Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Hello Boris, and welcome to the list. I didn't understand your algorithm, you use many terms that you didn't define. It probably would be clearer if you use some kind of pseudocode and systematically describe all occurring procedures. But I think more fundamental questions that need clarifying won't depend on these. What is it that your system tries to predict? Does it predict only specific terminal inputs, values on the ends of its sensors? Or something else? When does prediction occur? What is this prediction for? How does it help? How does the system use it? What use is this ability of the system for us? -- Vladimir Nesov [EMAIL PROTECTED] --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Although I symphathize with some of Hawkin's general ideas about unsupervised learning, his current HTM framework is unimpressive in comparison with state-of-the-art techniques such as Hinton's RBM's, LeCun's convolutional nets and the promising low-entropy coding variants. But it should be quite clear that such methods could eventually be very handy for AGI. For example, many of you would agree that a reliable, computationally affordable solution to Vision is a crucial factor for AGI: much of the world's information, even on the internet, is encoded in audiovisual information. Extracting (sub)symbolic semantics from these sources would open a world of learning data to symbolic systems. An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? Vision may be classified under Narrow AI, but I reckon that an AGI can never understand our physical world without a reliable perceptual system. Therefore, perception is essential for any AGI reasoning about physical entities! Greets, Durk On Sun, Mar 30, 2008 at 4:34 PM, Derek Zahn [EMAIL PROTECTED] wrote: It seems like a reasonable and not uncommon idea that an AI could be built as a mostly-hierarchical autoassiciative memory. As you point out, it's not so different from Hawkins's ideas. Neighboring pixels will correlate in space and time; features such as edges should become principle components given enough data, and so on. There is a bunch of such work on self-organizing the early visual system like this. That overall concept doesn't get you very far though; the trick is to make it work past the first few rather obvious feature extraction stages of sensory data, and to account for things like episodic memory, language use, goal-directed behavior, and all other cognitive activity that is not just statistical categorization. I sympathize with your approach and wish you luck. If you think you have something that produce more than Hawkins has with his HTM, please explain it with enough precision that we can understand the details. -- *agi* | Archives http://www.listbox.com/member/archive/303/=now http://www.listbox.com/member/archive/rss/303/ | Modifyhttp://www.listbox.com/member/?;Your Subscription 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On Sun, Mar 30, 2008 at 7:23 PM, Kingma, D.P. [EMAIL PROTECTED] wrote: Although I symphathize with some of Hawkin's general ideas about unsupervised learning, his current HTM framework is unimpressive in comparison with state-of-the-art techniques such as Hinton's RBM's, LeCun's convolutional nets and the promising low-entropy coding variants. But it should be quite clear that such methods could eventually be very handy for AGI. For example, many of you would agree that a reliable, computationally affordable solution to Vision is a crucial factor for AGI: much of the world's information, even on the internet, is encoded in audiovisual information. Extracting (sub)symbolic semantics from these sources would open a world of learning data to symbolic systems. An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? Vision may be classified under Narrow AI, but I reckon that an AGI can never understand our physical world without a reliable perceptual system. Therefore, perception is essential for any AGI reasoning about physical entities! At this point I think that although vision doesn't seem absolutely necessary, it may as well be implemented, if it can run on the same substrate as everything else (it probably can). It may prove to be a good playground for prototyping. If it's implemented with moving fovea (which is essentially what LeCun's hack is about) and relies on selective attention (so that only gist of the scene is perceived, read supported on higher levels), it shouldn't require insanely much resources, compared to the rest of reasoning engine. Alas in this picture I give up my previous assessment (of few months back) that reasoning can be implemented efficiently, so that only few active concepts need to figure into computation each tact. In my current model all concepts compute all the time... -- Vladimir Nesov [EMAIL PROTECTED] --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
RE: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
[EMAIL PROTECTED] writes: But it should be quite clear that such methods could eventually be very handy for AGI. I agree with your post 100%, this type of approach is the most interesting AGI-related stuff to me. An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? Even more interesting: How could a symbolic engine ever reason about the real world *with* access to such information? :) --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On 30/03/2008, Kingma, D.P. [EMAIL PROTECTED] wrote: Although I symphathize with some of Hawkin's general ideas about unsupervised learning, his current HTM framework is unimpressive in comparison with state-of-the-art techniques such as Hinton's RBM's, LeCun's convolutional nets and the promising low-entropy coding variants. But it should be quite clear that such methods could eventually be very handy for AGI. For example, many of you would agree that a reliable, computationally affordable solution to Vision is a crucial factor for AGI: much of the world's information, even on the internet, is encoded in audiovisual information. Extracting (sub)symbolic semantics from these sources would open a world of learning data to symbolic systems. An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? So a deafblind person couldn't reason about the real world? Put ear muffs and a blind fold on, see what you can figure out about the world around you. Less certainly, but then you could figure out more about the world if you had magnetic sense like pidgeons. Intelligence is not about the modalities of the data you get, it is about the what you do with the data you do get. All of the data on the web is encoded in electronic form, it is only because of our comfort with incoming photons and phonons that it is translated to video and sound. This fascination with A/V is useful, but does not help us figure out the core issues that are holding us up whilst trying to create AGI. Will Pearson --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Derek: How could a symbolic engine ever reason about the real world *with* access to such information? I hope my work eventually demonstrates a solution to your satisfaction. In the meantime there is evidence from robotics, specifically driverless cars, that real world sensor input can be sufficiently combined and abstracted for use by symbolic route planners. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 - Original Message From: Derek Zahn [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Sunday, March 30, 2008 11:21:52 AM Subject: RE: [agi] Intelligence: a pattern discovery algorithm of scalable complexity. .hmmessage P { margin:0px;padding:0px;} body.hmmessage { FONT-SIZE:10pt;FONT-FAMILY:Tahoma;} [EMAIL PROTECTED] writes: But it should be quite clear that such methods could eventually be very handy for AGI. I agree with your post 100%, this type of approach is the most interesting AGI-related stuff to me. An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? Even more interesting: How could a symbolic engine ever reason about the real world *with* access to such information? :) agi | Archives | Modify Your Subscription Special deal for Yahoo! users friends - No Cost. Get a month of Blockbuster Total Access now http://tc.deals.yahoo.com/tc/blockbuster/text3.