Re: [agi] Computing's coming Theory of Everything
Ben, On 7/22/08, Benjamin Johnston [EMAIL PROTECTED] wrote: /Restating (not copying) my original posting, the challenge of effective unstructured learning is to utilize every clue and NOT just go with static clusters, etc. This includes temporal as well as positional clues, information content, etc. PCA does some but certainly not all of this, but considering that we were talking about clustering here just a couple of weeks ago, ratcheting up to PCA seems to be at least a step out of the basement./ You should actually try PCA on real data before getting too excited about it. Why, as I have already conceded that virgin PCA isn't a solution? I would expect it to fail in expected ways until it is repaired/recreated to address known shortcomings, e.g. that it works on linear luminosity rather than logarithmic luminosity. In short, I am not ready for data yet - until I am first tentatively happy with the math. Clustering and dimension reduction are related, but they are different and equally valid techniques designed for different purposes. Perhaps you missed the discussion a couple of weeks ago, where I listed some of the UNstated assumptions in clustering that are typically NOT met in the real world, e.g.: 1. It presumes that cluster exist, whether or not they actually do. 2. It is unable to deal with data that has wildly different importance. 3. Corollary to 2 above, any random input completely trashes it. 4. It is designed for neurons/quantities where intermediate values have special significance, rather than for fuzzy indicators that are just midway between TRUE and FALSE. This might be interesting for stock market analysis, but has no (that I know of) parallel in our own neurons. It is absurd to say that one is ratcheting up from the other. I agree that they do VERY different jobs, but I assert that the one that clustering does has nothing to do with NN, AGI, or most of the rest of the real world. I short, I am listening and carefully considering all arguments here, but in this case, I am still standing behind my ratcheting up statement, at least until I hear a better challenge to it. Steve Richfield --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
Re: [agi] TOE -- US PATENT ISSUED for the TEN ETHICAL LAWS OF ROBOTICS
On Wed, Jul 23, 2008 at 1:13 AM, Mike Archbold wrote: It seems to me like to be real AGI you have skipped over the parts of Aristotle more applicable to AGI, like his metaphysics and logic. For example in the metaphysics he talks about beginning and end, causes, continuous/discrete, and this type of thing. At first glance it looks like your invention starts with ethics; why not build atop a metaphysics base? I'm not going to pass a judgement on your work but it seems like it's not going over well here with the crowd that has dealt with patent law. From my perspective I guess I don't like the idea of patenting some automation of Aristotle unless it was in a kind of production-ready state (ie., beyond mere concept stage). His invention is ethics, because that's what his field of work is. See his list of books here: http://www.allbookstores.com/author/John_E_Lamuth.html * A Diagnostic Classification of the Emotions : A Three-digit Coding System for Affective Language by Jay D. Edwards (Illustrator), John E. Lamuth April 2005, Paperback List Price: $34.95 * Character Values : Promoting a Virtuous Lifestyle cover Character Values : Promoting a Virtuous Lifestyle by Jay D. Edwards (Illustrator), John E. Lamuth (Editor) April 2005, Paperback List Price: $28.95 * Communication Breakdown : Decoding The Riddle Of Mental Illness by Jay D. Edwards (Introduction by), John E. Lamuth (Editor) June 2004, Paperback List Price: $28.95 * A Revolution in Family Values : Tradition Vs. Technology by Jay D. Edwards (Illustrator), John E. Lamuth April 2002, Paperback List Price: $19.95 * A Revolution in Family Values : Spirituality for a New Millennium by John E. Lamuth March 2001, Hardcover List Price: $24.95 * The Ultimate Guide to Family Values : A Grand Unified Theory of Ethics and Morality by John E. Lamuth September 1999, Hardcover List Price: $19.95 and his author profile here: http://www.angelfire.com/rnb/fairhaven/Contact_Fairhaven_Books.html Biography John E. LaMuth is a 52 year-old counselor and author, native to the Southern California area. Credentials include a Bachelor of Science Degree in Biological Sciences from University of California, Irvine: followed by a Master of Science Degree in Counseling from California State University, Fullerton; with an emphasis in Marriage, Family, and Child Counseling. John is currently engaged in private practice in Divorce and Family Mediation Counseling in the San Bernardino County area - JLM Mediation Service - Lucerne Valley, CA 92356 USA. John also serves as an Adjunct Faculty Member at Victor Valley College, Victorville, CA. BillK --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
