Re: [computer-go] Intelligence
It seems like adaptation in the context of a game of Go just making the best response to the opponent's move, however unexpected. So, if there were such a thing as a perfect Go player, it would have no need to learn, but it would be perfectly adaptive, in this context. Of course, one could also test how adaptive a computer player is to other changes in context; for example, by changing the rules on time, or switching from Chinese to Japanese rules (or even some made-up rule variant), or changing the board size, or using irregularly shaped boards, or asking it to explain a move in a way that a human would understand, or playing a good teaching game for a beginner, or even playing a different game altogether. The ability to adapt to such changes seems closer to what I'd call general-purpose intelligence. - Brian ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
Hideki Kato wrote: Creativity here is, to generate a new method by combining methods the system already has, in order to solve a problem. That is creativity for the job of designing algorithms. Playing go, creativity is finding moves _that work_ that nobody would have thought of. I think there are two myths about creativity: 1. Creativity is always good. 2. Humans are more creative than computers. 1. Creativity has to do with exploring unexpected directions. When you are subject to restrictions and have some measurable goal, there is an optimal amount of creativity for a given problem. (Imagine creativity like a thermal energy in simulated Annealing.) Too few creativity restricts you to an local minimum from which you have not enough energy to escape. Too much creativity takes you outside the goal maximization paths. The most creative go player is the uniform random player, but that it uninteresting creativity the only interesting creativity is creativity that works. Vomiting on a canvas and pretending to be an artist for that is uninteresting creativity (aka stupidity). 2. For humans it is extremely difficult to simply create one hundred uniformly random digits. Either you bias or, trying to compensate the overall distribution, you fall into serial correlation. Computer creativity is way easier, faster, measurable and reliable than human creativity. Jacques. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
I was wondering how he knows it as well. Then I decided that an Oracle must have revealed it to him. On 7/23/07, Jim O'Flaherty, Jr. [EMAIL PROTECTED] wrote: How do you know this is incorrect? Are you claiming omniscience? [EMAIL PROTECTED] wrote: No. Erik is wrong even in theory. An arguement can fault in two aspects:assumption and logic. His arguement faults on the former, even his logic is iron clad. He assumed the existence of an Oracle, which we all know is incorrect. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
I agree. Thank you for much better explanation than what I can do in English :-). (Imagine creativity like a thermal energy in simulated Annealing.) I prefer, however, non-linear dynamics in massive neural networks with feedback than SA because it's my home of research. Hideki. Jacques Basaldúa: [EMAIL PROTECTED]: Hideki Kato wrote: Creativity here is, to generate a new method by combining methods the system already has, in order to solve a problem. That is creativity for the job of designing algorithms. Playing go, creativity is finding moves _that work_ that nobody would have thought of. I think there are two myths about creativity: 1. Creativity is always good. 2. Humans are more creative than computers. 1. Creativity has to do with exploring unexpected directions. When you are subject to restrictions and have some measurable goal, there is an optimal amount of creativity for a given problem. (Imagine creativity like a thermal energy in simulated Annealing.) Too few creativity restricts you to an local minimum from which you have not enough energy to escape. Too much creativity takes you outside the goal maximization paths. The most creative go player is the uniform random player, but that it uninteresting creativity the only interesting creativity is creativity that works. Vomiting on a canvas and pretending to be an artist for that is uninteresting creativity (aka stupidity). 2. For humans it is extremely difficult to simply create one hundred uniformly random digits. Either you bias or, trying to compensate the overall distribution, you fall into serial correlation. Computer creativity is way easier, faster, measurable and reliable than human creativity. Jacques. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ -- [EMAIL PROTECTED] (Kato) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
