Re: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE BINDING PROBLEM"?
Ed Porter wrote: ## RICHARD LOOSEMORE LAST EMAIL #>> My preliminary response to your suggestion that other Shastri papers do describe ways to make binding happen correctly is as follows: anyone can suggest ways that *might* cause correct binding to occur - anyone can wave their hands, write a program, and then say "backward chaining" - but there is a world of difference between suggesting mechanisms that *might* do it, and showing that those mechanisms actually do cause correct bindings to be established in practice. What happens in practice is that the proposed mechanisms work for (a) toy cases for which they were specifically designed to work, and/or (b) a limited number of the more difficult cases, and that what we also find is that they (c) tend to screw up in all kinds of interesting ways when the going gets tough. At the end of the day, these proposals don't solve the binding problem, they just work some of the time, with no clear reason given why they should work all of the time. They are, in a word, hacks. Understanding that they only have the status of hacks is a very important sign of maturity as an AI researcher. There is a very deep truth buried in that fact. #ED PORTERS CURRENT RESPONSE > Forward and backward chaining are not hacks. They has been two of the most commonly and often successfully techniques in AI search for at least 30 years. They are not some sort of wave of the hand. They are much more concretely grounded in successful AI experience than many of your much more ethereal, and very arguably hand waving, statements about having many of the difficult problems in AI are to be cured by some as yet unclearly defined emergence from complexity. Oh dear: yet again I have to turn a blind eye to the ad hominem insults. You are using terms like "forward and backward chaining" without understanding exactly what they mean, and what role they play in their context, and what their limitations are. These mechanisms work great, but only in carefully proscribed settings! It is precisely my point that when it comes to establishing a correct binding between two referents, it means absolutely nothing to say that you are going to invoke mechanisms such as backward chaining. Let me illustrate with an example. Binding is finding out if two referents are the same thing, or if they are closely linked by some intermediary. Here is an example sentence that needs to have its referents untangled: "At one time, one of them might have said to one of his own that one and one and one is one, but one does not know whether, on the one hand, this is one of those platitudes that those folks are so fond of, or if, on the other, the One is literally meant to be more than one." A backward chaining search to resolve the referents of "one" in this sentence would very likely not return a result before it would have to be cut off due to time constraints but if that happens, then the result of using backward chaining is that the sentence cannot be understood by the system. Which means that backward chaining is not being used to proceed to the solution of the binding problem in this case, it is being used as a mechanism that might, if you are lucky, work. A mechanism that might, if you are lucky, work is a hack a heuristic if you want to use polite language. It is handwaving to say that backward chaining can resolve the binding problem, because when faced with difficult cases like this one, the mechanism goes belly up. Some thing that works some of the time, but gives garbage in other cases, and with no clear distinction between the cases, is a hack. Learning patterns of temporal activation and using them to guide forward and backward chaining are not hacks either. It his been used for years also. The operation of the binding in the type of Shruiti-like system I have described has been demonstrated in systems with over a hundred thousand nodes, and worked well. Expanding a Shruite-like or Novamente-like system to a much large size would call for more sophisticated inference control. This is a challenge that has not been properly experimented with, but for which there are many promising paths. Nevertheless, the type of inference systems I have suggested are much more concrete, easy to understand, and have more support from success in similar system that have been built than your unexplained notion that binding --- even when it can't be handled implicitly but the use of multiple models, as described in the Poggio paper about which I started this thread --- can be handled by some unexplained constraint and emergence from complexity. Sigh. Richard Loosemore ## RICHARD LOOSEMORE EMAIL BEFORE LAST #>> Or rather, it is not clear how you can *guarantee* the finding of a solution. ED PORTERS LAST EMAIL >> [in such massive searching, humans often miss the most appr
Re: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE BINDING PROBLEM"?
