RE: [agi] Re: pattern definition
Mike, It's not all geometric. Patterns need not be defined by vector' lines, or only magnitudes of image properties. The same recognition mechanisms in the brain are emulatable by mathematical, indexable, categorizable, recognizable and systematic, engineered processes. Even images of Madonna- which it's nice to whip out more complex(complicated) examples to entice refutement - you should start off with simpler and then move to complex a.k.a. engineering verses philosophy. But building up a pattern recognizer is not something that is formidable, it's just work that needs to be done. I don't see problems here even with complex imagery, video it's just resources. Sure some algorithms need to be refined and an AGI algorithm verses standard pattern recognition hardcoded- the same algorithms should be applicable to visual, audial, language - over a diverse set of I/O streams. john From: Mike Tintner [mailto:[EMAIL PROTECTED] Sent: Tuesday, May 13, 2008 4:01 PM To: agi@v2.listbox.com Subject: Re: [agi] Re: pattern definition Joe, Thanks for reply - yes, I thought you meant something like this, but it's good to have it spelled out. I think you're making what seems to me to be a v. common mistake among AGI-ers. Yes, you can reduce any image whatsoever on a computer screen, to some set of mathemetical formulae/properties. You can reduce it to so many lines, points, triangles, fractals etc. etc But that's not the problem. The problem is: how do you do that *systematically* for a SET of images (not just one)? How can you guarantee (or come anywhere remotely close) that your system of GEOMETRIC FORM analysis will be able to recognize the same OBJECT FORMS in many different images? - that by breaking complex images down into all those lines, points etc in whatever way you choose, you will be able to recognize, say, the faces, noses, mouths, necks etc in several, different images? Or the plastic bags in them? To focus the problem - in admittedly a v. difficult form (but hopefully it will help you focus better) - how will your *geometric* system recognize the faces and their parts in this set of images, as humans can: http://cr.middlebury.edu/public/spanish/sp371/images/esperpento/goya_viejos. jpg http://www.thebestlinks.com/images/2/2f/El_Greco.jpg http://www.nzine.co.nz/images/articles/picasso_lg.jpg http://www.roussard.com/media/oeuvres/modigliani/lithos/modiglianiIMGP6719.j pg http://www.gerard-schurmann.com/bacon.jpg http://aphrabehn.files.wordpress.com/2007/03/scarfe1.jpg http://www.oppdalfilmklubb.no/img/the-wall.jpg http://www.frederickwildman.com/wildmansite/wmphp/images/hugel/10large.jpg http://internat.martinique.free.fr/images/le_sommeil-salvador_dali.jpg (Note that even a set of ordinarily photographed faces in different positions will still present all kinds of recognition problems). How IOW do you equate an OBJECT FORM like that of face/ nose/ mouth/ chair/ tree/ oak/ handbag etc. etc. with GEOMETRIC FORMS? I am pretty sure that no such equation is possible, period - given that objects can take a vast if not infinite range of forms from different POV's.and in different positions. And that surely is what the history of failures in visual object recognition tells us. (What BTW is *your* explanation of that history of failure? It is rather surprising (no?) that so many AGI-ers can state that images can definitely be analysed geometrically, given the field's striking lack of success here. Surely a certain amount of questioning and soul-or-some-part-of-brain-searching is in order here). I think it's worth thrashing this subject out, because it keeps cropping up here and elsewhere and is so important - and you seem like a reasonable guy, so maybe we ( anyone else) can do that. I think my distinction between geometric form and object form is v. helpful for discussions here, it may not be at all new, but it doesn't seem to be commonplace. P.S. Yes, bucket is a simple object - and it's conceivable that a lot of people might come up with similar mental visualisations of the concept - but even then you might be surprised - and McLuhan's point was re WORD descriptions of buckets and other objects. If you think you can describe it or almost any other object verbally, be my guest :). Even recognising the buckets in different images - (and therefore developing a viable equation of bucket with geometric forms) - strikes me as no simple task for a computer: http://classroomclipart.com/images/gallery/New/Clipart3/paint_brush.jpg http://www.craftamerica.com/images/products/6500_75_rusty_tin_bucket.jpg http://christopher-pelley.abbozzogallery.com/images/red%20bucket.jpg http://www1.istockphoto.com/file_thumbview_approve/487639/2/istockphoto_4876 39_bucket_and_spade.jpg http://z.about.com/d/hotels/1/0/l/G/bucket.jpg http://www.bobjonespaintings.com/large%20images/bucket.jpg http://www.jenklairkids.com/Eshop/products/girl_dog_bucket.jpg