Thanks. Like the discussion. Sometimes, learning and creation from machine intelligence point of view is not much difference. For example, when a computer is building a mathematical model from data set, it would need to construct a proper formula (creation), and at the same time, adjust parameters of the model to extract general behavior from data (learning). Weimin - Original Message - From: Jacques Basaldúa [EMAIL PROTECTED] To: computer-go@computer-go.org Sent: Monday, July 23, 2007 4:10 AM Subject: Re: [computer-go] Intelligence Hideki Kato wrote: Creativity here is, to generate a new method by combining methods the system already has, in order to solve a problem. That is creativity for the job of designing algorithms. Playing go, creativity is finding moves _that work_ that nobody would have thought of. I think there are two myths about creativity: 1. Creativity is always good. 2. Humans are more creative than computers. 1. Creativity has to do with exploring unexpected directions. When you are subject to restrictions and have some measurable goal, there is an optimal amount of creativity for a given problem. (Imagine creativity like a thermal energy in simulated Annealing.) Too few creativity restricts you to an local minimum from which you have not enough energy to escape. Too much creativity takes you outside the goal maximization paths. The most creative go player is the uniform random player, but that it uninteresting creativity the only interesting creativity is creativity that works. Vomiting on a canvas and pretending to be an artist for that is uninteresting creativity (aka stupidity). 2. For humans it is extremely difficult to simply create one hundred uniformly random digits. Either you bias or, trying to compensate the overall distribution, you fall into serial correlation. Computer creativity is way easier, faster, measurable and reliable than human creativity. Jacques. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
On 7/21/07, Weimin Xiao [EMAIL PROTECTED] wrote: Intelligence is the ability to adapt or learn. A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
Hi Erik, Erik van der Werf: [EMAIL PROTECTED] IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. I used to think learning is required for intelligence but recently I'd like to propose some creativity is. Hideki (gg) -- [EMAIL PROTECTED] (Kato) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
All, For reasons similar to those mentioned by others, I have found the phrase artificial intelligence to be less than adequate to convey my interests in this domain. And after considerable time, I came up with a term that I prefer; synthetic awareness. It comes from having interests in several different domains which feed into my interest in fabricating non-homo-sapien memetic propagation. First, synthetic is more inclusive. It means that borrowing and incorporating specialized awareness/knowledge from organic/memetic domains is included and acceptable. It also means that fabrication of new awareness/knowledge from strictly computation domains also works. Secondly, awareness is more expansive than knowledge. Boolean mathematic frames (proof focused rule based systems) and the symbolic efficiencies around linguistics (must be able to be articulated accurately) have most intellectuals fixated on producing idealized knowledge. And while there is significant value in the results produced, the results (to me) are too sequential and fragile to be expected to scale up to extremely high levels of complexity. This is why computer Checkers/Draughts is solved, computer Chess is not solved but beat the highest skilled humans, and computer Go is not even effectively beating low ranking amateurs. Awareness covers much more complex notions like the subtleties implied in intuition and creativity. Here is my reframing of a statement by a psychology author, Nathanial Branden: STATEMENT_REFRAME The need to create synthetic awareness has acquired a new urgency in the computational age. The more rapid then rate of change, the more fragile and dangerous it is to operate computers mechanically, relying on routines of Boolean software and Boolean behavior that may be irrelevant or obsolete. /STATEMENT_REFRAME As has been discussed ad infinitum here on computer_go, I don't see computer Go be solved meaning like Checkers/Draughts has been solved. I do think it is achievable to generate some sort of computational result which can eventually outplay the humans of the highest skill. I also think some significant breakthroughs are required around the move away from booleans (perfect move-vs-imperfect move) and towards scalars (probability of each available move will lead to overall increased value). While the domain of the rules of Go feel very rigid, the complexity is so vast that any idealized solution is going to turn out to be a local optima, i.e. with enough effort and exploration, it will be discovered the idealized solution, too, has weaknesses which can be exploited and eventually cause it's failure. As such, the more dynamic and creative the nature of the resulting entity, the more likely it will be the entity can eventually hop out of the local optima in search of an even higher optima. The more reserved, risk averse and rigid the entity, the more likely it will be unable to move forward and the sooner it will succumb to another entity's discovering it's weaknesses and eventually out-playing it. Go is the perfect game for demonstrating that even with a perfectly rigid foundation, the solution space is vastly more effectively searched via dynamic evolving mechanisms than via static rigid mechanisms. And as can be seen with the recent UCT/MC results, we are still just barely above randomness in terms of discovering and inventing solutions. Jim Erik van der Werf wrote: On 7/21/07, Weimin Xiao [EMAIL PROTECTED] wrote: Intelligence is the ability to adapt or learn. A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