What does it do? useful in AGI? Re: [agi] US PATENT ISSUED for the TEN ETHICAL LAWS OF ROBOTICS
2008/7/22 Mike Archbold [EMAIL PROTECTED]: It looks to me to be borrowed from Aristotle's ethics. Back in my college days, I was trying to explain my project and the professor kept interrupting me to ask: What does it do? Tell me what it does. I don't understand what your system does. What he wanted was input-function-output. He didn't care about my fancy data structure or architecture goals, he just wanted to know what it DID. I have come across this a lot. And while it is a very useful heuristic for sniffing out bad ideas that don't do anything I also think it is harmful to certain other endeavours. Imagine this hypothetical conversation between Turing and someone else (please ignore all historical inaccuracies). Sceptic: Hey Turing, how is it going. Hmm, what are you working on at the moment? Turing: A general purpose computing machine. Sceptic: I'm not really sure what you mean by computing. Can you give me an example of something it does? Turing: Well you can use it calculate differential equations Sceptic: So it is a calculator, we already have machines that can do that. Turing: Well it can also be a chess player. Sceptic: Wait, what? How can something be a chess player and a calculator? Turing: Well it isn't both at the same time, but you can reconfigure it to do one then the other. Sceptic: If you can reconfigure something, that means it doesn't intrinsically do one or the other. So what does the machine do itself? Turing: Well, err, nothing. I think the quest for general intelligence (if we are to keep any meaning in the word general), will have be hindered by trying to pin down what candidate systems do, in the same way general computing would be. I think the requisite question in AGI to fill the gap formed by not allowing this question, is, How does it change? Will --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
Re: What does it do? useful in AGI? Re: [agi] US PATENT ISSUED for the TEN ETHICAL LAWS OF ROBOTICS
Will: Mike Archbold [EMAIL PROTECTED]: It looks to me to be borrowed from Aristotle's ethics. Back in my college days, I was trying to explain my project and the professor kept interrupting me to ask: What does it do? Tell me what it does. I don't understand what your system does. What he wanted was input-function-output. He didn't care about my fancy data structure or architecture goals, he just wanted to know what it DID. I have come across this a lot. And while it is a very useful heuristic for sniffing out bad ideas that don't do anything I also think it is harmful to certain other endeavours. Imagine this hypothetical conversation between Turing and someone else (please ignore all historical inaccuracies). Sceptic: Hey Turing, how is it going. Hmm, what are you working on at the moment? Turing: A general purpose computing machine. Sceptic: I'm not really sure what you mean by computing. Can you give me an example of something it does? Turing: Well you can use it calculate differential equations Sceptic: So it is a calculator, we already have machines that can do that. Turing: Well it can also be a chess player. Sceptic: Wait, what? How can something be a chess player and a calculator? Turing: Well it isn't both at the same time, but you can reconfigure it to do one then the other. Sceptic: If you can reconfigure something, that means it doesn't intrinsically do one or the other. So what does the machine do itself? Turing: Well, err, nothing. I think the quest for general intelligence (if we are to keep any meaning in the word general), will have be hindered by trying to pin down what candidate systems do, in the same way general computing would be. I think the requisite question in AGI to fill the gap formed by not allowing this question, is, How does it change? Will, You're actually almost answering the [correct and proper] question: what does it do? But you basically end up as with that sub problem, evading it. What a General Intelligence does is basically simple. It generalizes creatively - it connects different domains - it learns skills and ideas in one domain, and then uses them to learn skills and ideas in other domains. It learns how to play checkers, and then chess, and then war games, and then geometry. A computer is in principle a general intelligence - a machine that can do all these things - like the brain. But in practice it has to be programmed separately for each specialised skill and can only learn within a specialised domain. It has so far been unable to be truly general purpose - and think and learn across domains.. The core problem - what a general intelligence must DO therefore - is to generalize creatively - to connect different domains - chalk and cheese, storms and teacups, chess