Ed Porter wrote: ## RICHARD LOOSEMORE WROTE #>> Now I must repeat what I said before about some (perhaps many?) claimed solutions to the binding problem: these claimed solutions often establish the *mechanism* by which a connection could be established IF THE TWO ITEMS WANT TO TALK TO EACH OTHER. In other words, what these people (e.g. Shastri and Ajjannagadde) do is propose a two step solution: (1) the two instances magically decide that they need to get hooked up, and (2) then, some mechanism must allow these two to make contact and set up a line to one another. Think of it this way: (1) You decide that at this moment that you need to call Britney Spears, and (2) You need some mechanism whereby you can actually establish a phone connection that goes from your place to Britney's place. The crazy part of this "solution" to the binding problem is that people often make the quiet and invisible assumption that (1) is dealt with (the two items KNOW that they need to talk), and then they go on to work out a fabulously powerful way (e.g. using neural synchronisation) to get part (2) to happen. The reason this is crazy is that the first part IS the binding problem, not the second part! The second phase (the practical aspects of making the phone call get through) is just boring machinery. By the time the two parties have decided that they need to hook up, the show is already over... the binding problem has been solved. But if you look at papers describing these so-called solutions to the binding problem you will find that the first part is never talked about. At least, that was true of the S & A paper, and at least some of the papers that followed it, so I gave up following that thread in utter disgust. MY REPLY >> [Your description of Shastri's work is inaccurate --- at least from his papers I have read, which include among others, " Advances in Shruti -- A neurally motivated model of relational knowledge representation and rapid inference using temporal synchrony" Applied Intelligence, 11: 79-108, 1999 ( http://www.icsi.berkeley.edu/~shastri/psfiles/shruti_adv_98.ps ); and "Massively parallel knowledge representation and reasoning: Taking a cue from the Brain", by Shastri and Mani. It is obvious from reading Shasti that his notion of what should talk to what (i.e., i.e., be searched by spreading activation) is determined by a form of forward and/or backward chaining, which can automatically be learned from temporal associations between pattern activations, and the bindings involved can be learned by the occurrences of the same one or more pattern element instances as a part or as an attribute in one or more of those temporally related patterns. Shruiti's representational scheme has limitations that make it ill suited for use as the general representation scheme in an AGI (problems which I think can be fixed with a more generalized architecture), but the particular problem you are accusing his system of here --- i.e., that it provides no guidance as to what should be searched for when to answer a given query --- is not in fact a problem (other than the issue of possible exponential explosion of the search tree, which is discussed in my answers below)] > ## RICHARD LOOSEMORE WROTE #>> It is very important to break through this confusion and find out exactly why the two relevant entities would decide to talk to each other. Solving any other aspect of the problem is not of any value. Now, going back to your question about how it would happen: if you look for a determinstic solution to the problem, I am not sure you can come up with a general answer. Whereas there is a nice, obvious solution to the question "Is Socrates mortal?" given the facts "Socrates is a man" and "All men are mortal", it is not at all clear how to do more complex forms of binding without simply doing massive searches. MY REPLY >> [You often do have to do massive searches -- it is precisely because the human brains can do such massive searches (averaging roughly 3 to 300 trillion/second in the cortex alone) that lets us so often come up with the appropriate memory or reason at the appropriate time. But the massive searches in a large Shruiti-like or Novamente-like system are not totally-blind searches --- instead they are often massive search guided by forward and/or backward chaining -- by previously learned and/or recently activated probabilities and importances --- by relative scores of various search threads or pattern activations --- by inference patterns that may have proven successful in previous similar searches --- by similar episodic memories --- and --- by interaction with the current context as represented by the other current activations] Well, I will hold my fire until I get to your comments below, but I must insist that what I said was accurate: his first major paper on this topic was a sleight of ha
RE: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE BINDING PROBLEM"?
