "FARG" > meant, and would have had to either (1) read your valuable response with > less than the understanding it deserves or (2) embarrassed myself by > admitting ignorance and asking for a clarification.) > > With regard to your answer, copied below, I thought the answer would be > something like that. > > So which of the below types of "representational problems" are the reasons > why their basic approach is not automatically extendable? > > > 1. They have no general purpose representation that can represent almost > anything in a sufficiently uniform representational scheme to let their > analogy net matching algorithm be universally applied without requiring > custom patches for each new type of thing to be represented. > > 2. They have no general purpose mechanism for determining what are relevant > similarities and generalities across which to allow slippage for purposes of > analogy. > > 3. They have no general purpose mechanism for automatically finding which > compositional patterns map to which lower level representations, and which > of those compositional patterns are similar to each other in a way > appropriate for slippages. > > 4. They have no general purpose mechanism for automatically determining what > would be appropriately coordinated slippages in semantic hyperspace. > > 5. Some reason not listed above. > > I don't know the answer. There is no reason why you should. But if you -- > or any other interested reader – do, or if you have any good thoughts on > the subject, please tell me. I guess I do know more on this topic, but it is a long story for which I don't have the time to tell. Hopefully the following paper can answer some of the questions: A logic of categorization Pei Wang and Douglas Hofstadter Journal of Experimental & Theoretical Artificial Intelligence, Vol.18, No.2, Pages 193-213, 2006 Pei > I may be naïve. I may be overly big-hardware optimistic. But based on the > architecture I have in mind, I think a Novamente-type system, if it is not > already architected to do so, could be modified to handle all of these > problems (except perhaps 5, if there is a 5) and, thus, provide powerful > analogy drawing across virtually all domains. > > Edward W. Porter > Porter & Associates > 24 String Bridge S12 > Exeter, NH 03833 > (617) 494-1722 > Fax (617) 494-1822 > [EMAIL PROTECTED] > > > > -Original Message- > From: J Storrs Hall, PhD [mailto:[EMAIL PROTECTED] > Sent: Thursday, October 04, 2007 1:44 PM > To: [email protected] > Subject: Re: [agi] breaking the small hardware mindset > > > > On Thursday 04 October 2007 10:56:59 am, Edward W. Porter wrote: > > You appear to know more on the subject of current analogy drawing > > research than me. So could you please explain to me what are the major > > current problems people are having in trying figure out how to draw > > analogies using a structure mapping approach that has a mechanism for > > coordinating similarity slippage, an approach somewhat similar to > > Hofstadter approach in Copycat? > > > Lets say we want a system that could draw analogies in real time when > > generating natural language output at the level people can, assuming > > there is some roughly semantic-net like representation of world > > knowledge, and lets say we have roughly brain level hardware, what > > ever that is. What are the current major problems? > > The big problem is that structure mapping is brittlely dependent on > representation, as Hofstadter complains; but that the FARG school hasn't > really come up with a generative theory (every Copycat-like analogizer > requires a pile of human-written Codelets which increases linearly with the > knowledge base -- and thus there is a real problem building a Copycat that > can learn its concepts). > > In my humble opinion, of course. > > Josh > > - > This list is sponsored by AGIRI: http://www.agiri.org/email > To unsubscribe or change your options, please go to: > http://v2.listbox.com/member/?&; > > > This list is sponsored by AGIRI: http://www.agiri.org/email > To unsubscribe or change your options, please go to: > http://v2.listbox.com/member/?&; - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50073913-f918fd
RE: [agi] breaking the small hardware mindset
Josh, (Talking of breaking the small hardware mindset, thank god for the company with the largest hardware mindset -- or at least the largest physical embodiment of one-- Google. Without them I wouldnt have known what FARG meant, and would have had to either (1) read your valuable response with less than the understanding it deserves or (2) embarrassed myself by admitting ignorance and asking for a clarification.) With regard to your answer, copied below, I thought the answer would be something like that. So which of the below types of representational problems are the reasons why their basic approach is not automatically extendable? 1. They have no general purpose representation that can represent almost anything in a sufficiently uniform representational scheme to let their analogy net matching algorithm be universally applied without requiring custom patches for each new type of thing to be represented. 