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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Durk, Absolutely right about the need for what is essentially an imaginative level of mind. But wrong in thinking: Vision may be classified under Narrow AI You seem to be treating this extra audiovisual perception layer as a purely passive layer. The latest psychology philosophy recognize that this is in fact a level of v. active thought and intelligence. And our culture is only starting to understand imaginative thought generally. Just to begin reorienting your thinking here, I suggest you consider how much time people spend on audiovisual information (esp. tv) vs purely symbolic information (books). And allow for how much and how rapidly even academic thinking is going audiovisual. Know of anyone trying to give computers that extra layer? I saw some vague reference about this recently.of which I have only a confused memory. Durk:Although I symphathize with some of Hawkin's general ideas about unsupervised learning, his current HTM framework is unimpressive in comparison with state-of-the-art techniques such as Hinton's RBM's, LeCun's convolutional nets and the promising low-entropy coding variants. But it should be quite clear that such methods could eventually be very handy for AGI. For example, many of you would agree that a reliable, computationally affordable solution to Vision is a crucial factor for AGI: much of the world's information, even on the internet, is encoded in audiovisual information. Extracting (sub)symbolic semantics from these sources would open a world of learning data to symbolic systems. An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? Vision may be classified under Narrow AI, but I reckon that an AGI can never understand our physical world without a reliable perceptual system. Therefore, perception is essential for any AGI reasoning about physical entities! Greets, Durk On Sun, Mar 30, 2008 at 4:34 PM, Derek Zahn [EMAIL PROTECTED] wrote: It seems like a reasonable and not uncommon idea that an AI could be built as a mostly-hierarchical autoassiciative memory. As you point out, it's not so different from Hawkins's ideas. Neighboring pixels will correlate in space and time; features such as edges should become principle components given enough data, and so on. There is a bunch of such work on self-organizing the early visual system like this. That overall concept doesn't get you very far though; the trick is to make it work past the first few rather obvious feature extraction stages of sensory data, and to account for things like episodic memory, language use, goal-directed behavior, and all other cognitive activity that is not just statistical categorization. I sympathize with your approach and wish you luck. If you think you have something that produce more than Hawkins has with his HTM, please explain it with enough precision that we can understand the details. agi | Archives | Modify Your Subscription -- agi | Archives | Modify Your Subscription -- No virus found in this incoming message. Checked by AVG. Version: 7.5.519 / Virus Database: 269.22.1/1349 - Release Date: 3/29/2008 5:02 PM --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
RE: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Stephen Reed writes: How could a symbolic engine ever reason about the real world *with* access to such information? I hope my work eventually demonstrates a solution to your satisfaction. Me too! In the meantime there is evidence from robotics, specifically driverless cars, that real world sensor input can be sufficiently combined and abstracted for use by symbolic route planners. True enough, that is one answer: by hand-crafting the symbols and the mechanics for instantiating them from subsymbolic structures. We of course hope for better than this but perhaps generalizing these working systems is a practical approach. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Mike, you seem to have misinterpreted my statement. Perception is certainly not 'passive', as it can be described as active inference using a (mostly actively) learned world model. Inference is done on many levels, and could integrate information from various abstraction levels, so I don't see it as an isolated layer. On Sun, Mar 30, 2008 at 6:27 PM, Mike Tintner [EMAIL PROTECTED] wrote: Durk, Absolutely right about the need for what is essentially an imaginative level of mind. But wrong in thinking: Vision may be classified under Narrow AI You seem to be treating this extra audiovisual perception layer as a purely passive layer. The latest psychology philosophy recognize that this is in fact a level of v. active thought and intelligence. And our culture is only starting to understand imaginative thought generally. Just to begin reorienting your thinking here, I suggest you consider how much time people spend on audiovisual information (esp. tv) vs purely symbolic information (books). And allow for how much and how rapidly even academic thinking is going audiovisual. Know of anyone trying to give computers that extra layer? I saw some vague reference about this recently.of which I have only a confused memory. Durk:Although I symphathize with some of Hawkin's general ideas about unsupervised learning, his current HTM framework is unimpressive in comparison with state-of-the-art techniques such as Hinton's RBM's, LeCun's convolutional nets and the promising low-entropy coding variants. But it should be quite clear that such methods could eventually be very handy for AGI. For example, many of you would agree that a reliable, computationally affordable solution to Vision is a crucial factor for AGI: much of the world's information, even on the internet, is encoded in audiovisual information. Extracting (sub)symbolic semantics from these sources would open a world of learning data to symbolic systems. An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? Vision may be classified under Narrow AI, but I reckon that an AGI can never understand our physical world without a reliable perceptual system. Therefore, perception is essential for any AGI reasoning about physical entities! Greets, Durk On Sun, Mar 30, 2008 at 4:34 PM, Derek Zahn [EMAIL PROTECTED] wrote: It seems like a reasonable and not uncommon idea that an AI could be built as a mostly-hierarchical autoassiciative memory. As you point out, it's not so different from Hawkins's ideas. Neighboring pixels will correlate in space and time; features such as edges should become principle components given enough data, and so on. There is a bunch of such work on self-organizing the early visual system like this. That overall concept doesn't get you very far though; the trick is to make it work past the first few rather obvious feature extraction stages of sensory data, and to account for things like episodic memory, language use, goal-directed behavior, and all other cognitive activity that is not just statistical categorization. I sympathize with your approach and wish you luck. If you think you have something that produce more than Hawkins has with his HTM, please explain it with enough precision that we can understand the details. -- *agi* | Archives http://www.listbox.com/member/archive/303/=now http://www.listbox.com/member/archive/rss/303/ | Modifyhttp://www.listbox.com/member/?;Your Subscription http://www.listbox.com -- *agi* | Archives http://www.listbox.com/member/archive/303/=now http://www.listbox.com/member/archive/rss/303/ | Modifyhttp://www.listbox.com/member/?;Your Subscription http://www.listbox.com -- No virus found in this incoming message. Checked by AVG. Version: 7.5.519 / Virus Database: 269.22.1/1349 - Release Date: 3/29/2008 5:02 PM -- *agi* | Archives http://www.listbox.com/member/archive/303/=now http://www.listbox.com/member/archive/rss/303/ | Modifyhttp://www.listbox.com/member/?;Your Subscription 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On Sun, Mar 30, 2008 at 6:48 PM, William Pearson [EMAIL PROTECTED] wrote: On 30/03/2008, Kingma, D.P. [EMAIL PROTECTED] wrote: An audiovisual perception layer generates semantic interpretation on the (sub)symbolic level. How could a symbolic engine ever reason about the real world without access to such information? So a deafblind person couldn't reason about the real world? Put ear muffs and a blind fold on, see what you can figure out about the world around you. Less certainly, but then you could figure out more about the world if you had magnetic sense like pidgeons. Intelligence is not about the modalities of the data you get, it is about the what you do with the data you do get. All of the data on the web is encoded in electronic form, it is only because of our comfort with incoming photons and phonons