Re: [agi] Re: pattern definition
Joseph H: Mike, what is your stance on vector images? -- Hi Joe, What's the point of this question? Is it something like: geometry can be used to analyse any shapes? --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] Re: pattern definition
Well, I figured the point of the question would be pretty clear seeing as you were claiming a logical/mathematical description of images would be inadequate, but I don't think that could be further from the truth... You could recreate a large amount of detail in an image using mathematics and it would be a great deal more compact of a description than a bitmap representation. AND, you could store the mathematical properties of the image in a DB of some sort to find similar shapes within a large body of images. When you remember scenes from years ago, it is unlikely that you remember which way the grain of the wood was facing, or how many scratches were on the left side of a corner table's handle... so why not represent them in a similar manner as vector images? Using a mathematical description would allow for a more compact, searchable, and inference-available representation. To me, keeping a little box of mathematical expressions to describe an image is a far better choice of both memory and potential processing power than to lug around a bitmap or any sort, unless you want to store the image in case you find another way to interpret it. Though humans don't remember everyday scenes through mathematical description, we do prune out the irrelevant stuff by only remembering general shapes, common textures, and orientations (unless we make it a priority to remember specific features). Mathematical equations and logical statements might not tell YOU a lot about an image, but if someone were to sit down and carefully describe an image using logical statements, equalities, and mathematical expressions, and if someone were to sit down and carefully read these... with time the image would emerge, though we humans aren't suited for this task, a machine will be more than capable, and it would be a much wiser use of resources. - Joe --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] Re: pattern definition
Mike, here's your bucket. Circle(0,50,10) Circle(0,45,10) Ring(0,45,6,8) Cylinder(0,50,45,10) Cylinder(0,45,-10,8) Disk(0,-10,8) - Joe --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] Re: pattern definition
Joe, Thanks for reply - yes, I thought you meant something like this, but it's good to have it spelled out. I think you're making what seems to me to be a v. common mistake among AGI-ers. Yes, you can reduce any image whatsoever on a computer screen, to some set of mathemetical formulae/properties. You can reduce it to so many lines, points, triangles, fractals etc. etc But that's not the problem. The problem is: how do you do that *systematically* for a SET of images (not just one)? How can you guarantee (or come anywhere remotely close) that your system of GEOMETRIC FORM analysis will be able to recognize the same OBJECT FORMS in many different images? - that by breaking complex images down into all those lines, points etc in whatever way you choose, you will be able to recognize, say, the faces, noses, mouths, necks etc in several, different images? Or the plastic bags in them? To focus the problem - in admittedly a v. difficult form (but hopefully it will help you focus better) - how will your *geometric* system recognize the faces and their parts in this set of images, as humans can: http://cr.middlebury.edu/public/spanish/sp371/images/esperpento/goya_viejos.jpg http://www.thebestlinks.com/images/2/2f/El_Greco.jpg http://www.nzine.co.nz/images/articles/picasso_lg.jpg http://www.roussard.com/media/oeuvres/modigliani/lithos/modiglianiIMGP6719.jpg http://www.gerard-schurmann.com/bacon.jpg http://aphrabehn.files.wordpress.com/2007/03/scarfe1.jpg http://www.oppdalfilmklubb.no/img/the-wall.jpg http://www.frederickwildman.com/wildmansite/wmphp/images/hugel/10large.jpg http://internat.martinique.free.fr/images/le_sommeil-salvador_dali.jpg (Note that even a set of ordinarily photographed faces in different positions will still present