>>=FROM ED'S ORIGINAL POST=> it is precisely because the human brains can do such massive searches (averaging roughly 3 to 300 trillion/second in the cortex alone) that lets us so often come up with the appropriate memory or reason at the appropriate time. >== MIKE'S RESPONSE=> Do you think the brain works by massive search in dealing with problems? Chess - a top master may consider consciously v. roughly 150 moves in a minute. Do you think his unconscious brain is considering a lot more? How many, roughly in what time? ===ED PORTER => Big Blue showed the power of massive search in Chess. In the human brain, we are not capable of massive exact searches, particularly ones involving complex rapid accurate sequential processing, but we are capable of massive less accurate parallel search. If a human considers 150 moves a minute, that is a period with roughly 2000 gama waves, during each of which there can be a massive separately encoded spreading activation. And many forms of spreading activation may be independent, to various decrease, from such gama waves. I think the consideration of each move probably involve massive searches in memory for patterns related to that move in the current context, and multiple massive searches involving multiple levels of implication from such patterns. If you think about how implication spread, you realize that is easy to have millions or billions of potential activation in just 3 or 4 inferencing steps, without some sort of filtering process. You also have to realize that your consciousness is only aware of that small portion of the activations in your brain which win competitive process for the attention necessary to make your consciousness aware of them. >== MIKE'S RESPONSE=> "Name 10 famous Frenchmen". How many Frenchmen roughly do you think your brain is checking out and how fast as you deal with that? ===ED PORTER => This task might not require as broad a search as some, because it only requires a relatively few indices and the number of object indexed by some of those indices is rather small, but I would still assume it involves millions of activations. I think the brain's indexing is often much less simple and clear than that used in most simple databases programs. You may well not have a clearly defined index (is a French person), and even if you do, many people whom you know of who are French may not be clearly labeled under it. Instead you probably have experiences of people in many different contexts which might indicate they are French. Also I think our brains often can most quickly recover things that are indexed by multiple indices. If you recently spent a year working in France for a French company with many French co-workers, you would probably be able to rattle off names of Frenchmen much more quickly because you could just think of all the people you have spent hundreds of hours with within the offices of your French employer, and there you would have many indices coding for the desired quality, making the appropriate answer pop out above the noise much more boldly. >== MIKE'S RESPONSE=> Do you dispute Hawkins' "one hundred step rule"? He argues that the brain can recognize a face in 1/2 sec. - which can involve information traversing a chain of at most 100 neurons in that time. And "the largest conceivable parallel computer can't do anything useful in one hundred steps, no matter how large or how fast." [See "On Intelligence" pp 66-7] This rule would presumably severely limit the number of associations that can be made with any idea in a given time, or no? ===ED PORTER => The Poggio/Serre work that I have cited so many times before (including my post that started this thread) provides a working computer model for the very type of fast feed-forward object recognition that is done very rapidly by the brain. I think it was modeling the type of recognition the brain can do in about 150ms, which lets you think you saw an alligator, a lion, a dog, a fish, etc. In that system a 160x160 pixel input patch required 23 million models, each with many inputs and outputs. If I remember correctly the lower level models had 16x16 pixel receptive fields, which is 256 inputs for each such model, so presumably many tens of millions of node to node communications would be involved in the spreading activation involved in each such recognition rapid recognition. And the 160x160 grayscale input space is much smaller than the input space of the human visual field which is probably a roughly 300x300 foviated field with red, green, blue, grayscale, and stereo vision --- a whole separate set of models for motion perception --- and an ability to recognize many more than the, I think, roughly 1000K objects the Poggio/Serre system could recognize. To top this all off, if a person is scanning a changing scene, this processes of many million of activ
Re: [agi] Re: Can We Start P.S.