2. They have no general purpose mechanism for determining what are relevant similarities and generalities across which to allow slippage for purposes of analogy. 3. They have no general purpose mechanism for automatically finding which compositional patterns map to which lower level representations, and which of those compositional patterns are similar to each other in a way appropriate for slippages. 4. They have no general purpose mechanism for automatically determining what would be appropriately coordinated slippages in semantic hyperspace. 5. Some reason not listed above. I dont know the answer. There is no reason why you should. But if you -- or any other interested reader do, or if you have any good thoughts on the subject, please tell me. I may be naïve. I may be overly big-hardware optimistic. But based on the architecture I have in mind, I think a Novamente-type system, if it is not already architected to do so, could be modified to handle all of these problems (except perhaps 5, if there is a 5) and, thus, provide powerful analogy drawing across virtually all domains. Edward W. Porter Porter & Associates 24 String Bridge S12 Exeter, NH 03833 (617) 494-1722 Fax (617) 494-1822 [EMAIL PROTECTED] -Original Message- From: J Storrs Hall, PhD [mailto:[EMAIL PROTECTED] Sent: Thursday, October 04, 2007 1:44 PM To: [email protected] Subject: Re: [agi] breaking the small hardware mindset On Thursday 04 October 2007 10:56:59 am, Edward W. Porter wrote: > You appear to know more on the subject of current analogy drawing > research than me. So could you please explain to me what are the major > current problems people are having in trying figure out how to draw > analogies using a structure mapping approach that has a mechanism for > coordinating similarity slippage, an approach somewhat similar to > Hofstadter approach in Copycat? > Lets say we want a system that could draw analogies in real time when > generating natural language output at the level people can, assuming > there is some roughly semantic-net like representation of world > knowledge, and lets say we have roughly brain level hardware, what > ever that is. What are the current major problems? The big problem is that structure mapping is brittlely dependent on representation, as Hofstadter complains; but that the FARG school hasn't really come up with a generative theory (every Copycat-like analogizer requires a pile of human-written Codelets which increases linearly with the knowledge base -- and thus there is a real problem building a Copycat that can learn its concepts). In my humble opinion, of course. Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50064710-fa7794
Re: [agi] breaking the small hardware mindset
On Thursday 04 October 2007 01:57:22 pm, Edward W. Porter wrote: > You talk about the Cohen article I quoted as perhaps leading to a major > paradigm shift, but actually much of its central thrust is similar to > ideas that have been around for decades. Cohens gists are surprisingly > similar to the scripts Schank was talking about circa 1980. And his "static image schemas" are Minsky's frames. J - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50042155-b316e3
RE: [agi] breaking the small hardware mindset
ay, October 04, 2007 12:33 PM To: [email protected] Subject: Re: [agi] breaking the small hardware mindset Edward P: II skimmed LGIST: Learning Generalized Image Schemas for Transfer Thrust D Architecture Report, by Carole Beal and Paul Cohen at the USC Information Sciences Institute. It was one of the PDFs listed on the web link you sent me (at http://eksl.isi.edu/files/papers/cohen_2006_1160084799.pdf). It was interesting and valuable. I found its initial few pages a good statement of some solid AI ideas. Its idea of splitting states based on entropy is a good one, one that I have myself have considered as a guide for when and where in semantic space to split models and how to segment temporal representations. Thanks for pointing this out. My v. quick impression is that it is a step, at least, to a major paradigm shift (although all your criticisms may be valid). [JWJohnston - I only saw this site literally today after I had posted] However - correct me - their "image schemas" are symbolically represented. They are not true image schemas in my or Lakoff/Mark Johnson's terms. I believe one of the central sources of the brain's adaptive power is the ability to represent, manipulate and compare visual and other kinds of graphics/ "image schemas" directly. IOW it can represent "an agent goes to a place" as (speaking very roughly): outline graphics of - a circle or similar (for "agent") - an arrow (for "goes to") - another circle or square (for "place"). (AFAICT this is consistent with Lakoff & Johnson's thinking). If I ask you or any human to tell me a story about "an agent going to a place", you will of course, be able to tell me a virtually infinite number of stories - a prime example of the brain's adaptive power and ability to draw analogies. That ability, I believe, derives from being able to directly, visually