all kinds of recognition problems). How IOW do you equate an OBJECT FORM like that of face/ nose/ mouth/ chair/ tree/ oak/ handbag etc. etc. with GEOMETRIC FORMS? I am pretty sure that no such equation is possible, period - given that objects can take a vast if not infinite range of forms from different POV's.and in different positions. And that surely is what the history of failures in visual object recognition tells us. (What BTW is *your* explanation of that history of failure? It is rather surprising (no?) that so many AGI-ers can state that images can definitely be analysed geometrically, given the field's striking lack of success here. Surely a certain amount of questioning and soul-or-some-part-of-brain-searching is in order here). I think it's worth thrashing this subject out, because it keeps cropping up here and elsewhere and is so important - and you seem like a reasonable guy, so maybe we ( anyone else) can do that. I think my distinction between geometric form and object form is v. helpful for discussions here, it may not be at all new, but it doesn't seem to be commonplace. P.S. Yes, bucket is a simple object - and it's conceivable that a lot of people might come up with similar mental visualisations of the concept - but even then you might be surprised - and McLuhan's point was re WORD descriptions of buckets and other objects. If you think you can describe it or almost any other object verbally, be my guest :). Even recognising the buckets in different images - (and therefore developing a viable equation of bucket with geometric forms) - strikes me as no simple task for a computer: http://classroomclipart.com/images/gallery/New/Clipart3/paint_brush.jpg http://www.craftamerica.com/images/products/6500_75_rusty_tin_bucket.jpg http://christopher-pelley.abbozzogallery.com/images/red%20bucket.jpg http://www1.istockphoto.com/file_thumbview_approve/487639/2/istockphoto_487639_bucket_and_spade.jpg http://z.about.com/d/hotels/1/0/l/G/bucket.jpg http://www.bobjonespaintings.com/large%20images/bucket.jpg http://www.jenklairkids.com/Eshop/products/girl_dog_bucket.jpg http://annievic.accountsupport.com/images/beachrosebucket.jpg http://www.entretienardiz.com/images/cleaning_bucket.jpg Well, I figured the point of the question would be pretty clear seeing as you were claiming a logical/mathematical description of images would be inadequate, but I don't think that could be further from the truth... You could recreate a large amount of detail in an image using mathematics and it would be a great deal more compact of a description than a bitmap representation. AND, you could store the mathematical properties of the image in a DB of some sort to find similar shapes within a large body of images. When you remember scenes from years ago, it is unlikely that you remember which way the grain of the wood was facing, or how many scratches were on the left side of a corner table's handle... so why not represent them in a similar manner as vector images? Using a mathematical description would allow for a more compact, searchable, and inference-available representation. To me, keeping a little box of
Re: [agi] Re: pattern definition
Joe, And here's a perhaps easier [?], certainly more commonplace set - how will your system recognize each is Madonna: http://www.the-planets.com/madonna/madonna_200.jpg http://www.ouvre.com/wp-content/banniere-itms-madonna.png http://www.metroactive.com/papers/metro/01.04.96/gifs/madonna1-9601.gif http://www.kabeleins.de/imperia/md/images/musik/galerien/madonna/madonna_10_303_404_Schwarzkopf.jpg http://www.itongadol.com.ar/imagenes/madonna22.jpg dan michaels [EMAIL PROTECTED] Mike, here's your bucket. Circle(0,50,10) Circle(0,45,10) Ring(0,45,6,8) Cylinder(0,50,45,10) Cylinder(0,45,-10,8) Disk(0,-10,8) - Joe -- agi | Archives | Modify Your Subscription --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] Re: pattern definition