Valentina, On Thu, Jul 10, 2008 at 7:55 AM, Valentina Poletti <[EMAIL PROTECTED]> wrote: > > As I explained above, many/most complex problems and conflicts can be fixed >> WITHOUT a full understanding of them, so your argument above is really >> irrelevant to my assertion. >> > > Yeh.. but i wasn't talking about such problems here. I was talking about > problems you do have a full understanding of. For example see your > statement: Random investment beats nearly all other methods. > This has been carefully studied and is now believed to be well understood. Then resulted in the "invention" of "contrarian investment" strategies, about where there are now a number of good books. In a nutshell, by the time that an industry-wide "opinion" develops, all of the "smart money" has already taken advantage of the opportunity (or lack thereof), so things can only go the opposite way. > > Not at all! There is some broadly-applicable logical principles that NEVER > EVER fail, like Reductio ad Absurdum. Some of these are advanced and not > generally known, even to people here on this forum, like Reverse Reductio ad > Absurdum. Some conflicts require this advanced level of understanding for > the participants to participate in a process that leads to a mutually > satisfactory conclusion. > > Why do you assume most people on this forum would not know/understand > them? > I look at feedback and comments, which seem to presume lack of this understanding. > And how would you relate this to culture anyways? > An interesting question, and one that I am still considering... Dr. Eliza doesn't do much that people shouldn't also be able to do - but for prior shitforbrains social programming. > > Yes, and THIS TOO is also one of those advanced concepts. If you ask a > Palestinian about what the problem is in the Middle East, he will say that > it is the Israelis. If you ask an Israeli, he will say that it is the > Palestinians. If you ask a Kanamet (from the Twilight Zone show "To Serve > Man", the title of a cook book), he will say that the problem is that they > are wasting good food. However, Reverse Reductio ad Absurdum methods can > point the way to a solution that satisfies all parties. > > Hmm.. I guess I just don't see how. Could you be a lil more specific? :) > If you DEEPLY examine the positions by drilling WAY down into the collective thought process, you find "flaws" in each sufficient to drive a common solution through. I have written longer posts on this in the past. To illustrate: 1. The Koran teaches to respect Jewdiasm and Christianity, so Jews SHOULD be able to live pretty much as they please in a Muslim society. 2. Israel claims legitimacy by UN decree, but where did the UN ever get the authority to carve a new state from an existing state? OK, so they have their state, but where does any government get the right to confiscate land without payment? OK, so they have confiscated the land, isn't this a PUBLIC asset and hence just as available to ANY inhabitant whether Israeli or Palestinian? 3. The Kanamets just want ANY peaceful solution, so they will be pleased by anything that is OK with both Israelis and Palestinians. In short, if either side actually respected the religions that they claim, then the other side should be able to live therein without problems. The problem is a population that attends mosques/synagogues but has never actually READ the entirety of their respective religious documents, as I have. Note that we have the same problems here in America, where our representatives are only too eager to set our Constitution aside as convenient. Christians believe as much or more in their Doctors as they do in Jesus, etc. > >> In short, you appear to be laboring under the most dangerous assumption of >> all - that man's efforts to improve his lot and address his problems is at >> all logical. It is rarely so, as advanced methods often suggest radically >> different and better approaches. Throwing AGIs into the present social mess >> would be an unmitigated disaster, of the very sorts that you suggest. >> > > When you say 'man' do you include yourself as well? ;) I hope not.. I don't > assume that: Yet you seem to assume that the methods you have are better > than anybody else's for any field. > This has two levels of response: 1. I (and my family) seem to be the only ones working on new systems of logic. This field has been nearly dormant for the last half-century, since the introduction of Game Theory. A notable exception has been in the field of economics, where new methods are being regularly developed, some with potential application outside of economics. 2. Perhaps you have read the book Smart Drugs co-authored by my good friend (and another past-president of The Smart Life Forum) Stephen Fowkes? This book (and Fowkes' research) addresses various pharmacological approaches to enhancing brain function. Of course, these drugs only make temporary metabolic changes, so I engineered a rel
Re: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE BINDING PROBLEM"?