transform a circle or similar into almost any object or creature . Thus you will be able to tell me a story about a human/man/woman/rabbit/snake etc for your "agent." That ability can also visually transform an arrow or similar into any form of object movement - into say a human running/walking/driving/riding a bus etc. for "goes to" - and can transform a square into a skyscraper/ town/ shop/ forest etc. for "place." (One obvious piece of evidence for this is the brain's ability to see any objects whatsoever their shape as balls on an abacus - it's the foundation of our ability to count objects and maths). But all this - as I understand - is beyond digital computers. They can't handle visual shapes directly - no "imagination." And that is just one of the absolute brick walls AGI faces, which no amount of tweaking will overcome. P.S. I have to say I wasn't that impressed by the other 2 papers of Cohen linked by JWJohnston. But thanks also for pointing them out - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50026498-5f2264
Re: [agi] breaking the small hardware mindset
On Thursday 04 October 2007 10:56:59 am, Edward W. Porter wrote: > You appear to know more on the subject of current analogy drawing research > than me. So could you please explain to me what are the major current > problems people are having in trying figure out how to draw analogies > using a structure mapping approach that has a mechanism for coordinating > similarity slippage, an approach somewhat similar to Hofstadter approach > in Copycat? > Lets say we want a system that could draw analogies in real time when > generating natural language output at the level people can, assuming there > is some roughly semantic-net like representation of world knowledge, and > lets say we have roughly brain level hardware, what ever that is. What > are the current major problems? The big problem is that structure mapping is brittlely dependent on representation, as Hofstadter complains; but that the FARG school hasn't really come up with a generative theory (every Copycat-like analogizer requires a pile of human-written Codelets which increases linearly with the knowledge base -- and thus there is a real problem building a Copycat that can learn its concepts). In my humble opinion, of course. Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50021664-0a9ddc
Re: [agi] breaking the small hardware mindset
On Thursday 04 October 2007 11:52:01 am, Vladimir Nesov wrote: > Analogy-making can be reformulated as other problems, so even if it's > not named this way it's still associated with many approaches to > learning. Recalling relevant knowledge is about the same thing as > analogy-making, and in lifelong learning almost all knowledge comes > from past experience, so perception of current scene consists of > recalling refined elements of this experience. > > So, could you elucidate on why do you specifically address analogy-making? If I have the primitive "make an analogy between A and B" I can use it as a subroutine in "recall the memory that makes the best analogy to X" and it seems simpler than trying to do it the other way around. Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=50017827-107af6
Re: [agi] breaking the small hardware mindset
Edward P: II skimmed “LGIST: Learning Generalized Image Schemas for Transfer Thrust D Architecture Report”, by Carole Beal and Paul Cohen at the USC Information Sciences Institute. It was one of the PDFs listed on the web link you sent me (at http://eksl.isi.edu/files/papers/cohen_2006_1160084799.pdf). It was interesting and valuable. I found its initial few pages a good statement of some solid AI ideas. Its idea of splitting states based on entropy is a good one, one that I have myself have considered as a guide for when and where in semantic space to split models and how to segment temporal representations. Thanks for pointing this out. My v. quick impression is that it is a step, at least, to a major paradigm shift (although all your criticisms may be valid). [JWJohnston - I only saw this site literally today after I had posted] However - correct me - their "image schemas" are symbolically represented. They are not true image schemas in my or Lakoff/Mark Johnson's terms. I believe one of the central sources of the brain's adaptive power is the ability to represent, manipulate and compare visual and other kinds of graphics/ "image schemas" directly. IOW it can represent "an agent goes to a place" as (speaking very roughly): outline graphics of - a circle or similar (for "agent") - an arrow (for "goes to") - another circle or square (for "place"). (AFAICT this is consistent with Lakoff & Johnson's thinking). If I ask you or any human to tell me a story about "an agent going to a place", you will of course, be able to tell me a virtually infinite number of stories - a prime example of the brain's adaptive power and ability to draw analogies. That ability, I believe, derives from being able to directly, visually transform a circle or similar into almost any object or creature . Thus you will be able to tell me a story about