Boris: I define intelligence as an ability to predict/plan by discovering projecting patterns within an input flow. IOW a capacity to generalize. A general intelligence is something that generalizes from incoming info. about the world. Well, no it can't be just that. Look at what you write at the end of your blog: Hope this makes sense. And it doesn't literally make much sense because your blog has a lot of generalizations with no examples - no individualizations/particularisations of, for example, what individual/particular problems your algorithms might apply to. The making sense level of your brain - an AGI that works - is the level that seeks individual examples (and exceptions) for every generalization. A general intelligence doesn't just generalize, it individualizes. It can talk not just about the field of AGI but about Boris K, Ben G., Stephen Reed, etc etc. And it has to, otherwise those generalizations don't make sense. I'm stressing this because so many people's ideas about AGI like yours involve only, or almost only a generalizing intelligence with no individualizing, sensemaking level. Boris: Entities must not be multiplied unnecessarily. William of Okkam. A pattern is a set of matching inputs. A match is a partial identity of the comparands. The comparands for general intelligence must incrementally indefinitely scale in complexity. The scaling must start from the bottom: uncompressed single-integer comparands, the match here is the sum of bitwise AND. For more see my blog: http://scalable-intelligence.blogspot.com/ Boris. - Original Message - From: Richard Loosemore [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 08, 2008 1:17 PM Subject: [agi] Re: pattern definition [EMAIL PROTECTED] wrote: Hello I am writing a literature review on AGI and I am mentioning the definition of pattern as explained by Ben in his work. A pattern is a representation of an object on a simpler scale. For example, a pattern in a drawing of a mathematical curve could be a program that can compute the curve from a formula (Looks et al. 2004). My supervisor told me that she doesn?t see how this can be simpler than the actual drawing. Any other definition I could use in the same context to explain to a non-technical audience? thanks xav Xav, [I am copying this to the AGI mailing list because it is more appropriate there than on Singularity] A more general definition of pattern would include the idea that there is a collection of mechanisms that take in a source of information (e.g. an image consisting of a grid of pixels) and respond in such a way that each mechanism 'triggers' in some way when a particular arrangement of signal values appears in the information source. Note that the triggering of each mechanism is the 'recognition' of a pattern, and the mechanism in question is a 'recognizer' of a pattern. (In this way of looking at things, there are many mechanisms, one for each pattern). The 'particular arrangement of signal values' is the pattern itself. Most importantly note that a mechanism does not have to trigger for some exact, deterministic set of signal values. For example, a mechanism could respond in a stochastic, noisy way to a whole bunch of different arrangements of signal values. It is allowed to be slightly inconsistent, and not always respond in the same way to the same input (although it would be a particularly bad pattern recognizer if it did not behave in a reasonably consistent way!). The amount of the 'triggering' reaction does not have to be all-or-nothing, either: the mechanism can give a graded response. What the above paragraph means is that the thing that we call a 'pattern' is actually 'whatever makes a mechanism trigger', and we have to be extremely tolerant of the fact that a wide range of different signal arrangements will give rise to triggering ... so a pattern is something much more amorphous and hard to define than simply *one* arrangement of signals. Finally, there is one more twist to this definition, which is very important. Everything said above was about arrangements of signals in the primary information source ... but we also allow that some mechanisms are designed to trigger on an arrangement of other *mechanisms*, not just primary input signals. In other words, this pattern finding system is hierarchical, and there can be abstract patterns. This definition of pattern is the most general one that I know of. I use it in my own work, but I do not know if it has been explicitly published and named by anyone else. In this conception, patterns are defined by the mechanisms that trigger, and further deponent sayeth not what they are, in any more fundamental way. And one last thing: as far as I can seem this does not easily map onto the concept of Kolmogorov complexity. At least, the mapping is very awkward and uninformative, if it exists. If a
RE: [agi] Re: pattern definition