that it is translated to video and sound. This fascination with A/V is useful, but does not help us figure out the core issues that are holding us up whilst trying to create AGI. Will Pearson Intelligence is not *only* about the modalities of the data you get, but modalities are certainly important. A deafblind person can still learn a lot about the world with taste, smell, and touch, but the senses one has access to defines the limits to the world model one can build. If I put on ear muffs and a blind fold right now, I can still reason quite well using touch, since I have access to a world model build using e.g. vision. If you were deafblind and paralysed since your birth, would you have any possibility of spatial reasoning? No, maybe except for some extremely crude genetically coded heuristics. Sure, you could argue that an intelligence purely based on text, disconnected from the physical world, could be intelligent, but it would have a very hard time reasoning about interaction of entities in the physicial world. It would be unable to understand humans in many aspects: I wouldn't call that generally intelligent. Perception is a about learning and using a model of our physical world. Input is often high-bandwidth, while output is often low-bandwidth and useful for high-level processing (e.g. reasining and memory). Luckily, efficient methods are arising, so I'm quite optimistic about progress towards this aspect of intelligence. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On Sun, Mar 30, 2008 at 10:16 PM, Kingma, D.P. [EMAIL PROTECTED] wrote: Intelligence is not *only* about the modalities of the data you get, but modalities are certainly important. A deafblind person can still learn a lot about the world with taste, smell, and touch, but the senses one has access to defines the limits to the world model one can build. If I put on ear muffs and a blind fold right now, I can still reason quite well using touch, since I have access to a world model build using e.g. vision. If you were deafblind and paralysed since your birth, would you have any possibility of spatial reasoning? No, maybe except for some extremely crude genetically coded heuristics. Sure, you could argue that an intelligence purely based on text, disconnected from the physical world, could be intelligent, but it would have a very hard time reasoning about interaction of entities in the physicial world. It would be unable to understand humans in many aspects: I wouldn't call that generally intelligent. Perception is a about learning and using a model of our physical world. Input is often high-bandwidth, while output is often low-bandwidth and useful for high-level processing (e.g. reasining and memory). Luckily, efficient methods are arising, so I'm quite optimistic about progress towards this aspect of intelligence. One of the requirements that I try to satisfy with my design is ability to equivalently perceive information encoded by seemingly incompatible modalities. For example, visual stream can be encoded using a set of pairs tag,color, where tags are unique labels that correspond to positions of pixels. This set of pairs can be shuffled and supplied using serial input (where tags and colors are encoded as binary words of activation), and system must be able to reconstruct representation as good as that supplied by naturally arranged video input. Of course getting to that point requires careful incremental teaching, but after that there should be no real difference (aside from bandwidth, of course). It might be useful to look at all concepts as 'modalities': you can 'see' your thoughts, when you know a certain theory, you can 'see' how it's applied, how its parts interact, what obvious conclusions are. Prewiring sensory input in a certain way merely pushes learning in certain direction, just like inbuilt drives bias action in theirs. This way, for example, it should be possible to teach a 'modality' for understanding simple graphs encoded as text, so that on one hand text-based input is sufficient, and on the other hand system effectively perceives simple vector graphics. This trick can be used to explain spacial concepts from natural language. But, again, video camera might be a simpler and more powerful way to the same end, even if visual processing is severely limited. -- Vladimir Nesov [EMAIL PROTECTED] --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
[agi] Symbols
Related obliquely to the discussion about pattern discovery algorithms What is a symbol? I am not sure that I am using the words in this post in exactly the same way they are normally used by cognitive scientists; to the extent that causes confusion, I'm sorry. I'd rather use words in their strict conventional sense but I do not fully understand what that is. These thoughts are fuzzier than I'd like; if I was better at de-fuzzifying them I might be a pro instead of an amateur! Proposition: a symbol is a token with both denotative and model-theoretic semantics. The denotative semantacs are what makes a symbol refer to something or be about something. The model-theoretic semantics allow symbol processing operations to occur (such as reasoning). I believe this is a somewhat more restrictive use of the word symbol than is necessarily implied by Newell and Simon in the Physical Symbol System Hypothesis, but my aim is engineering rather than philosophy. I'm actually somewhat skeptical that human beings use symbols in this sense for much of our cognition. We appear to be a million times better at it than any other animal, and that is the special thing that makes us so great, but we still aren't very good at it. However, most of the things we want to build AGI *for* require us to greatly expand the symbol processing capabilities of mere humans. I think we're mostly interested in building artificial scientists and engineers rather than artificial musicians. Since computer programs, engineering drawings, and physics theories are explicitly symbolic constructs, we're more interested in effectively creating symbols than in the totality of the murky subsymbolic world supporting it. To what extent can we separate them? I wish I knew. In this view, subsymbolic simply refers to tokens that lack some of the features of symbols. For example, a representation of a pixel from a camera has clear denotational semantics but it is not elaborated as well as a better symbol would be (the light coming from direction A at time B is not as useful as the light reflecting off of Fred's pinky fingernail). Similarly, and more importantly, subsymbolic products of sensory systems lack useful model-theoretic semantics. The origin of symbols problem involves how those semantics arise -- and to me it's the most interesting piece of the AGI puzzle. Is anybody else interested in this kind of question, or am I simply inventing issues that are not meaningful and useful? --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Vladimir, I agree with you on many issues, but... On Sun, Mar 30, 2008 at 9:03 PM, Vladimir Nesov [EMAIL PROTECTED] wrote: This way, for example, it should be possible to teach a 'modality' for understanding simple graphs encoded as text, so that on one hand text-based input is sufficient, and on the other hand system effectively perceives simple vector graphics. This trick can be used to explain spacial concepts from natural language. But, again, video camera might be a simpler and more powerful way to the same end, even if visual processing is severely limited. Vector graphics can indeed be communicated to an AGI by relatively low-bandwidth textual input. But, unfortunately, the physical world is not made of vector graphics, so reducing the physical world to vector graphics is quite lossy (and computationally expensive an sich). I'm not sure whether you're assuming that vector graphics is very useful for AGI, but I would disagree. Prewiring sensory input in a certain way merely pushes learning in certain direction, just like inbuilt drives bias action in theirs. Who said perception needs to be prewired? Perception should be made efficient by exploiting statistical regularities in the data, not assuming them per se. Regularities in the data (captured by your world model) should tell you where to focus your attention on *most* of the time, not *all* the time ;) --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On Sun, Mar 30, 2008 at 11:33 PM, Kingma, D.P. [EMAIL PROTECTED] wrote: Vector graphics can indeed be communicated to an AGI