pieces and horses and tanks . [I presume that is what you are getting at with: How does it change?] That's your sub problem - the sub can't move. All the standard domain checks for non-movement - battery failure, loose wire etc. - show nothing. The sub, if it's an AGI, must find the altogether new kind of reason in a new domain, that is preventing it moving. (Perhaps it was some mistyped but reasonable, or otherwise ambiguous, command. Perhaps it's some peculiar kind of external suction..). What makes creative generalization so difficult (and 'creative') is that no domain follows rationally (i.e. logico-mathematically or strictly linguistically) from another. You cannot deduce chalk from cheese, or chess from checkers. And you cannot in fact deduce almost any branch of rational systems themselves from any other - Riemannian geometry, for example, does not follow logically or geometrically or statistically or via Bayes from Euclidean, any more than topology or fractals. The FIRST thing AGI'ers should be discussing is how they propose to solve the what-does-it-do problem of creative generalization - or, at any rate, what are their thoughts and ideas so far. You think they're being wise by universally avoiding this problem - *the* problem. I think they're just chicken. --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
Re: [agi] Computing's coming Theory of Everything
Replying in reverse order Story: I once viewed being able to invert the Airy Disk transform (what makes a blur from a point of light in a microscope or telescope) as an EXTREMELY valuable thing to do to greatly increase their power, so I set about finding a transform function. Then, I wrote a program to test it, first making an Airy Disk blur and then transforming it back to the original point. It sorta worked, but there was lots of computational noise in the result, so I switched to double precision, whereupon it failed to work at all. After LOTS more work, I finally figured out that the Airy Disk function was a perfect spacial low pass filter, so that two points that were too close to be resolved as separate points made EXACTLY the same perfectly circular pattern as did a single point of the same total brightness. In single precision, I was inverting the computational noise, and doing a pretty good job of it. However, for about a month, I thought that I had changed the world. Neat. I have a professor who is doing some stuff with a similar transform, but with a circle (/sphere) rather than a disc (/ball). I thought it was information-preserving? Wouldn't two dots make something of an oval? Yet, if we take the multilevel approach, the 2nd level will be trying to take advantage of dependencies in those variables... Probably not linear dependencies because these should have been wrung out in the previous level. Hopefully, the next layer would look at time sequencing, various combinations, etc. Well, since I am not thinking of the algorithm as-is, I assumed that it would be finding more than just linear dependencies. And if each layer was linear, then wouldn't it still fail for the same reason? (Because it would be looking for linear dependencies in variables that are linearly independent, just as I had argued that it would be looking for nonlinear dependence in nonlinearly dependent variables?) In other words, the successive layers would need to be actually different from eachother (perhaps adding in time-information as you suggested) to do anything useful. So again what we are looking for is a useful division of the task into subtasks. Hmm... the algorithm for a single level would need to subtract the information encoded in the new variable each time, so that the next iteration is working with only the still-unexplained properties of the data. (Taking another puff) Unfortunately, PCA methods produce amplitude information but not phase information. This is a little like indefinite integration, where you know what is there, but not enough to recreate it. Further, maximum information channels would seem to be naturally orthogonal, so subtracting, even if it were possible, is probably unnecessary. Yep, this is my point, I was just saying it a different way. Since maximum information channels should be orthogonal, the algorithm needs to do *something* like subtracting. (For example, if we are compressing a bunch of points that nearly fall on a line, we should first extract a variable telling us where on the line. We should then remove that dimension from the data, so that we've got just a patch of fuzz. Any significant variables in the fuzz will be independent of line-location, because if they were not we would have caught them on the first extraction. So then we extract the remaining variables from this fuzz rather than the original data.) It is not even capable of representing context-free patterns (for example, pictures of fractals). Can