So many overloads - pattern, complexity, atoms - can't we come up with new terms like schfinkledorfs? - but a very interesting question is - given an image of W x H pixels of 1 bit depth (on or off), one frame, how many patterns exist within this grid? When you think about it, it becomes an extremely difficult question to answer because within a static image you can have dupes, different sizes, dimensions, distortions, compressions, expansions, combo's... it's crazy. BUT, there is a pattern to the patterns - there's a mathematical description of them. John -Original Message- From: Richard Loosemore [mailto:[EMAIL PROTECTED] Sent: Thursday, May 08, 2008 11:18 AM To: agi@v2.listbox.com Subject: [agi] Re: pattern definition [EMAIL PROTECTED] wrote: Hello I am writing a literature review on AGI and I am mentioning the definition of pattern as explained by Ben in his work. A pattern is a representation of an object on a simpler scale. For example, a pattern in a drawing of a mathematical curve could be a program that can compute the curve from a formula (Looks et al. 2004). My supervisor told me that she doesn?t see how this can be simpler than the actual drawing. Any other definition I could use in the same context to explain to a non-technical audience? thanks xav Xav, [I am copying this to the AGI mailing list because it is more appropriate there than on Singularity] A more general definition of pattern would include the idea that there is a collection of mechanisms that take in a source of information (e.g. an image consisting of a grid of pixels) and respond in such a way that each mechanism 'triggers' in some way when a particular arrangement of signal values appears in the information source. Note that the triggering of each mechanism is the 'recognition' of a pattern, and the mechanism in question is a 'recognizer' of a pattern. (In this way of looking at things, there are many mechanisms, one for each pattern). The 'particular arrangement of signal values' is the pattern itself. Most importantly note that a mechanism does not have to trigger for some exact, deterministic set of signal values. For example, a mechanism could respond in a stochastic, noisy way to a whole bunch of different arrangements of signal values. It is allowed to be slightly inconsistent, and not always respond in the same way to the same input (although it would be a particularly bad pattern recognizer if it did not behave in a reasonably consistent way!). The amount of the 'triggering' reaction does not have to be all-or-nothing, either: the mechanism can give a graded response. What the above paragraph means is that the thing that we call a 'pattern' is actually 'whatever makes a mechanism trigger', and we have to be extremely tolerant of the fact that a wide range of different signal arrangements will give rise to triggering ... so a pattern is something much more amorphous and hard to define than simply *one* arrangement of signals. Finally, there is one more twist to this definition, which is very important. Everything said above was about arrangements of signals in the primary information source ... but we also allow that some mechanisms are designed to trigger on an arrangement of other *mechanisms*, not just primary input signals. In other words, this pattern finding system is hierarchical, and there can be abstract patterns. This definition of pattern is the most general one that I know of. I use it in my own work, but I do not know if it has been explicitly published and named by anyone else. In this conception, patterns are defined by the mechanisms that trigger, and further deponent sayeth not what they are, in any more fundamental way. And one last thing: as far as I can seem this does not easily map onto the concept of Kolmogorov complexity. At least, the mapping is very awkward and uninformative, if it exists. If a mechanism triggers on a possibly stochastic, nondeterminstic set of features, it can hardly be realised by a feasible algorithm, so talking about a pattern as an algorithm that can generate the source seems, to me at least, to be unworkable. Hope that is useful. Richard Loosemore P.S. Nice to see some Welsh in the boilerplate stuff at the bottom of your message. I used to work at Bangor in the early 90s, so it brought back fond memories to see Prifysgol Bangor! Are you in the Psychology department? --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?; 2bb036 Powered by Listbox: http://www.listbox.com --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your
Re: [agi] Re: pattern definition
