[agi] Mindplex for Is-a Functionality
Thurs.22.JUL.2010 -- Mindplex for Is-a Functionality As we contemplate AI coding for responses to such questions as Who is Andru? What is Andru? Who are you? What are you? we realize that simple memory-activation of question-words like who or what will not be sufficient to invoke the special handling of mental issues raised by such question-words. Nay, we realize that each question-word will need to call not so much a mind-module of normal syntactic control, such as NounPhrase or VerbPhrase, but rather something like a WhoPlex or a WhatPlex or a WherePlex or even a WhyPlex, as a kind of meta-module which is not a building block of the cognitive architecture, but is rather a governance of the interaction of the regular mind-modules. A WhatPlex, for instance, in answering a What-is question, must predispose the AI Mind to provide a certain kind of information (e.g., ontological class) couched amid certain concomitant mind-modules (e.g., EnArticle a) so as to output an answer such as, I am a robot. Since the quasi-mind-modules to be invoked by question-words comprise a small cluster of similar mental complexes necessary for the special handling of the input of the question-words, we might as well designate the members of the set of complexes as code structures with names like WhatPlex ending in -Plex. Witness that the Google enterprise has named its campus or cluster of buildings as the Googleplex. Ben Goertzel has used a similar term to refer to a mindplex of mind components. We will try to use WhoPlex and WhatPlex to remind ourselves as AI appcoders that we are letting rules of special handling accumulate by an accretion akin to the emergence of a mental complex. Arthur -- See the HTML version below for its links. http://robots.net/person/AI4U/diary/23.html --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
[agi] Re: Huge Progress on the Core of AGI
An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most accurate and predictive hypothesis. That is the ultimate and true measure of correctness. Also, since we can't measure every possible prediction or every last prediction (and we certainly can't predict everything), our measure of predictiveness can't possibly be right all the time! We have no choice but to use a heuristic of some kind. So, its clear to me that the right hypothesis is more predictive and then simpler. But, it is also clear that there will never be a single measure of this that can be applied to all problems. I hope to eventually find a nice model for how to apply it to different problems though. This may be the reason that so many people have tried and failed to develop general AI. Yes, there is a solution. But there is no silver bullet that can be applied to all problems. Some methods are better than others. But I think another major reason of the failures is that people think they can predict things without sufficient information. By approaching the problem this way, we compound the need for heuristics and the errors they produce because we simply don't have sufficient information to make a good decision with limited evidence. If approached correctly, the right solution would solve many more problems with the same efforts than a poor solution would. It would also eliminate some of the difficulties we currently face if sufficient data is available to learn from. In addition to all this theory about better hypotheses, you have to add on the need to solve problems in reasonable time. This also compounds the difficulty of the problem and the complexity of solutions. I am always fascinated by the extraordinary difficulty and complexity of this problem. The more I learn about it, the more I appreciate it. Dave --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Re: Huge Progress on the Core of AGI
Jim, Why more predictive *and then* simpler? --Abram On Thu, Jul 22, 2010 at 11:49 AM, David Jones davidher...@gmail.com wrote: An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most accurate and predictive hypothesis. That is the ultimate and true measure of correctness. Also, since we can't measure every possible prediction or every last prediction (and we certainly can't predict everything), our measure of predictiveness can't possibly be right all the time! We have no choice but to use a heuristic of some kind. So, its clear to me that the right hypothesis is more predictive and then simpler. But, it is also clear that there will never be a single measure of this that can be applied to all problems. I hope to eventually find a nice model for how to apply it to different problems though. This may be the reason that so many people have tried and failed to develop general AI. Yes, there is a solution. But there is no silver bullet that can be applied to all problems. Some methods are better than others. But I think another major reason of the failures is that people think they can predict things without sufficient information. By approaching the problem this way, we compound the need for heuristics and the errors they produce because we simply don't have sufficient information to make a good decision with limited evidence. If approached correctly, the right solution would solve many more problems with the same efforts than a poor solution would. It would also eliminate some of the difficulties we currently face if sufficient data is available to learn from. In addition to all this theory about better hypotheses, you have to add on the need to solve problems in reasonable time. This also compounds the difficulty of the problem and the complexity of solutions. I am always fascinated by the extraordinary difficulty and complexity of this problem. The more I learn about it, the more I appreciate it. Dave *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com -- Abram Demski http://lo-tho.blogspot.com/ http://groups.google.com/group/one-logic --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed:
Re: [agi] Re: Huge Progress on the Core of AGI