by relatively low-bandwidth textual input. But, unfortunately, the physical world is not made of vector graphics, so reducing the physical world to vector graphics is quite lossy (and computationally expensive an sich). I'm not sure whether you're assuming that vector graphics is very useful for AGI, but I would disagree. I referred to manually providing explanation in conversational format. Of course it's lossy, but whether it's lossy compared to the real world is not an issue, it's much more important how it compares to 'gist' scheme that we extract from full vision. It's clearly not much. Vision allows to attend to any of huge number of details present in the input, but there are only few details seen at a time. When a specific issue needs a spacial explanation, it can be carried out by explicitly specifying its structure in vector graphics. Prewiring sensory input in a certain way merely pushes learning in certain direction, just like inbuilt drives bias action in theirs. Who said perception needs to be prewired? Perception should be made efficient by exploiting statistical regularities in the data, not assuming them per se. Regularities in the data (captured by your world model) should tell you where to focus your attention on *most* of the time, not *all* the time ;) By prewiring I meant a trivial level, like routing signals from the retina to certain places in the brain, from the start suggesting that nearby pixels on the retina are close together, and making temporal synchrony of signals to be approximately the same as in image on the retina. Bad prewiring would consist in sticking signals from pixels on the retina to random parts of the brain, with random delays. It would take much more effort to acquire good visual perception in this case (and would be impossible on brain wetware). -- Vladimir Nesov [EMAIL PROTECTED] --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Alright, agreed with all you say. If I understood correctly, your system (at the moment) assumes scene descriptions at a level higher than pixels, but certainly lower than objects. An application of such system seems be a simulated, virtual world where such descriptions are at hand... Is this indeed the direction you're going? Greets, Durk On Sun, Mar 30, 2008 at 10:00 PM, Vladimir Nesov [EMAIL PROTECTED] wrote: On Sun, Mar 30, 2008 at 11:33 PM, Kingma, D.P. [EMAIL PROTECTED] wrote: Vector graphics can indeed be communicated to an AGI by relatively low-bandwidth textual input. But, unfortunately, the physical world is not made of vector graphics, so reducing the physical world to vector graphics is quite lossy (and computationally expensive an sich). I'm not sure whether you're assuming that vector graphics is very useful for AGI, but I would disagree. I referred to manually providing explanation in conversational format. Of course it's lossy, but whether it's lossy compared to the real world is not an issue, it's much more important how it compares to 'gist' scheme that we extract from full vision. It's clearly not much. Vision allows to attend to any of huge number of details present in the input, but there are only few details seen at a time. When a specific issue needs a spacial explanation, it can be carried out by explicitly specifying its structure in vector graphics. Prewiring sensory input in a certain way merely pushes learning in certain direction, just like inbuilt drives bias action in theirs. Who said perception needs to be prewired? Perception should be made efficient by exploiting statistical regularities in the data, not assuming them per se. Regularities in the data (captured by your world model) should tell you where to focus your attention on *most* of the time, not *all* the time ;) By prewiring I meant a trivial level, like routing signals from the retina to certain places in the brain, from the start suggesting that nearby pixels on the retina are close together, and making temporal synchrony of signals to be approximately the same as in image on the retina. Bad prewiring would consist in sticking signals from pixels on the retina to random parts of the brain, with random delays. It would take much more effort to acquire good visual perception in this case (and would be impossible on brain wetware). -- Vladimir Nesov [EMAIL PROTECTED] --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On Mon, Mar 31, 2008 at 12:21 AM, Kingma, D.P. [EMAIL PROTECTED] wrote: Alright, agreed with all you say. If I understood correctly, your system (at the moment) assumes scene descriptions at a level higher than pixels, but certainly lower than objects. An application of such system seems be a simulated, virtual world where such descriptions are at hand... Is this indeed the direction you're going? I'm far from dealing with high-level stuff, so it's only in design. Vector graphics that I talked about was supposed to be provided manually by a human. For example, it can be a part of explanation of what 'between' word is about. Alternatively a kind of sketchpad can be used. My point is that 'modality' seems to be a learnable thing, that can be stimulated not only by direct sensory input, but also by learned inferences coming from completely different modalities. -- Vladimir Nesov [EMAIL PROTECTED] --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Logical Satisfiability...Get used to it.
I agree with Richard and hereby formally request that Ben chime in. It is my contention that SAT is a relatively narrow form of Narrow AI and not general enough to be on an AGI list. This is not meant, in any way shape or form, to denigrate the work that you are doing. It is very important work. It's just that you're performing the equivalent of presenting a biology paper at a physics convention.:-) - Original Message - From: Jim Bromer To: agi@v2.listbox.com Sent: Sunday, March 30, 2008 11:52 AM Subject: **SPAM** Re: [agi] Logical Satisfiability...Get used to it. On the contrary, Vladimir is completely correct in requesting that the discussion go elsewhere: this has no relevance to the AGI list, and there are other places where it would be pertinent. Richard Loosemore If Ben doesn't want me to continue, I will stop posting to this group. Otherwise please try to understand what I said about the relevance of SAT to AGI and try to address the specific issues that I mentioned. On the other hand, if you don't want to waste your time in this kind of discussion then do just that: Stay out of it. Jim Bromer Jim Bromer -- agi | Archives | Modify Your Subscription --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Symbols
From: Derek Zahn Is anybody else interested in this kind of question, or am I simply inventing issues that are not meaningful and useful? The issues you bring up are key/core to a major part of AGI. Unfortunately, they are also issues hashed over way to many times in a mailing list format where resolution is nearly impossible. Might I suggest attempting to do this in wiki format instead? I would be very interested in participating. Mark --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
True enough, that is one answer: by hand-crafting the symbols and the mechanics for instantiating them from subsymbolic structures. We of course hope for better than this but perhaps generalizing these working systems is a practical approach. Um. That is what is known as the grounding problem. I'm sure that Richard Loosemore would be more than happy to send references explaining why this is not productive. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
From: Kingma, D.P. [EMAIL PROTECTED] Sure, you could argue that an intelligence purely based on text, disconnected from the physical world, could be intelligent, but it would have a very hard time reasoning about interaction of entities in the physicial world. It would be unable to understand humans in many aspects: I wouldn't call that generally intelligent. Given sufficient bandwidth, why would it have a hard time reasoning about interaction of entities? You could describe vision down to the pixel, hearing down to the pitch and decibel, touch down to the sensation, etc. and the system could internally convert it to exactly what a human feels. You could explain to it all the known theories of psychology and give it the personal interactions of billions of people. Sure, that's a huge amount of bandwidth, but it proves that your statement is inaccurate. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Logical Satisfiability...Get used to it.