RE: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE BINDING PROBLEM"?Ed:it is precisely because the human brains can do such massive searches (averaging roughly 3 to 300 trillion/second in the cortex alone) that lets us so often come up with the appropriate memory or reason at the appropriate time. Do you think the brain works by massive search in dealing with problems? Chess - a top master may consider consciously v. roughly 150 moves in a minute. Do you think his unconscious brain is considering a lot more? How many, roughly in what time? "Name 10 famous Frenchmen". How many Frenchmen roughly do you think your brain is checking out and how fast as you deal with that? Do you dispute Hawkins' "one hundred step rule"? He argues that the brain can recognize a face in 1/2 sec. - which can involve information traversing a chain of at most 100 neurons in that time. And "the largest conceivable parallel computer can't do anything useful in one hundred steps, no matter how large or how fast." [See "On Intelligence" pp 66-7] This rule would presumably severely limit the number of associations that can be made with any idea in a given time, or no? --- 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=8660244&id_secret=106510220-47b225 Powered by Listbox: http://www.listbox.com
Re: [agi] Re: Can We Start P.S.
Mike, On Wed, Jul 9, 2008 at 7:27 PM, Mike Tintner <[EMAIL PROTECTED]> wrote: > Steve: > MT:My general point is that the proper business of AGI is problematic, > open, ill-structured problems (real world problems) for which ANY > predetermined method or structure of problem-solving is wrong, (or since > there is no "right" or "wrong" with such problems, "superineffective") - > and which usually demand (unstructured) investigation of the relevant > environment to find fresh options and evidence. > >From the remainder of your response, I see that we have different ideas what a "problem" is. Much of what you call a problem I would call an activity. Detailed comments follow,,, > > *Steve:I hear you, but I don't believe these to actually exist, except in > some (unstructured) people's minds. Can you exhibit one such problem for > dissection and discussion?* > > Steve: > > -Write me a program that will make producing a multimedia essay - > video/graphics/text/sound/etc. - easy and fast for almost everyone. > This is apparently beyond human capability, and hence apparently beyond present consideration. > > -Talk to me about your father.for three minutes. > Which requires knowledge about my father, who is now dead, gone, and left few surviving details. > > -Write an essay on "the meaning of life." > Being an AGI, it has no relevant experience to write about. > > -Tidy up your room > This is (apparently) beyond even my ability, and while some future AGI might conceivably do this, I wouldn't then know where things are, what with my archaeological filing system (chronological by depth). > > -Have sex with your partner. > Gee, I sure hope not. That is entirely MY job. > > -Have a daydream about having sex with Madonna or some celebrity. > This is a specifics-of-computation issue, and since we are trying to figure out here what works, this would seem to be a minimum an unnecessary constraint, and at worse serious shitforbrains programming. > > -Outline a political strategy to improve McCain's chances. > Or better yet, see that even the Iraq government wants us out of there, so instead work on improving Obama's chances. > > -Compose a story about an AGI going berserk in a totally new way. > Clearly a counterproductive pursuit. > > -Surf on the web for the next 10 mins. > Google already does this to form its directories. > > ANY formal creative problem - > My very first computer program (on an electromechanical Burroughs E-101 accounting machine) composed rock-n-roll melodies. Another one of my early computer programs composed all possible 12-tone melodies. I then printed out the four inch thick stack and filed it with the U.S. Copyright office. Hence, I have claim against any/all new 12-tone compositions. Have you ever attended a "computer generated art" contest? Some of it is pretty good. > > -how is memory laid down in the brain? > Even the entire human population is too stupid to engage in the efforts needed to get to the bottom of this, as I have recently explained here on this forum. > -invent an electric battery that will be half the price of the cheapest one > available > Beyond present human ability. -find the solution for the "theory of everything" in physics > Solutions are not what is "missing", but rather some experimental evidence to support it. -devise an additional branch of "metacognition" to go beyond logic > But then, logic would simply encompass metacognition, as it has encompassed Reverse Reductio ad Absurdum and Game Theory. Note that most of the above "problems" are "inductive" in nature, in that while no process points directly to their solution, prospective solutions can be "tested" for acceptability. This is precisely parallel with differential equations, where there is no process to go directly to the derivative of a formula, but almost anything can be integrated to see if you got back to the original formula. Such problems have a number of "weaknesses" to exploit to arrive at solutions, e.g. characterization, exhaustive search, class elimination, etc. > > COMMENT: > All of these problems you can deal with, and start to think about. But you > do not have complete structures - conscious or intuitive - for thinking > about any of them. > "Thinking" in the classical sense is certainly not necessary and may be inhibitive. For example, most Game Theory suitable problems confound "thinking" because thinking gets trapped into "if I do this, then he does that, then I do this, then..." loops. It will be extraordinary if you don't grope about quite a bit and get stuck > for a while in trying to solve them - as I'm sure you're aware if you cast > your mind back to any creative or programming or essaywriting thinking > you've ever done - or the last minute you spent on any reflective thinking. > > The reason you don't have structures is that it would be > wrong/superineffective to have structures for these types of > problems..Ideally, normatively, wrong. > Perhap
Re: [agi] Re: Can We Start P.S.