people do this? Yes, yes absolutely. Not in the visual cortex maybe, at least not in the lower regions, but people can see the pattern at some level. I can prove this by drawing the sierpinski triangle for you. The issue is which invariant transforms are supported by the system. For example, the unaltered algorithm might not support location-invariance in a picture, so people might add eye-movements to the algorithm, making it slide around taking many sub-picture samples. Next, people might want size-invariance, then rotation-invariance. These three together might seem to cover everything, but they do not. First, we've thrown out possibly useful information along the way; people can ignore size sometimes, but it is sometimes important, and even more so for rotation and location. Second, more complicated types of invariance can be learned; there is really an infinite variety. This is why relational methods are necessary: they can see things from the beginning as both in a particular location, and as being in a relationship to surroundings that is location-independent. The same holds for size if we add the proper formulas. (Hmm... I admit that current relational methods can't so easily account for rotation invariance... it would be possible but very expensive...) Such systems might produce some good results, but the formalism cannot represent complex relational ideas. All you need is a model, any model, capable of
Re: What does it do? useful in AGI? Re: [agi] US PATENT ISSUED for the TEN ETHICAL LAWS OF ROBOTICS
2008/7/22 Mike Archbold [EMAIL PROTECTED]: It looks to me to be borrowed from Aristotle's ethics. Back in my college days, I was trying to explain my project and the professor kept interrupting me to ask: What does it do? Tell me what it does. I don't understand what your system does. What he wanted was input-function-output. He didn't care about my fancy data structure or architecture goals, he just wanted to know what it DID. I have come across this a lot. And while it is a very useful heuristic for sniffing out bad ideas that don't do anything I also think it is harmful to certain other endeavours. Imagine this hypothetical conversation between Turing and someone else (please ignore all historical inaccuracies). Sceptic: Hey Turing, how is it going. Hmm, what are you working on at the moment? Turing: A general purpose computing machine. Sceptic: I'm not really sure what you mean by computing. Can you give me an example of something it does? Turing: Well you can use it calculate differential equations Sceptic: So it is a calculator, we already have machines that can do that. Turing: Well it can also be a chess player. Sceptic: Wait, what? How can something be a chess player and a calculator? Turing: Well it isn't both at the same time, but you can reconfigure it to do one then the other. Sceptic: If you can reconfigure something, that means it doesn't intrinsically do one or the other. So what does the machine do itself? Turing: Well, err, nothing. I think the quest for general intelligence (if we are to keep any meaning in the word general), will have be hindered by trying to pin down what candidate systems do, in the same way general computing would be. I think the requisite question in AGI to fill the gap formed by not allowing this question, is, How does it change? Will Will, I see what you mean that trying to pin down input-function-output too early in the AGI game would be a hinderance, since by the general nature it kind of assumes these in an ideal way, but it seems to me that if the poster is at the patent stage he should have this specified, otherwise it sounds like patenting an idea that needs a lot more work to me. Mike Archbold --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
Re: [agi] Computing's coming Theory of Everything
This is getting long in embedded-reply format, but oh well On Wed, Jul 23, 2008 at 12:24 PM, Steve Richfield [EMAIL PROTECTED] wrote: Abram, On 7/23/08, Abram Demski [EMAIL PROTECTED] wrote: Replying in reverse order Story: I once viewed being able to invert the Airy Disk transform (what makes a blur from a point of light in a microscope or telescope) as an EXTREMELY valuable thing to do to greatly increase their power, so I set about finding a transform function. Then, I wrote a program to test it, first making an Airy Disk blur and then transforming it back to the original point. It sorta worked, but there was lots of computational noise in the result, so I switched to double precision, whereupon it failed to work at all. After LOTS more work, I finally figured out that the Airy Disk function was a perfect spacial low pass filter, so that two points that were too close to be resolved as separate points made EXACTLY the same perfectly circular pattern as did a single point of the same total brightness. In single precision, I was inverting the computational