My judgment as list moderator: 1) Discussions of particular, speculative algorithms for solving SAT are not really germane for this list 2) Announcements of really groundbreaking new SAT algorithms would certainly be germane to the list 3) Discussions of issues specifically regarding the integration of SAT solvers into AGI architectures are highly relevant to this list 4) If you think some supernatural being placed an insight in your mind, you're probably better off NOT mentioning this when discussing the insight in a scientific forum, as it will just cause your idea to be taken way less seriously by a vast majority of scientific-minded people... -- Ben G, List Owner On Sun, Mar 30, 2008 at 4:41 PM, Mark Waser [EMAIL PROTECTED] wrote: I agree with Richard and hereby formally request that Ben chime in. It is my contention that SAT is a relatively narrow form of Narrow AI and not general enough to be on an AGI list. This is not meant, in any way shape or form, to denigrate the work that you are doing. It is very important work. It's just that you're performing the equivalent of presenting a biology paper at a physics convention.:-) - Original Message - From: Jim Bromer To: agi@v2.listbox.com Sent: Sunday, March 30, 2008 11:52 AM Subject: **SPAM** Re: [agi] Logical Satisfiability...Get used to it. On the contrary, Vladimir is completely correct in requesting that the discussion go elsewhere: this has no relevance to the AGI list, and there are other places where it would be pertinent. Richard Loosemore If Ben doesn't want me to continue, I will stop posting to this group. Otherwise please try to understand what I said about the relevance of SAT to AGI and try to address the specific issues that I mentioned. On the other hand, if you don't want to waste your time in this kind of discussion then do just that: Stay out of it. Jim Bromer Jim Bromer agi | Archives | Modify Your Subscription agi | Archives | Modify Your Subscription -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC Director of Research, SIAI [EMAIL PROTECTED] If men cease to believe that they will one day become gods then they will surely become worms. -- Henry Miller --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
From: Kingma, D.P. [EMAIL PROTECTED] Vector graphics can indeed be communicated to an AGI by relatively low-bandwidth textual input. But, unfortunately, the physical world is not made of vector graphics, so reducing the physical world to vector graphics is quite lossy (and computationally expensive an sich). Huh? Intelligence is based upon lossyness and the ability to lose rarely relevant (probably incorrect) outlier information is frequently the key to making problems tractable (though it can also set you up for failure when you miss a phase transition by mistaking it for just an odd outlier :-) since it forms the basis of discovery by analogy. Matt Mahoney's failure to recognize this has him trapped in *exact* compression hell.;-) Who said perception needs to be prewired? Perception should be made efficient by exploiting statistical regularities in the data, not assuming them per se. Regularities in the data (captured by your world model) should tell you where to focus your attention on *most* of the time, not *all* the time ;) Which is the correct answer to the grounding problem. Thank you. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Logical Satisfiability...Get used to it.
4) If you think some supernatural being placed an insight in your mind, you're probably better off NOT mentioning this when discussing the insight in a scientific forum, as it will just cause your idea to be taken way less seriously by a vast majority of scientific-minded people... Awesome answer! However, only *some* religions believe in supernatural beings and I, personally, have never seen any evidence supporting such a thing. Have you been having such experiences and been avoiding mentioning them because you're afraid for your reputation? Ben, I'm worried about you now.;-) --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
RE: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Mark Waser writes: True enough, that is one answer: by hand-crafting the symbols and the mechanics for instantiating them from subsymbolic structures. We of course hope for better than this but perhaps generalizing these working systems is a practical approach. Um. That is what is known as the grounding problem. I'm sure that Richard Loosemore would be more than happy to send references explaining why this is not productive. It's not the grounding problem. The symbols crashing around inthese robotic systems are very well grounded. The problem is that these systems are narrow, not that they manipulateungrounded symbols. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Symbols
In this surrounding discussions, everyone seems deeply confused - it's nothing personal, so is our entire culture - about the difference between SYMBOLS 1. Derek Zahn curly hair big jaw intelligent eyes . etc. etc and IMAGES 2. http://robot-club.com/teamtoad/nerc/h2-derek-sunflower.JPG I suggest that everytime you want to think about this area, you all put symbols besides the corresponding images, and slowly it will start to become clear that each does things the other CAN'T do, period. We are all next to illiterate - and I mean, mind-blowingly ignorant - about how images function. What, for example, does an image of D.Z. or any person, do, that no amount of symbols - whether words, numbers, algebraic formulae, or logical propositions - could ever do? Why are images almost always more powerful than the corresponding symbols? Why do they communicate so much faster? Derek: Related obliquely to the discussion about pattern discovery algorithms What is a symbol? I am not sure that I am using the words in this post in exactly the same way they are normally used by cognitive scientists; to the extent that causes confusion, I'm sorry. I'd rather use words in their strict conventional sense but I do not fully understand what that is. These thoughts are fuzzier than I'd like; if I was better at de-fuzzifying them I might be a pro instead of an amateur! Proposition: a symbol is a token with both denotative and model-theoretic semantics. The denotative semantacs are what makes a symbol refer to something or be about something. The model-theoretic semantics allow symbol processing operations to occur (such as reasoning). I believe this is a somewhat more restrictive use of the word symbol than is necessarily implied by Newell and Simon in the Physical Symbol System Hypothesis, but my aim is engineering rather than philosophy. I'm actually somewhat skeptical that human beings use symbols in this sense for much of our cognition. We appear to be a million times better at it than any other animal, and that is the special thing that makes us so great, but we still aren't very good at it. However, most of the things we want to build AGI *for* require us to greatly expand the symbol processing capabilities of mere humans. I think we're mostly interested in building artificial scientists and engineers rather than artificial musicians. Since computer programs, engineering drawings, and physics theories are explicitly symbolic constructs, we're more interested in effectively creating symbols than in the totality of the murky subsymbolic world supporting it. To what extent can we separate them? I wish I knew. In this view, subsymbolic simply refers to tokens that lack some of the features of symbols. For example, a representation of a pixel from a camera has clear denotational semantics but it is not elaborated as well as a better symbol would be (the light coming from direction A at time B is not as useful as the light reflecting off of Fred's pinky fingernail). Similarly, and more importantly, subsymbolic products of sensory systems lack useful model-theoretic semantics. The origin of symbols problem involves how those semantics arise -- and to me it's the most interesting piece of the AGI puzzle. Is anybody else interested in this kind of question, or am I simply inventing issues that are not meaningful and useful? -- agi | Archives | Modify Your Subscription -- No virus found in this incoming message. Checked by AVG. Version: 7.5.519 / Virus Database: 269.22.1/1349 - Release Date: 3/29/2008 5:02 PM --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Logical Satisfiability...Get used to it.