a human/man/woman/rabbit/snake etc for your "agent." That ability can also visually transform an arrow or similar into any form of object movement - into say a human running/walking/driving/riding a bus etc. for "goes to" - and can transform a square into a skyscraper/ town/ shop/ forest etc. for "place." (One obvious piece of evidence for this is the brain's ability to see any objects whatsoever their shape as balls on an abacus - it's the foundation of our ability to count objects and maths). But all this - as I understand - is beyond digital computers. They can't handle visual shapes directly - no "imagination." And that is just one of the absolute brick walls AGI faces, which no amount of tweaking will overcome. P.S. I have to say I wasn't that impressed by the other 2 papers of Cohen linked by JWJohnston. But thanks also for pointing them out - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49952160-096c90
Re: [agi] breaking the small hardware mindset
On 10/4/07, J Storrs Hall, PhD <[EMAIL PROTECTED]> wrote: > Research in analogy-making is slow -- I can only think of Gentner and > Hofstadter and their groups as major movers. We don't have a solid theory of > analogy yet (structure-mapping to the contrary notwithstanding). It's clearly > central, and so I don't understand why more people aren't working on it. Analogy-making can be reformulated as other problems, so even if it's not named this way it's still associated with many approaches to learning. Recalling relevant knowledge is about the same thing as analogy-making, and in lifelong learning almost all knowledge comes from past experience, so perception of current scene consists of recalling refined elements of this experience. So, could you elucidate on why do you specifically address analogy-making? -- Vladimir Nesovmailto:[EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49862316-ecf9ff
Re: [agi] breaking the small hardware mindset
On Thursday 04 October 2007 10:42:46 am, Mike Tintner wrote: > ... I find > no general sense of the need for a major paradigm shift. It should be > obvious that a successful AGI will transform and revolutionize existing > computational paradigms ... I find it difficult to imagine a development that would at the same time revolutionize existing paradigms and yet not require a paradigm shift. Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49818920-208813
RE: [agi] breaking the small hardware mindset
Josh, in your 10/4/2007 9:57 AM post you wrote: RESEARCH IN ANALOGY-MAKING IS SLOW -- I CAN ONLY THINK OF GENTNER AND HOFSTADTER AND THEIR GROUPS AS MAJOR MOVERS. WE DON'T HAVE A SOLID THEORY OF ANALOGY YET (STRUCTURE-MAPPING TO THE CONTRARY NOTWITHSTANDING). IT'S CLEARLY CENTRAL, AND SO I DON'T UNDERSTAND WHY MORE PEOPLE AREN'T WORKING ON IT. (BTW: ANYTIME YOU'RE DOING ANYTHING THAT EVEN SMELLS LIKE SUBGRAPH ISOMORPHISM, BIG IRON IS YOUR FRIEND.) You appear to know more on the subject of current analogy drawing research than me. So could you please explain to me what are the major current problems people are having in trying figure out how to draw analogies using a structure mapping approach that has a mechanism for coordinating similarity slippage, an approach somewhat similar to Hofstadter approach in Copycat? Lets say we want a system that could draw analogies in real time when generating natural language output at the level people can, assuming there is some roughly semantic-net like representation of world knowledge, and lets say we have roughly brain level hardware, what ever that is. What are the current major problems? Edward W. Porter Porter & Associates 24 String Bridge S12 Exeter, NH 03833 (617) 494-1722 Fax (617) 494-1822 [EMAIL PROTECTED] -Original Message- From: J Storrs Hall, PhD [mailto:[EMAIL PROTECTED] Sent: Thursday, October 04, 2007 9:57 AM To: [email protected] Subject: Re: [agi] breaking the small hardware mindset On Wednesday 03 October 2007 09:37:58 pm, Mike Tintner wrote: > I disagree also re how much has been done. I don't think AGI - > correct me - has solved a single creative problem - e.g. creativity - unprogrammed adaptivity - drawing analogies - visual object recognition - NLP - concepts - creating an emotional system - general learning - embodied/ grounded knowledge - visual/sensory thinking.- every dimension in short of "imagination". (Yes, vast creativity has gone into narrow AI, but that's different). Ah, the Lorelei sings so sweetly. That's what happened to AI in the 80's -- it went off chasing "human-level performance" at specific tasks, which requires a completely different mindset (and something of a different toolset) than solving the general AI problem. To repeat a previous letter, solving particular problems is engineering, but AI needed science. There are, however, several subproblems that may need to be solved to make a general AI work. General learning is surely one of them. I happen to think that analogy-making is another. But there has been a significant amount of basic research done on these areas. 