Hey Steve, thanks for the clarifications! > My point was that the operation of most interesting phenomena is NOT > fully understood, but consists of various parts, many of which ARE > understood, or are at least easily understandable. Given the typical figure > 6 shape of most problematical cause-and-effect chains, many MAJOR problems > can be solved WITHOUT being fully understood, by simply interrupting the > process at two points, one in the lead-in from the root cause, and one in > the self-sustaining loop at the end. This usually provides considerable > choice in designing a cure. Of course this can't cure everything, but it > WOULD cure ~90% of the illnesses that now kill people, fix most (though > certainly not all) social and political conflicts, etc. > Yep, totally agree. But according to what you state below, there exist some methods that would produce exact resulsts - given you understand the system completely. That is what I was arguing against. In many fields there are problems that are understood completely and yet are still unsolvable. We know exactly the formula for say, the Lorenz curves. Yet it is impossible to determine with any certainly a point a million iterations from now. That is because even a variation at the atomic level would change the result considerably. And if we observe such variation, we change it. It seems to be nature's nature that we can never know it with exacness. Unless we are talking mathematics of course.. but as someone already pointed out on this list, mathematics has little to do with the real world. > As I explained above, many/most complex problems and conflicts can be > fixed WITHOUT a full understanding of them, so your argument above is really > irrelevant to my assertion. > Yeh.. but i wasn't talking about such problems here. I was talking about problems you do have a full understanding of. For example see your statement: Random investment beats nearly all other methods. Not at all! There is some broadly-applicable logical principles that NEVER EVER fail, like Reductio ad Absurdum. Some of these are advanced and not generally known, even to people here on this forum, like Reverse Reductio ad Absurdum. Some conflicts require this advanced level of understanding for the participants to participate in a process that leads to a mutually satisfactory conclusion. Why do you assume most people on this forum would not know/understand them? And how would you relate this to culture anyways? Yes, and THIS TOO is also one of those advanced concepts. If you ask a Palestinian about what the problem is in the Middle East, he will say that it is the Israelis. If you ask an Israeli, he will say that it is the Palestinians. If you ask a Kanamet (from the Twilight Zone show "To Serve Man", the title of a cook book), he will say that the problem is that they are wasting good food. However, Reverse Reductio ad Absurdum methods can point the way to a solution that satisfies all parties. Hmm.. I guess I just don't see how. Could you be a lil more specific? :) > > In short, you appear to be laboring under the most dangerous assumption of > all - that man's efforts to improve his lot and address his problems is at > all logical. It is rarely so, as advanced methods often suggest radically > different and better approaches. Throwing AGIs into the present social mess > would be an unmitigated disaster, of the very sorts that you suggest. > When you say 'man' do you include yourself as well? ;) I hope not.. I don't assume that: Yet you seem to assume that the methods you have are better than anybody else's for any field. --- 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=8660244&id_secret=106510220-47b225 Powered by Listbox: http://www.listbox.com
RE: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE BINDING PROBLEM"?