On Sun, Mar 30, 2008 at 5:09 PM, Mark Waser [EMAIL PROTECTED] wrote: 4) If you think some supernatural being placed an insight in your mind, you're probably better off NOT mentioning this when discussing the insight in a scientific forum, as it will just cause your idea to be taken way less seriously by a vast majority of scientific-minded people... Awesome answer! However, only *some* religions believe in supernatural beings and I, personally, have never seen any evidence supporting such a thing. I've got one in a jar in my basement ... but don't worry, I won't let him out till the time is right ;-) ... and so far, all his AI ideas have proved to be absolute bullshit, unfortunately ... though he's done a good job of helping me put hexes on my neighbors... Have you been having such experiences and been avoiding mentioning them because you're afraid for your reputation? Ben, I'm worried about you now.;-) --- 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 -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC Director of Research, SIAI [EMAIL PROTECTED] If men cease to believe that they will one day become gods then they will surely become worms. -- Henry Miller --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Symbols
On Mon, Mar 31, 2008 at 12:02 AM, Mike Tintner [EMAIL PROTECTED] wrote: We are all next to illiterate - and I mean, mind-blowingly ignorant - about how images function. What, for example, does an image of D.Z. or any person, do, that no amount of symbols - whether words, numbers, algebraic formulae, or logical propositions - could ever do? Why are images almost always more powerful than the corresponding symbols? Why do they communicate so much faster? Because of higher bandwidth? Mike, what is the point in crying ignorance, while providing no constructive comment? Argument from awe can lead to all kinds of wrong conclusions. -- Vladimir Nesov [EMAIL PROTECTED] --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Symbols
Why are images almost always more powerful than the corresponding symbols? Why do they communicate so much faster? Um . . . . dude . . . . it's just a bandwidth thing. Think about images vs. visual symbols vs. word descriptions vs. names. It's a spectrum from high-bandwidth information transfer to almost pure reference tags. If it's something you've never run across before, images are best -- high bandwidth but then you end up with high mental processing costs. For familiar items, word descriptions (or better yet, single word names) require little bandwidth and little in the way of subsequent processing costs. - Original Message - From: Mike Tintner To: agi@v2.listbox.com Sent: Sunday, March 30, 2008 4:02 PM Subject: Re: [agi] Symbols In this surrounding discussions, everyone seems deeply confused - it's nothing personal, so is our entire culture - about the difference between SYMBOLS 1. Derek Zahn curly hair big jaw intelligent eyes . etc. etc and IMAGES 2. http://robot-club.com/teamtoad/nerc/h2-derek-sunflower.JPG I suggest that everytime you want to think about this area, you all put symbols besides the corresponding images, and slowly it will start to become clear that each does things the other CAN'T do, period. We are all next to illiterate - and I mean, mind-blowingly ignorant - about how images function. What, for example, does an image of D.Z. or any person, do, that no amount of symbols - whether words, numbers, algebraic formulae, or logical propositions - could ever do? Why are images almost always more powerful than the corresponding symbols? Why do they communicate so much faster? Derek: Related obliquely to the discussion about pattern discovery algorithms What is a symbol? I am not sure that I am using the words in this post in exactly the same way they are normally used by cognitive scientists; to the extent that causes confusion, I'm sorry. I'd rather use words in their strict conventional sense but I do not fully understand what that is. These thoughts are fuzzier than I'd like; if I was better at de-fuzzifying them I might be a pro instead of an amateur! Proposition: a symbol is a token with both denotative and model-theoretic semantics. The denotative semantacs are what makes a symbol refer to something or be about something. The model-theoretic semantics allow symbol processing operations to occur (such as reasoning). I believe this is a somewhat more restrictive use of the word symbol than is necessarily implied by Newell and Simon in the Physical Symbol System Hypothesis, but my aim is engineering rather than philosophy. I'm actually somewhat skeptical that human beings use symbols in this sense for much of our cognition. We appear to be a million times better at it than any other animal, and that is the special thing that makes us so great, but we still aren't very good at it. However, most of the things we want to build AGI *for* require us to greatly expand the symbol processing capabilities of mere humans. I think we're mostly interested in building artificial scientists and engineers rather than artificial musicians. Since computer programs, engineering drawings, and physics theories are explicitly symbolic constructs, we're more interested in effectively creating symbols than in the totality of the murky subsymbolic world supporting it. To what extent can we separate them? I wish I knew. In this view, subsymbolic simply refers to tokens that lack some of the features of symbols. For example, a representation of a pixel from a camera has clear denotational semantics but it is not elaborated as well as a better symbol would be (the light coming from direction A at time B is not as useful as the light reflecting off of Fred's pinky fingernail). Similarly, and more importantly, subsymbolic products of sensory systems lack useful model-theoretic semantics. The origin of symbols problem involves how those semantics arise -- and to me it's the most interesting piece of the AGI puzzle. Is anybody else interested in this kind of question, or am I simply inventing issues that are not meaningful and useful? agi | Archives | Modify Your Subscription No virus found in this incoming message. Checked by AVG. Version: 7.5.519 / Virus Database: 269.22.1/1349 - Release Date: 3/29/2008 5:02 PM -- 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
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On 30/03/2008, Kingma, D.P. [EMAIL PROTECTED] wrote: Intelligence is not *only* about the modalities of the data you get, but modalities are certainly important. A deafblind person can still learn a lot about the world with taste, smell, and touch, but the senses one has access to defines the limits to the world model one can build. As long as you have one high bandwidth modality you should be able to add on technological gizmos to convert information to that modality, and thus be able to model the phenomenon from that part of the world. Humans manage to convert modalities E.g. http://www.engadget.com/2006/04/25/the-brain-port-neural-tongue-interface-of-the-future/ Using touch on the tongue. We don't do it very well, but that is mainly because we don't have to do it it very often. AIs that are designed to have new modalities added to them, using their major modality of their memory space+interrupts (or other computational modality), may be even more flexible than humans and able to adapt to to a new modality as quickly as a current computer is able to add a new device. If I put on ear muffs and a blind fold right now, I can still reason quite well using touch, since I have access to a world model build using e.g. vision. If you were deafblind and paralysed since your birth, would you have any possibility of spatial reasoning? No, maybe except for some extremely crude genetically coded heuristics. Sure if you don't get any spatial information you won't be able to model spatially. But getting the information is different from having a dedicated modality. My point was that audiovisual is not the only way to get spatial information. It may not even be the best way for what we happen to want to do. So not to get too hung up on any specific modality when discussing intelligence. Sure, you could argue that an intelligence purely based on text, disconnected from the physical world, could be intelligent, but it would have a very hard time reasoning about interaction of entities in the physicial world. It would be unable to understand humans in many aspects: I wouldn't call that generally intelligent. I'm not so much interested in this case, but what about the case where you have a robot with Sonar, Radar and other sensors. But not the normal 2 camera +2 microphone thing people imply when they say audiovisual. Will Pearson --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Logical Satisfiability...Get used to it.