21st century AI, even narrow AI, looks very different from say 80's expert systems. Lots of new techniques that work a lot better. Some of them require big iron, some don't. Research in analogy-making is slow -- I can only think of Gentner and Hofstadter and their groups as major movers. We don't have a solid theory of analogy yet (structure-mapping to the contrary notwithstanding). It's clearly central, and so I don't understand why more people aren't working on it. (btw: anytime you're doing anything that even smells like subgraph isomorphism, big iron is your friend.) One main reason I support the development of AGI as a serious subfield is not that I think any specific approach here is likely to work (even mine), but that there is a willingness to experiment and a tolerance for new and odd-sounding ideas that spells a renaissance of science in AI. Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49804068-d1884d
Re: [agi] breaking the small hardware mindset
Mike Tintner wrote: >My impression is everyone's clinging to >existing paradigms, even though they obviously don't work for AGI as opposed >to AI. By all means disabuse me and point to someone contemplating such a >shift. > You just pointed us to one (!): Paul Cohen (see http://www.isi.edu/~cohen/talks-presentations/EdFest/The%20Knowledge%20Principle.pdf and http://www.isi.edu/~cohen/talks-presentations/NIST%202006/assessing-decathletes.pdf). He's one of many (like many on this list and luminaries in field) saying the time is right to focus on AI engineering and not only on AI science. Probably not a paradigm shift, but most here probably don't think one is necessary. Do you? (Sorry, I haven't followed your earlier postings very closely. You seem to be one in a minority in this group thinking we're NOT getting close to AGI. Is that true?) I share the opinion of Ben, Josh, Edward Porter, and others that the time is right and it's going to happen.) -JW - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49802037-6c1c48
Re: [agi] breaking the small hardware mindset
Josh: One main reason I support the development of AGI as a serious subfield is not that I think any specific approach here is likely to work (even mine), but that there is a willingness to experiment and a tolerance for new and odd-sounding ideas that spells a renaissance of science in AI. Well, there has to be a willingness to experiment by definition.But I find no general sense of the need for a major paradigm shift. It should be obvious that a successful AGI will transform and revolutionize existing computational paradigms - and involve a major new scientific theory (or theories) of mind/ mind model. My impression is everyone's clinging to existing paradigms, even though they obviously don't work for AGI as opposed to AI. By all means disabuse me and point to someone contemplating such a shift. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49713036-8ee55c
Re: [agi] breaking the small hardware mindset
On Wednesday 03 October 2007 09:37:58 pm, Mike Tintner wrote: > I disagree also re how much has been done. I don't think AGI - correct me - has solved a single creative problem - e.g. creativity - unprogrammed adaptivity - drawing analogies - visual object recognition - NLP - concepts - creating an emotional system - general learning - embodied/ grounded knowledge - visual/sensory thinking.- every dimension in short of "imagination". (Yes, vast creativity has gone into narrow AI, but that's different). Ah, the Lorelei sings so sweetly. That's what happened to AI in the 80's -- it went off chasing "human-level performance" at specific tasks, which requires a completely different mindset (and something of a different toolset) than solving the general AI problem. To repeat a previous letter, solving particular problems is engineering, but AI needed science. There are, however, several subproblems that may need to be solved to make a general AI work. General learning is surely one of them. I happen to think that analogy-making is another. But there has been a significant amount of basic research done on these areas. 21st century AI, even narrow AI, looks very different from say 80's expert systems. Lots of new techniques that work a lot better. Some of them require big iron, some don't. Research in analogy-making is slow -- I can only think of Gentner and Hofstadter and their groups as major movers. We don't have a solid theory of analogy yet (structure-mapping to the contrary notwithstanding). It's clearly central, and so I don't understand why more people aren't working on it. (btw: anytime you're doing anything that even smells like subgraph isomorphism, big iron is your friend.) One main reason I support the development of AGI as a serious subfield is not that I think any specific approach here is likely to work (even mine), but that there is a willingness to experiment and a tolerance for new and odd-sounding ideas that spells a renaissance of science in AI. Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49680928-5b6fb1
RE: [agi] breaking the small hardware mindset