noise, and doing a pretty good job of it. However, for about a month, I thought that I had changed the world. Neat. I have a professor who is doing some stuff with a similar transform, but with a circle (/sphere) rather than a disc (/ball). The Airy Disk is the name of the transform. In fact, it is the central maxima surrounded by faint rings of rapidly diminishing brightness typical of what a star produces. Note that you can cut the radius of the first minima to ~2/3 by stopping out all but a peripheral ring on the lens, which significantly increases the resolution - a well known trick among experienced astronomers, but completely missed by the Hubble team! Just stopping out the middle of their mirror would make it equivalent to half again its present diameter, though its light-gathering ability would be greatly reduced. Of course, this could easily be switched in and out just as they are already switching other optical systems in and out. Can you tell me a little more about what your professor is doing? He came up with a fast way of doing the transform, which allows him to quickly identify points that have spherical shapes around them (of a given radius). He does the transform for a few different radius-values, so he detects spheres of different sizes, and then he uses the resulting information to help classify points. An example application would be picking out important structures in X-ray images or CAT scans: train the system on points that doctors pick out, then use it to pick out points in a new image. Spheres may not be the best feature to use, but they work, and since his algorithm allows them to be calculated extremely quickly, it becomes a good choice. Imagine a layer where the inputs represent probabilities of situations in the real world, and the present layer must recognize combinations that are important. This would seem to require ANDing (multiplication) rather than simple linear addition. However, if we first take the logarithms of the incoming probabilities, simple addition produces ANDed probabilities. OK, so lets make this a little more complicated by specifying that some of those inputs are correlated, and hence should receive reduced weighting. We can compute the weighted geometric mean of a group of inputs by simply multiplying each by its weight (synaptic efficacy), and adding the results together. Of course, the sum of these efficacies would be 1.0. If I understand, what you are saying is that linear dependencies might be squeezed out, but some nonlinear dependencies might become linear for various reasons, including purposefully applying nonlinear functions (log, sigmoid...) to the resulting variables. It seems there are some standard ways of introducing nonlinearity: http://en.wikipedia.org/wiki/Kernel_principal_component_analysis On a related note, the standard classifier my professor applied to the sphere-data worked by taking the data to a higher-dimensional space that made nonlinear dependencies linear. It then found a plane that cut between yes points and no points. Agreed. Nonlinearities, time information, scope, memory, etc. BTW, have you looked at asynchronous logic - where they have MEMORY elements sprinkled in with the logic?! Why? Because they look for some indication of a subsequent event, e.g. inputs going to FALSE, before re-evaluating the inputs. This is akin to pipelining - which OF COURSE you would expect in highly parallel systems like us. Asynchronous logic has many of the same design issues as our own brains, and some REALLY counter-intuitive techniques have been developed, like 2-wire logic, where TRUE and FALSE are transmitted on two different wires to eliminate the need for synchronicity. There are several such eye-popping methods that could well be working within us. This sounds exactly like the invocation
Re: [agi] TOE -- US PATENT ISSUED for the TEN ETHICAL LAWS OF ROBOTICS
John LaMuth wrote: Yes, this is extensively based on Aristotle's Golden Mean The input-output flowchart is shown appended below... The details are described at http://www.angelfire.com/rnb/fairhaven/specs.html (the last half) This is the real deal the ultimate TOE of friendly AI communication So it is a theory of everything, now? Yesterday it was just a patent. In fact, it is content-free nonsense. I could give you a box-and-arrow diagram describing the entire universe at the same superficial level of detail ... would that mean I was God? And would the USPTO then grant me a patent for System and Method for Managing All of Creation? You do not show the slightest sign of understanding how to build an AGI that behaves in a friendly way, or indeed in any other way. There is no mechanism in your patent. All you have done is write some Articles of Good Behavior that the AGI is supposed to keep on the back of its bedroom door and commit to memory while it is growing up. Richard Loosemore *** John replies Richard Yes - I consider the content of my patents as a TOE (restricted to the domain of emotionally-charged language) as diagrammed at: http://www.angelfire.com/rnb/fairhaven/Masterdiagram.html Virtually every category of affective language (from Rogets Thesaurus) is represented To the great advantage of all-inclusiveness... JLM www.charactervalues.org --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