Erik, In perfect theory, I agree with you. In the practicality of attempting to generate more effective computer Go players, I disagree. In theory, there is a perfect girlfriend for me. In practicality, there is my adapting to make the current girlfriend good enough and better, with perfection never really obtainable. Jim Erik van der Werf wrote: On 7/21/07, Weimin Xiao [EMAIL PROTECTED] wrote: Intelligence is the ability to adapt or learn. A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. For a moran without a goal, the ability to adapt or to learn is where he shows his intelligence. Weimin - Original Message - From: Erik van der Werf [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sunday, July 22, 2007 7:10 AM Subject: Re: [computer-go] Intelligence On 7/21/07, Weimin Xiao [EMAIL PROTECTED] wrote: Intelligence is the ability to adapt or learn. A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
I would believe the creativity is implied in learning. Weimin - Original Message - From: Hideki Kato [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sunday, July 22, 2007 7:38 AM Subject: Re: [computer-go] Intelligence Hi Erik, Erik van der Werf: [EMAIL PROTECTED] IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. I used to think learning is required for intelligence but recently I'd like to propose some creativity is. Hideki (gg) -- [EMAIL PROTECTED] (Kato) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
Can this oracle explain logically how he become one? :)? -Original Message- From: Erik van der Werf [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sun, 22 Jul 2007 7:10 am Subject: Re: [computer-go] Intelligence On 7/21/07, Weimin Xiao [EMAIL PROTECTED] wrote:? Intelligence is the ability to adapt or learn.? ? A hypothetical almighty oracle that already knows the correct answer? to every question and the right response in every situation would? never have to adapt. Hence evidence of intelligence according to your? definition would not be observed.? ? IMO the adaptation is just a means to an end. The end (Intelligence,? whatever it is) does not necessarily require adaptation.? ? Erik? ___? computer-go mailing list? [EMAIL PROTECTED] http://www.computer-go.org/mailman/listinfo/computer-go/? AOL now offers free email to everyone. Find out more about what's free from AOL at AOL.com. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
On 7/22/07, Weimin Xiao [EMAIL PROTECTED] wrote: A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. For a moran without a goal, the ability to adapt or to learn is where he shows his intelligence. I suppose you mean moron ;-) But yes, as long as we make fallible AI systems, adaptivity or learning will probably be an important feature to distinguish between the various shades of stupidity. Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. I think it is normal to expect, or at least in my common sense, that rationality is somehow constrained with practical limitations. So that anything intelligent in world can't know everything. Because of that intelligence means and needs adaptation for current context and enviroment kind of choosing what needs to be known depending of goals ofcourse. So because rationality is bounded it needs adapt because world around this intelligent behaviour (allways) changes, to staying intelligent it needs to adapt its enviroment which is never same than it was before, expect maybe in game of Go which nesessary don't need adaptive intelligence kind of static intelligence should be enought then but then nobody needs to call that for intelligent anymore and so on, but that does not matter because such philosophical questions are rarely solved anyway so thats fine. t. harri - Original Message - From: Jim O'Flaherty, Jr. [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sunday, July 22, 2007 6:40 PM Subject: Re: [computer-go] Intelligence Erik, In perfect theory, I agree with you. In the practicality of attempting to generate more effective computer Go players, I disagree. In theory, there is a perfect girlfriend for me. In practicality, there is my adapting to make the current girlfriend good enough and better, with perfection never really obtainable. Jim Erik van der Werf wrote: On 7/21/07, Weimin Xiao [EMAIL PROTECTED] wrote: Intelligence is the ability to adapt or learn. A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
On 7/22/07, Jim O'Flaherty, Jr. [EMAIL PROTECTED] wrote: In theory, there is a perfect girlfriend for me. In practicality, there is my adapting to make the current girlfriend good enough and better, with perfection never really obtainable. Interesting example. Intelligence may be like beauty; very difficult, if not impossible, to define objectively. But then, you seem to know pretty well what she should be like ;-) Erik ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
On 7/22/07, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: Can this oracle explain logically how he become one? :) :-) That depends on the domain. If the domain is Go-world you would not even be able to phrase that question. If the domain would be the world in which you live, the correct answer would probably be something like You are too young for this boy. ;-) E. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