Mike Tintner said in his 10/3/2007 9:38 PM post: I DON'T THINK AGI - CORRECT ME - HAS SOLVED A SINGLE CREATIVE PROBLEM - E.G. CREATIVITY - UNPROGRAMMED ADAPTIVITY - DRAWING ANALOGIES - VISUAL OBJECT RECOGNITION - NLP - CONCEPTS - CREATING AN EMOTIONAL SYSTEM - GENERAL LEARNING - EMBODIED/ GROUNDED KNOWLEDGE - VISUAL/SENSORY THINKING.- EVERY DIMENSION IN SHORT OF "IMAGINATION". A lot of good thinking has gone into how to attack each of the problems you listed above. I am quite sure that if I spent less than a week doing Google research on each such problem I could find at least twenty very good article on how to attack each of them. Yes, most of the approaches dont work very well yet, but they dont have the benefit sufficiently large integrated systems. In AI more is more. More knowledge provides more restraint, which leads to faster and better solutions. More knowledge provides more context specific probabilities and models. World knowledge helps solve the problem of common sense. Massive sensory and emotional labeling provide grounding. Massive associations provide meaning and thus appropriate implication. More computational power allows more alternatives to be explored. Moore is more. In my mind the questions is not whether or not each of these problems can be solved, it is how much time, hardware, and tweaking will be required to perform them at a human level. For example, having such a large system learn how to run itself automatically is non-trivial because the size of the problem space is very large. To get it all to work together well automatically might requires some significant conceptual breakthroughs, it will almost certainly requires some minor ones. We wont know until we try. To give you just one examples of some of the tremendously creative work that has been done in one of the allegedly unsolved problems describe above, read Doug Hofstadters work on Copycat to get a vision of how one elegant system solves the problem of analogy in a clever toy domain in a surprisingly creative way. That basic approach, described at a very broad level, could be mapped into a Novamente-like machine to draw analogizes between virtually any types of patterns that shared similarities at some level which seem worthy of note to the system in the current context. Edward W. Porter Porter & Associates 24 String Bridge S12 Exeter, NH 03833 (617) 494-1722 Fax (617) 494-1822 [EMAIL PROTECTED] -Original Message- From: Mike Tintner [mailto:[EMAIL PROTECTED] Sent: Wednesday, October 03, 2007 9:38 PM To: [email protected] Subject: Re: [agi] breaking the small hardware mindset Edward:The biggest brick wall is the small-hardware mindset that has been absolutely necessary for decades to get anything actually accomplished on the hardware of the day Completely disagree. It's that purely numerical mindset about small/big hardware that I see as so widespread and that shows merely intelligent rather than creative thinking. IQ which you mention is about intelligence not creativity. It's narrow AI as opposed to AGI. Somebody can no doubt give me the figures here - worms and bees and v. simple animals are truly adaptive despite having extremely small brains. (How many cells/ neurons ?) I disagree also re how much has been done. I don't think AGI - correct me - has solved a single creative problem - e.g. creativity - unprogrammed adaptivity - drawing analogies - visual object recognition - NLP - concepts - creating an emotional system - general learning - embodied/ grounded knowledge - visual/sensory thinking.- every dimension in short of "imagination". (Yes, vast creativity has gone into narrow AI, but that's different). If you don't believe it takes major creativity (or "knock-out ideas" pace Voss) , you don't solve creative problems. _ This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/? <http://v2.listbox.com/member/?&; > & - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49608086-0b0a58
Re: [agi] breaking the small hardware mindset
MessageEdward:The biggest brick wall is the small-hardware mindset that has been absolutely necessary for decades to get anything actually accomplished on the hardware of the day Completely disagree. It's that purely numerical mindset about small/big hardware that I see as so widespread and that shows merely intelligent rather than creative thinking. IQ which you mention is about intelligence not creativity. It's narrow AI as opposed to AGI. Somebody can no doubt give me the figures here - worms and bees and v. simple animals are truly adaptive despite having extremely small brains. (How many cells/ neurons ?) I disagree also re how much has been done. I don't think AGI - correct me - has solved a single creative problem - e.g. creativity - unprogrammed adaptivity - drawing analogies - visual object recognition - NLP - concepts - creating an emotional system - general learning - embodied/ grounded knowledge - visual/sensory thinking.- every dimension in short of "imagination". (Yes, vast creativity has gone into narrow AI, but that's different). If you don't believe it takes major creativity (or "knock-out ideas" pace Voss) , you don't solve creative problems. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=49583980-0ee313