And it doesn't literally make much sense because your blog has a lot of generalizations with no examples - no individualizations/particularisations of, for example, what individual/particular problems your algorithms might apply to. The making sense level of your brain - an AGI that works - is the level that seeks individual examples (and exceptions) for every generalization. If you need examples you're in the wrong field. A general intelligence doesn't just generalize, it individualizes. It can talk not just about the field of AGI but about Boris K, Ben G., Stephen Reed, etc etc. And it has to, otherwise those generalizations don't make sense. I'm stressing this because so many people's ideas about AGI like yours involve only, or almost only a generalizing intelligence with no individualizing, sensemaking level. Boris: Entities must not be multiplied unnecessarily. William of Okkam. A pattern is a set of matching inputs. A match is a partial identity of the comparands. The comparands for general intelligence must incrementally indefinitely scale in complexity. The scaling must start from the bottom: uncompressed single-integer comparands, the match here is the sum of bitwise AND. For more see my blog: http://scalable-intelligence.blogspot.com/ Boris. - Original Message - From: Richard Loosemore [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 08, 2008 1:17 PM Subject: [agi] Re: pattern definition [EMAIL PROTECTED] wrote: Hello I am writing a literature review on AGI and I am mentioning the definition of pattern as explained by Ben in his work. A pattern is a representation of an object on a simpler scale. For example, a pattern in a drawing of a mathematical curve could be a program that can compute the curve from a formula (Looks et al. 2004). My supervisor told me that she doesn?t see how this can be simpler than the actual drawing. Any other definition I could use in the same context to explain to a non-technical audience? thanks xav Xav, [I am copying this to the AGI mailing list because it is more appropriate there than on Singularity] A more general definition of pattern would include the idea that there is a collection of mechanisms that take in a source of information (e.g. an image consisting of a grid of pixels) and respond in such a way that each mechanism 'triggers' in some way when a particular arrangement of signal values appears in the information source. Note that the triggering of each mechanism is the 'recognition' of a pattern, and the mechanism in question is a 'recognizer' of a pattern. (In this way of looking at things, there are many mechanisms, one for each pattern). The 'particular arrangement of signal values' is the pattern itself. Most importantly note that a mechanism does not have to trigger for some exact, deterministic set of signal values. For example, a mechanism could respond in a stochastic, noisy way to a whole bunch of different arrangements of signal values. It is allowed to be slightly inconsistent, and not always respond in the same way to the same input (although it would be a particularly bad pattern recognizer if it did not behave in a reasonably consistent way!). The amount of the 'triggering' reaction does not have to be all-or-nothing, either: the mechanism can give a graded response. What the above paragraph means is that the thing that we call a 'pattern' is actually 'whatever makes a mechanism trigger', and we have to be extremely tolerant of the fact that a wide range of different signal arrangements will give rise to triggering ... so a pattern is something much more amorphous and hard to define than simply *one* arrangement of signals. Finally, there is one more twist to this definition, which is very important. Everything said above was about arrangements of signals in the primary information source ... but we also allow that some mechanisms are designed to trigger on an arrangement of other *mechanisms*, not just primary input signals. In other words, this pattern finding system is hierarchical, and there can be abstract patterns. This definition of pattern is the most general one that I know of. I use it in my own work, but I do not know if it has been explicitly published and named by anyone else. In this conception, patterns are defined by the mechanisms that trigger, and further deponent sayeth not what they are, in any more fundamental way. And one last thing: as far as I can seem this does not easily map onto the concept of Kolmogorov complexity. At least, the mapping is very awkward and uninformative, if it exists. If a mechanism triggers on a possibly stochastic, nondeterminstic set of features, it can hardly be realised by a feasible algorithm, so talking about a pattern as an algorithm that can generate the source seems, to me at least, to be unworkable. Hope that is useful. Richard Loosemore P.S.