No. Erik is wrong even in theory. An arguement can fault in two aspects:assumption and logic. His arguement faults on the?former, even his logic is iron clad. He assumed the existence of an Oracle, which we all know is incorrect. ?? -Original Message- From: Jim O'Flaherty, Jr. [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sun, 22 Jul 2007 10:40 am Subject: Re: [computer-go] Intelligence Erik,? ? In perfect theory, I agree with you. In the practicality of attempting to generate more effective computer Go players, I disagree.? ? In theory, there is a perfect girlfriend for me. In practicality, there is my adapting to make the current girlfriend good enough and better, with perfection never really obtainable.? ? Jim? ? Erik van der Werf wrote:? On 7/21/07, Weimin Xiao [EMAIL PROTECTED] wrote:? Intelligence is the ability to adapt or learn.? ? A hypothetical almighty oracle that already knows the correct answer? to every question and the right response in every situation would? never have to adapt. Hence evidence of intelligence according to your? definition would not be observed.? ? IMO the adaptation is just a means to an end. The end (Intelligence,? whatever it is) does not necessarily require adaptation.? ? Erik? ___? computer-go mailing list? [EMAIL PROTECTED] http://www.computer-go.org/mailman/listinfo/computer-go/? ? ___? computer-go mailing list? [EMAIL PROTECTED] http://www.computer-go.org/mailman/listinfo/computer-go/? AOL now offers free email to everyone. Find out more about what's free from AOL at AOL.com. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
On 7/23/07, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: No. Erik is wrong even in theory. An arguement can fault in two aspects:assumption and logic. His arguement faults on the former, even his logic is iron clad. He assumed the existence of an Oracle, which we all know is incorrect. 'We' seem to be drifting away a bit here... Adaptation is something that is easily observed with relatively stupid entities. To some extend I agree that such an observation probably indicates some kind of intelligence, but on the other hand, the world is full of adaptive systems which for some reason several of the earlier posters here would not consider to be intelligent. Once the level of intelligence of some artificial system would move far beyond the level of the observer he may no longer be able to observe the adaptation or learning (and with human observers in complex domains we probably don't even need to go to oracle-level for that). However, does that mean the system would now be considered unintelligent, or stupid, just because adaptation stopped or because we simply can't detect it? I don't think so! I guess most ordinary humans might even consider this system to be incredibly intelligent. But how do they get to that conclusion without observing any adaptation or learning? E. BTW Oracles are a useful tool for theory. Moreover, in practice they can be constructed for sufficiently small well defined finite domains such as small board Go, six-men chess (end)games, etc. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
How do you know this is incorrect? Are you claiming omniscience? [EMAIL PROTECTED] wrote: No. Erik is wrong even in theory. An arguement can fault in two aspects:assumption and logic. His arguement faults on the former, even his logic is iron clad. He assumed the existence of an Oracle, which we all know is incorrect. -Original Message- From: Jim O'Flaherty, Jr. [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sun, 22 Jul 2007 10:40 am Subject: Re: [computer-go] Intelligence Erik, In perfect theory, I agree with you. In the practicality of attempting to generate more effective computer Go players, I disagree. In theory, there is a perfect girlfriend for me. In practicality, there is my adapting to make the current girlfriend good enough and better, with perfection never really obtainable. Jim Erik van der Werf wrote: On 7/21/07, Weimin Xiao [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] wrote: Intelligence is the ability to adapt or learn. A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. Erik ___ computer-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ AOL now offers free email to everyone. Find out more about what's free from AOL at *AOL.com* http://www.aol.com?ncid=AOLAOF0002000437. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