Jim Bromer wrote: On the contrary, Vladimir is completely correct in requesting that the discussion go elsewhere: this has no relevance to the AGI list, and there are other places where it would be pertinent. Richard Loosemore If Ben doesn't want me to continue, I will stop posting to this group. Otherwise please try to understand what I said about the relevance of SAT to AGI and try to address the specific issues that I mentioned. On the other hand, if you don't want to waste your time in this kind of discussion then do just that: Stay out of it. Jim Bromer Since diplomacy did not work, I will come to the point: as far as i can see you have given no specific issues, only content-free speculation on topics of no relevance. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
Okay, with text, I mean natural language, in it's usual low-bandwidth form. That should clarify my statement. Any data can be represented with text of course, but that's not the point... The point that I was trying to make is that natural language is too low-bandwidth to provide sufficient data to learn a sufficient model about entities embedded in a complex physical world, such as humans. On Sun, Mar 30, 2008 at 10:50 PM, Mark Waser [EMAIL PROTECTED] wrote: From: Kingma, D.P. [EMAIL PROTECTED] Sure, you could argue that an intelligence purely based on text, disconnected from the physical world, could be intelligent, but it would have a very hard time reasoning about interaction of entities in the physicial world. It would be unable to understand humans in many aspects: I wouldn't call that generally intelligent. Given sufficient bandwidth, why would it have a hard time reasoning about interaction of entities? You could describe vision down to the pixel, hearing down to the pitch and decibel, touch down to the sensation, etc. and the system could internally convert it to exactly what a human feels. You could explain to it all the known theories of psychology and give it the personal interactions of billions of people. Sure, that's a huge amount of bandwidth, but it proves that your statement is inaccurate. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
On Sun, Mar 30, 2008 at 11:00 PM, Mark Waser [EMAIL PROTECTED] wrote: From: Kingma, D.P. [EMAIL PROTECTED] Vector graphics can indeed be communicated to an AGI by relatively low-bandwidth textual input. But, unfortunately, the physical world is not made of vector graphics, so reducing the physical world to vector graphics is quite lossy (and computationally expensive an sich). Huh? Intelligence is based upon lossyness and the ability to lose rarely relevant (probably incorrect) outlier information is frequently the key to making problems tractable (though it can also set you up for failure when you miss a phase transition by mistaking it for just an odd outlier :-) since it forms the basis of discovery by analogy. Matt Mahoney's failure to recognize this has him trapped in *exact* compression hell.;-) Agreed with that, exact compression is not the way to go if you ask me. But that doesn't mean any lossy method is OK. Converting a scene to vector graphics will lead you to throwing away much visual information early in the process: visual information (e.g. texture) that might be useful later in the process (for e.g. disambiguation). I'm not stating a vector description is not useful: I'm stating that information is thrown away that could have been used to construct an essential part of a world model that understands physical entities down to the level of e.g. textures. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
(Sorry for triple posting...) On Sun, Mar 30, 2008 at 11:34 PM, William Pearson [EMAIL PROTECTED] wrote: On 30/03/2008, Kingma, D.P. [EMAIL PROTECTED] wrote: Intelligence is not *only* about the modalities of the data you get, but modalities are certainly important. A deafblind person can still learn a lot about the world with taste, smell, and touch, but the senses one has access to defines the limits to the world model one can build. As long as you have one high bandwidth modality you should be able to add on technological gizmos to convert information to that modality, and thus be able to model the phenomenon from that part of the world. Humans manage to convert modalities E.g. http://www.engadget.com/2006/04/25/the-brain-port-neural-tongue-interface-of-the-future/ Using touch on the tongue. Nice article. Apparently even the brain's region for perception of taste is generally adaptable to new input. I'm not so much interested in this case, but what about the case where you have a robot with Sonar, Radar and other sensors. But not the normal 2 camera +2 microphone thing people imply when they say audiovisual. That's an interesting case indeed. AGIs equipped with sonar/radar/ladar instead of 'regular' vision should be perfectly able at certain forms of spatial reasoning, but still unable to understand humans at certain subjects. Still, if you don't need your agents to completely understand humans, audiovisual senses could go out of the window. It depends on your agent's goals, I guess. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Symbols
MW: MT: Why are images almost always more powerful than the corresponding symbols? Why do they communicate so much faster? Um . . . . dude . . . . it's just a bandwidth thing. Vlad:Because of higher bandwidth? Well, guys, if the only difference between an image and, say, a symbolic - verbal or mathematical or programming - description is bandwidth, perhaps you'll be able to explain how you see the Cafe Wall illusion from a symbolic description: http://www.at-bristol.org.uk/Optical/cafewall_main.htm A symbolic description of the above will only describe a set of parallel lines and rectangles - and there will be no illusion. (You could also try a similar exercise with some of the other illusions there). Or you might try a symbolic description of the Mona Lisa, and explain to me, how I will know from your description that she is smiling. You see if you take that image to pieces - as you must do in forming a symbolic description - there is no smile!: http://gotart.wordpress.com/2007/01/26/mona-lisa-lisa-gherardini/ And perhaps you can explain to me how you will see the final picture on any fully-formed jigsaw puzzle from just the pieces at the very beginning. Take a picture to pieces - and you don't get the picture any more. Like I said, we are extremely ignorant about how images work. (I'll explain more another time - but in the meantime, maybe Vlad can explain to us how and where the information that is lost in the above examples, is encoded.). --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
From: Kingma, D.P. [EMAIL PROTECTED] Okay, with text, I mean natural language, in it's usual low-bandwidth form. That should clarify my statement. Any data can be represented with text of course, but that's not the point... The point that I was trying to make is that natural language is too low-bandwidth to provide sufficient data to learn a sufficient model about entities embedded in a complex physical world, such as humans. Ah . . . . but natural language is *NOT* necessarily low-bandwidth. As humans experience it with pretty much just a single focus of attention and only one set of eyes and ears that can only operate so fast -- Yes, it is low bandwidth. But what about an intelligence with a hundred or more foci of attention and the ability to pull that many Wikipedia pages simultaneously at extremely high speed? --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