Re: [agi] TOE -- US PATENT ISSUED for the TEN ETHICAL LAWS OF ROBOTICS
Mike Yes, this is extensively based on Aristotle's Golden Mean The input-output flowchart is shown appended below... The details are described at http://www.angelfire.com/rnb/fairhaven/specs.html (the last half) This is the real deal the ultimate TOE of friendly AI communication John, It seems to me like to be real AGI you have skipped over the parts of Aristotle more applicable to AGI, like his metaphysics and logic. For example in the metaphysics he talks about beginning and end, causes, continuous/discrete, and this type of thing. At first glance it looks like your invention starts with ethics; why not build atop a metaphysics base? I'm not going to pass a judgement on your work but it seems like it's not going over well here with the crowd that has dealt with patent law. From my perspective I guess I don't like the idea of patenting some automation of Aristotle unless it was in a kind of production-ready state (ie., beyond mere concept stage). MIke http://www.listbox.com John replies Aristotle's Metaphysics is 2500 years out of date (unlike his ethics) He thought the brain operated as a Radiator !! I do incorporate his principles of Inductive Inference within the title of my patent But philosophy is a shaky foundation, so I rather substitute the Science of Behaviorism as my primary foundation as described at http://www.angelfire.com/rnb/fairhaven/behaviorism.html Through these instinctual principles of operant conditioning, it even proves possible to extend and establish links to the physical realm (the neural organization of the brain) see http://www.forebrain.org Hope this helps John L --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
Re: [agi] Computing's coming Theory of Everything
The Wikipedia article on PCA cites papers that show K-means clustering and PCA to be in a certain sense equivalent-- from what I read so far, the idea is that clustering is simply extracting discrete versions of the continuous variables that PCA extracts. http://en.wikipedia.org/wiki/Principal_component_analysis#Relation_to_K-means_clustering Does that settle it? On Wed, Jul 23, 2008 at 2:21 AM, Steve Richfield [EMAIL PROTECTED] wrote: Ben, On 7/22/08, Benjamin Johnston [EMAIL PROTECTED] wrote: /Restating (not copying) my original posting, the challenge of effective unstructured learning is to utilize every clue and NOT just go with static clusters, etc. This includes temporal as well as positional clues, information content, etc. PCA does some but certainly not all of this, but considering that we were talking about clustering here just a couple of weeks ago, ratcheting up to PCA seems to be at least a step out of the basement./ You should actually try PCA on real data before getting too excited about it. Why, as I have already conceded that virgin PCA isn't a solution? I would expect it to fail in expected ways until it is repaired/recreated to address known shortcomings, e.g. that it works on linear luminosity rather than logarithmic luminosity. In short, I am not ready for data yet - until I am first tentatively happy with the math. Clustering and dimension reduction are related, but they are different and equally valid techniques designed for different purposes. Perhaps you missed the discussion a couple of weeks ago, where I listed some of the UNstated assumptions in clustering that are typically NOT met in the real world, e.g.: 1. It presumes that cluster exist, whether or not they actually do. 2. It is unable to deal with data that has wildly different importance. 3. Corollary to 2 above, any random input completely trashes it. 4. It is designed for neurons/quantities where intermediate values have special significance, rather than for fuzzy indicators that are just midway between TRUE and FALSE. This might be interesting for stock market analysis, but has no (that I know of) parallel in our own neurons. It is absurd to say that one is ratcheting up from the other. I agree that they do VERY different jobs, but I assert that the one that clustering does has nothing to do with NN, AGI, or most of the rest of the real world. I short, I am listening and carefully considering all arguments here, but in this case, I am still standing behind my ratcheting up statement, at least until I hear a better challenge to it. Steve Richfield agi | Archives | Modify Your Subscription --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com