Correct logic based on false assumption?inevitably leads to self-contradiction. So if an assumption leads to self-contradiction, it must be false. It's not that we can make a false assumption and apply correct logic on it. It will never lead to a consistent theory. -Original Message- From: Jim O'Flaherty, Jr. [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sun, 22 Jul 2007 8:28 pm Subject: Re: [computer-go] Intelligence How do you know this is incorrect? Are you claiming omniscience?? ? [EMAIL PROTECTED] wrote:? No. Erik is wrong even in theory. An arguement can fault in two aspects:assumption and logic. His arguement faults on the former, even his logic is iron clad. He assumed the existence of an Oracle, which we all know is incorrect.? ? -Original Message-? From: Jim O'Flaherty, Jr. [EMAIL PROTECTED]? To: computer-go computer-go@computer-go.org? Sent: Sun, 22 Jul 2007 10:40 am? Subject: Re: [computer-go] Intelligence? ? Erik, In perfect theory, I agree with you. In the practicality of attempting to generate more effective computer Go players, I disagree. In theory, there is a perfect girlfriend for me. In practicality, there is my adapting to make the current girlfriend good enough and better, with perfection never really obtainable. Jim Erik van der Werf wrote: On 7/21/07, Weimin Xiao [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] wrote: Intelligence is the ability to adapt or learn. A hypothetical almighty oracle that already knows the correct answer to every question and the right response in every situation would never have to adapt. Hence evidence of intelligence according to your definition would not be observed. IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. Erik ___ compu ter-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org mailto:computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ? AOL now offers free email to everyone. Find out more about what's free from AOL at *AOL.com* http://www.aol.com?ncid=AOLAOF0002000437.? ? ? ___? computer-go mailing list? [EMAIL PROTECTED] http://www.computer-go.org/mailman/listinfo/computer-go/? ___? computer-go mailing list? [EMAIL PROTECTED] http://www.computer-go.org/mailman/listinfo/computer-go/? AOL now offers free email to everyone. Find out more about what's free from AOL at AOL.com. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
I don't think so. They are different concepts as well as functions. Learning is, changing internal state according to external input and then changing future behavior of a system. Creativity here is, to generate a new method by combining methods the system already has, in order to solve a problem. Hideki Weimin Xiao: [EMAIL PROTECTED]: I would believe the creativity is implied in learning. Weimin - Original Message - From: Hideki Kato [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Sunday, July 22, 2007 7:38 AM Subject: Re: [computer-go] Intelligence Hi Erik, Erik van der Werf: [EMAIL PROTECTED] IMO the adaptation is just a means to an end. The end (Intelligence, whatever it is) does not necessarily require adaptation. I used to think learning is required for intelligence but recently I'd like to propose some creativity is. Hideki (gg) -- [EMAIL PROTECTED] (Kato) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ -- [EMAIL PROTECTED] (Kato) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
[computer-go] Intelligence
Intelligence is the ability to adapt or learn. I would believe neural network is not a proper way on learning GO, as too many nodes would be needed for patterns, and storage and training may not be feasible. Weimin - Original Message - From: Erik van der Werf [EMAIL PROTECTED] To: computer-go computer-go@computer-go.org Sent: Wednesday, July 11, 2007 9:28 AM Subject: Re: [computer-go] Explanation to MoGo paper wanted. So how would you define intelligence? E. ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/ ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
Re: [computer-go] Intelligence
Intelligence is the ability to adapt or learn. I would believe neural network is not a proper way on learning GO, as too many nodes would be needed for patterns, and storage and training may not be feasible. But a variant on the neural network idea could work. (If these cells are sending a bit to one another, there is no additional overhead in sending a 32-bit pattern, not much in having different cells process the received patterns differently.) The normal ways of training a network to recognize a human-generated set of correct responses aren't applicable; but you can always form a list of which cells were involved in a particular move, and use it to raise thresholds, reduce sensitivity to particular inputs, etc. The problem someone here reminded me of yesterday--What subgoals can a program readily train itself to recognize? Generate some ~180 moves, then see whether they led to a win, and reward/discourage itself retroactively? Clumsy! So--How do most living beings do it? Pleasure/pain. Animate beings have internal indicators of How am I doing? When these are high, there's a tendency to repeat whatever one was doing, try more, get adventurous; if low, to STOP THAT! (Since THAT may not be well-defined, pain/discouragement can be taken too far, but it does offer the best chance of not repeating the situation.) The problem is, how to recognize when a program should 'pleasure itself'? Or suffer? Some kind of evolutionary scheme for generating good evaluators? We can't just indiscriminately let a program encourage whatever pathway leads it to encourage itself; it might decide it doesn't need to play that silly game! Ahhh! Maybe some long-term setting based on wins/losses, weighted toward recent games? When this is high, continue to moderately encourage moves/positions that the evaluator likes-- when low, kick the evaluating net/subnet until it either dies or gets less indiscriminatingly encouraging? Forrest Curo ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