From: Kingma, D.P. [EMAIL PROTECTED] Agreed with that, exact compression is not the way to go if you ask me. But that doesn't mean any lossy method is OK. Converting a scene to vector graphics will lead you to throwing away much visual information early in the process: visual information (e.g. texture) that might be useful later in the process (for e.g. disambiguation). I'm not stating a vector description is not useful: I'm stating that information is thrown away that could have been used to construct an essential part of a world model that understands physical entities down to the level of e.g. textures. I would agree completely except that I would think that there is some way to include texture in the vector graphics in the same way in which color is included. --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Symbols
From: Mike Tintner Well, guys, if the only difference between an image and, say, a symbolic - verbal or mathematical or programming - description is bandwidth, perhaps you'll be able to explain how you see the Cafe Wall illusion from a symbolic description: Sure! The Cafe Wall illusion is a result of the interaction between an image composed of four parallel horizontal lines dividing the image into five strips with alternating black and white bars with the second and fourth strips slightly offset so as to trick the human eye into believing that the parallel lines aren't and the optimizing algorithms of the human eye. I could go into enough detail to explain exactly how and why the trick works -- the fact that the eye is attempting to interpret a two-dimensional image as a three-dimensional scene -- but I think that I've made my point adequately. A symbolic description of the above will only describe a set of parallel lines and rectangles - and there will be no illusion. Of course not, the illusion is a result of the image being implemented on the hardware of the human eye and brain. Unless you describe the human eye and brain, you don't get the illusion -- but you can do so easily as I did above and the illusion re-appears. Or you might try a symbolic description of the Mona Lisa, and explain to me, how I will know from your description that she is smiling. You see if you take that image to pieces - as you must do in forming a symbolic description - there is no smile!: Huh? All I need to do is include the smile in the description. You can both take the image to pieces *AND* describe the whole at the same time. And perhaps you can explain to me how you will see the final picture on any fully-formed jigsaw puzzle from just the pieces at the very beginning. Take a picture to pieces - and you don't get the picture any more. Wrong. Take a child's ten piece puzzle apart and re-arrange all the pieces. It's simple enough that your mind can hold all of it at once and get the picture. It's only when you take it to too many pieces . . . Like I said, we are extremely ignorant about how images work. (I'll explain more another time - but in the meantime, maybe Vlad can explain to us how and where the information that is lost in the above examples, is encoded.). I would be extremely careful about throwing the word we around and assuming that everyone is just like you. Why does everyone else has to be ignorant about a subject just because you don't understand it yet? Do you understand general relativity? If not, does that suddenly mean that I don't understand it any more? How about biochemistry, physical chemistry, thermodynamics, evolution, simulated annealing, etc.? --- 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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
I'm going to attack you by questions again :-) You're more than welcome to, sorry for being brisk. I did reply about RSS on the blog, but for some reason the post never made it through. I don't how RSS works, but you can subscribe via bloglines.com. What are 'range' and 'complexity'? Is there a specific architecture of 'levels'? Why should higher-level concepts be multidimensional? Levels are defined incrementally, a comparison adds a set of derivatives to the syntax (complexity) of the template pattern. After sufficient accumulation (range) the pattern is evaluated selectively transfered to a higher level, where these derivatives are also compared, forming yet another level of complexity. Complexity generally corresponds to the range of search ( resulting projection) because it adds cost, which must be justified by the benefit: accumulated match (one of the derivatives). The levels may differ in dimensionality (we do live in a 4D world)b or modality integration, but this doesn't have to be designed-in, the differences can be discovered by the system. What is the dynamics of system's operation in time? Is inference feed-forward and 'instantaneous', measuring by external clock? Can capture time series? Temporal, as well as spatial, range of search ( duration is storage) increases with the level of generality, the feedback (projection) delay increases too. By 'what prediction is for?' I mean connection to action. How does prediction of inputs or features of inputs translate into action? If this prediction activity doesn't lead to any result, it may as well be absent. The intellectual part of action is planning, which technically is a self-prediction. Prediction is a pattern with adjusted focus: coordinates resolution, sent down the hierarchy the changes act as a motor feedback. Using the feedback the system will focus on areas of the environment with the greatest predictive potential. To do so, it will eventualy learn to use tools. Boris, http://scalable-intelligence.blogspot.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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
Re: [agi] Intelligence: a pattern discovery algorithm of scalable complexity.
It seems like a reasonable and not uncommon idea that an AI could be built as a mostly-hierarchical autoassiciative memory. As you point out, it's not so different from Hawkins's ideas. Neighboring pixels will correlate in space and time; features such as edges should become principle components given enough data, and so on. There is a bunch of such work on self-organizing the early visual system like this. That overall concept doesn't get you very far though; the trick is to make it work past the first few rather obvious feature extraction stages of sensory data, and to account for things like episodic memory, language use, goal-directed behavior, and all other cognitive activity that is not just statistical categorization. I sympathize with your approach and wish you luck. If you think you have something that produce more than Hawkins has with his HTM, please explain it with enough precision that we can understand the details. Good questions. I agree with you on Hawkins HTM, but his main problem is conceptual. He seems to be profoundly confused as to what the hierarchy should select for: generality or novelty. He nominates both, apparently not realizing that they're mutually exclusive. This creates a difficulty in defining a quantitative criterion for selection, which is a key for my approach. This internal inconsistency leads to haphazard hacking in the HTM. For example, he starts by comparing 2D frames in a binary fashion, which pretty perverse for an incremental approach. I start from the begining, by comparing pixels: the limit of resolution, I quantify the degree of match right there, as a distinct variable. I also record compare explicit coordinates derivatives, while he simply junks all that information. His approach doesn't scale because it's not consistent incremental enough. I disagree that we need to specifically code episodic memory, language, action, - to me these are emergent properties (damn, I hate that word:)). Boris. http://scalable-intelligence.blogspot.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=98558129-0bdb63 Powered by Listbox: http://www.listbox.com