## RICHARD LOOSEMORE WROTE #>> Now I must repeat what I said before about some (perhaps many?) claimed solutions to the binding problem: these claimed solutions often establish the *mechanism* by which a connection could be established IF THE TWO ITEMS WANT TO TALK TO EACH OTHER. In other words, what these people (e.g. Shastri and Ajjannagadde) do is propose a two step solution: (1) the two instances magically decide that they need to get hooked up, and (2) then, some mechanism must allow these two to make contact and set up a line to one another. Think of it this way: (1) You decide that at this moment that you need to call Britney Spears, and (2) You need some mechanism whereby you can actually establish a phone connection that goes from your place to Britney's place. The crazy part of this "solution" to the binding problem is that people often make the quiet and invisible assumption that (1) is dealt with (the two items KNOW that they need to talk), and then they go on to work out a fabulously powerful way (e.g. using neural synchronisation) to get part (2) to happen. The reason this is crazy is that the first part IS the binding problem, not the second part! The second phase (the practical aspects of making the phone call get through) is just boring machinery. By the time the two parties have decided that they need to hook up, the show is already over... the binding problem has been solved. But if you look at papers describing these so-called solutions to the binding problem you will find that the first part is never talked about. At least, that was true of the S & A paper, and at least some of the papers that followed it, so I gave up following that thread in utter disgust. MY REPLY >> [Your description of Shastri's work is inaccurate --- at least from his papers I have read, which include among others, " Advances in Shruti -- A neurally motivated model of relational knowledge representation and rapid inference using temporal synchrony" Applied Intelligence, 11: 79-108, 1999 ( http://www.icsi.berkeley.edu/~shastri/psfiles/shruti_adv_98.ps ); and "Massively parallel knowledge representation and reasoning: Taking a cue from the Brain", by Shastri and Mani. It is obvious from reading Shasti that his notion of what should talk to what (i.e., i.e., be searched by spreading activation) is determined by a form of forward and/or backward chaining, which can automatically be learned from temporal associations between pattern activations, and the bindings involved can be learned by the occurrences of the same one or more pattern element instances as a part or as an attribute in one or more of those temporally related patterns. Shruiti's representational scheme has limitations that make it ill suited for use as the general representation scheme in an AGI (problems which I think can be fixed with a more generalized architecture), but the particular problem you are accusing his system of here --- i.e., that it provides no guidance as to what should be searched for when to answer a given query --- is not in fact a problem (other than the issue of possible exponential explosion of the search tree, which is discussed in my answers below)] ## RICHARD LOOSEMORE WROTE #>> It is very important to break through this confusion and find out exactly why the two relevant entities would decide to talk to each other. Solving any other aspect of the problem is not of any value. Now, going back to your question about how it would happen: if you look for a determinstic solution to the problem, I am not sure you can come up with a general answer. Whereas there is a nice, obvious solution to the question "Is Socrates mortal?" given the facts "Socrates is a man" and "All men are mortal", it is not at all clear how to do more complex forms of binding without simply doing massive searches. MY REPLY >> [You often do have to do massive searches -- it is precisely because the human brains can do such massive searches (averaging roughly 3 to 300 trillion/second in the cortex alone) that lets us so often come up with the appropriate memory or reason at the appropriate time. But the massive searches in a large Shruiti-like or Novamente-like system are not totally-blind searches --- instead they are often massive search guided by forward and/or backward chaining -- by previously learned and/or recently activated probabilities and importances --- by relative scores of various search threads or pattern activations --- by inference patterns that may have proven successful in previous similar searches --- by similar episodic memories --- and --- by interaction with the current context as represented by the other current activations] ## RICHARD LOOSEMORE WROTE #>> Or rather, it is not clear how you can *guarantee* the finding of a solution. MY REPLY >> [in such massive searching, humans often