Re: [agi] Re: pattern definition
Jim, I doubt that your specification equals my individualization. If I want to be able to recognize the individuals, Curtis/Brian/Carl/ and Billi Bromer,only images will do it: http://www.dunningmotorsales.com/IMAGES/people/Curtis%20Bromer.jpg http://www.newyorksocialdiary.com/socialdiary/2006/02_27_06/images/BRomer-Sir-PThomas.jpg http://www.stellarsales.com/images/carl3.jpg http://www.dec-sped.org/images/executiveboard/Billi_Bromer.jpg If you'd like to try a logical, verbal, mathematical description of any oneof those individuals, so that someone will be sure to recognize them, be my guest :). That's why they put photos on your passport and not program printouts or verbal descriptions. All the words in the world won't tell you what a bucket looks like. McLuhan Jim/MT:, The making sense level of your brain - an AGI that works - is the level that seeks individual examples (and exceptions) for every generalization. A general intelligence doesn't just generalize, it individualizes. It can talk not just about the field of AGI but about Boris K, Ben G., Stephen Reed, etc etc. And it has to, otherwise those generalizations don't make sense. I'm stressing this because so many people's ideas about AGI ... involve only, or almost only a generalizing intelligence with no individualizing, sensemaking level. -- I agree with what Mike was saying in the part of his message I quoted here, except that the ability to understand involves the ability to make generalizations. But, a generalization can be seen as a specific relative to another level of generalization. I also think most people who have been seriously involved in AI and who think of AI in terms of generalization realize that specification must play an important role in understanding. Jim Bromer -- Be a better friend, newshound, and know-it-all with Yahoo! Mobile. Try it now. -- agi | Archives | Modify Your Subscription --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] Re: pattern definition
Mike, what is your stance on vector images? --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
Re: [agi] Re: pattern definition
Entities must not be multiplied unnecessarily. William of Okkam. A pattern is a set of matching inputs. A match is a partial identity of the comparands. The comparands for general intelligence must incrementally indefinitely scale in complexity. The scaling must start from the bottom: uncompressed single-integer comparands, the match here is the sum of bitwise AND. For more see my blog: http://scalable-intelligence.blogspot.com/ Boris. - Original Message - From: Richard Loosemore [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 08, 2008 1:17 PM Subject: [agi] Re: pattern definition [EMAIL PROTECTED] wrote: Hello I am writing a literature review on AGI and I am mentioning the definition of pattern as explained by Ben in his work. A pattern is a representation of an object on a simpler scale. For example, a pattern in a drawing of a mathematical curve could be a program that can compute the curve from a formula (Looks et al. 2004). My supervisor told me that she doesn?t see how this can be simpler than the actual drawing. Any other definition I could use in the same context to explain to a non-technical audience? thanks xav Xav, [I am copying this to the AGI mailing list because it is more appropriate there than on Singularity] A more general definition of pattern would include the idea that there is a collection of mechanisms that take in a source of information (e.g. an image consisting of a grid of pixels) and respond in such a way that each mechanism 'triggers' in some way when a particular arrangement of signal values appears in the information source. Note that the triggering of each mechanism is the 'recognition' of a pattern, and the mechanism in question is a 'recognizer' of a pattern. (In this way of looking at things, there are many mechanisms, one for each pattern). The 'particular arrangement of signal values' is the pattern itself. Most importantly note that a mechanism does not have to trigger for some exact, deterministic set of signal values. For example, a mechanism could respond in a stochastic, noisy way to a whole bunch of different arrangements of signal values. It is allowed to be slightly inconsistent, and not always respond in the same way to the same input (although it would be a particularly bad pattern recognizer if it did not behave in a reasonably consistent way!). The amount of the 'triggering' reaction does not have to be all-or-nothing, either: the mechanism can give a graded response. What the above paragraph means is that the thing that we call a 'pattern' is actually 'whatever makes a mechanism trigger', and we have to be extremely tolerant of the fact that a wide range of different signal arrangements will give rise to triggering ... so a pattern is something much more amorphous and hard to define than simply *one* arrangement of signals. Finally, there is one more twist to this definition, which is very important. Everything said above was about arrangements of signals in the primary information source ... but we also allow that some mechanisms are designed to trigger on an arrangement of other *mechanisms*, not just primary input signals. In other words, this pattern finding system is hierarchical, and there can be abstract patterns. This definition of pattern is the most general one that I know of. I use it in my own work, but I do not know if it has been explicitly published and named by anyone else. In this conception, patterns are defined by the mechanisms that trigger, and further deponent sayeth not what they are, in any more fundamental way. And one last thing: as far as I can seem this does not easily map onto the concept of Kolmogorov complexity. At least, the mapping is very awkward and uninformative, if it exists. If a mechanism triggers on a possibly stochastic, nondeterminstic set of features, it can hardly be realised by a feasible algorithm, so talking about a pattern as an algorithm that can generate the source seems, to me at least, to be unworkable. Hope that is useful. Richard Loosemore P.S. Nice to see some Welsh in the boilerplate stuff at the bottom of your message. I used to work at Bangor in the early 90s, so it brought back fond memories to see Prifysgol Bangor! Are you in the Psychology department? --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com