Predicting the old and predictable [incl in shape and form] is narrow AI. Squaresville. Adapting to the new and unpredictable [incl in shape and form] is AGI. Rock on. From: David Jones Sent: Thursday, July 22, 2010 4:49 PM To: agi Subject: [agi] Re: Huge Progress on the Core of AGI An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most accurate and predictive hypothesis. That is the ultimate and true measure of correctness. Also, since we can't measure every possible prediction or every last prediction (and we certainly can't predict everything), our measure of predictiveness can't possibly be right all the time! We have no choice but to use a heuristic of some kind. So, its clear to me that the right hypothesis is more predictive and then simpler. But, it is also clear that there will never be a single measure of this that can be applied to all problems. I hope to eventually find a nice model for how to apply it to different problems though. This may be the reason that so many people have tried and failed to develop general AI. Yes, there is a solution. But there is no silver bullet that can be applied to all problems. Some methods are better than others. But I think another major reason of the failures is that people think they can predict things without sufficient information. By approaching the problem this way, we compound the need for heuristics and the errors they produce because we simply don't have sufficient information to make a good decision with limited evidence. If approached correctly, the right solution would solve many more problems with the same efforts than a poor solution would. It would also eliminate some of the difficulties we currently face if sufficient data is available to learn from. In addition to all this theory about better hypotheses, you have to add on the need to solve problems in reasonable time. This also compounds the difficulty of the problem and the complexity of solutions. I am always fascinated by the extraordinary difficulty and complexity of this problem. The more I learn about it, the more I appreciate it. Dave 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:
Re: [agi] Comments On My Skepticism of Solomonoff Induction
I have to retract my claim that the programs of Solomonoff Induction would be trans-infinite. Each of the infinite individual programs could be enumerated by their individual instructions so some combination of unique individual programs would not correspond to a unique program but to the enumerated program that corresponds to the string of their individual instructions. So I got that one wrong. Jim Bromer --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Re: Huge Progress on the Core of AGI
Because simpler is not better if it is less predictive. On Thu, Jul 22, 2010 at 1:21 PM, Abram Demski abramdem...@gmail.com wrote: Jim, Why more predictive *and then* simpler? --Abram On Thu, Jul 22, 2010 at 11:49 AM, David Jones davidher...@gmail.comwrote: An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most accurate and predictive hypothesis. That is the ultimate and true measure of correctness. Also, since we can't measure every possible prediction or every last prediction (and we certainly can't predict everything), our measure of predictiveness can't possibly be right all the time! We have no choice but to use a heuristic of some kind. So, its clear to me that the right hypothesis is more predictive and then simpler. But, it is also clear that there will never be a single measure of this that can be applied to all problems. I hope to eventually find a nice model for how to apply it to different problems though. This may be the reason that so many people have tried and failed to develop general AI. Yes, there is a solution. But there is no silver bullet that can be applied to all problems. Some methods are better than others. But I think another major reason of the failures is that people think they can predict things without sufficient information. By approaching the problem this way, we compound the need for heuristics and the errors they produce because we simply don't have sufficient information to make a good decision with limited evidence. If approached correctly, the right solution would solve many more problems with the same efforts than a poor solution would. It would also eliminate some of the difficulties we currently face if sufficient data is available to learn from. In addition to all this theory about better hypotheses, you have to add on the need to solve problems in reasonable time. This also compounds the difficulty of the problem and the complexity of solutions. I am always fascinated by the extraordinary difficulty and complexity of this problem. The more I learn about it, the more I appreciate it. Dave *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com -- Abram Demski http://lo-tho.blogspot.com/
Re: [agi] Re: Huge Progress on the Core of AGI
David Jones wrote: But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. It isn't hard. To measure predictiveness, you assign a probability to each possible outcome. If the actual outcome has probability p, you score a penalty of log(1/p) bits. To measure simplicity, use the compressed size of the code for your prediction algorithm. Then add the two scores together. That's how it is done in the Calgary challenge http://www.mailcom.com/challenge/ and in my own text compression benchmark. -- Matt Mahoney, matmaho...@yahoo.com From: David Jones davidher...@gmail.com To: agi agi@v2.listbox.com Sent: Thu, July 22, 2010 3:11:46 PM Subject: Re: [agi] Re: Huge Progress on the Core of AGI Because simpler is not better if it is less predictive. On Thu, Jul 22, 2010 at 1:21 PM, Abram Demski abramdem...@gmail.com wrote: Jim, Why more predictive *and then* simpler? --Abram On Thu, Jul 22, 2010 at 11:49 AM, David Jones davidher...@gmail.com wrote: An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most accurate and predictive hypothesis. That is the ultimate and true measure of correctness. Also, since we can't measure every possible prediction or every last prediction (and we certainly can't predict everything), our measure of predictiveness can't possibly be right all the time! We have no choice but to use a heuristic of some kind. So, its clear to me that the right hypothesis is more predictive and then simpler. But, it is also clear that there will never be a single measure of this that can be applied to all problems. I hope to eventually find a nice model for how to apply it to different problems though. This may be the reason that so many people have tried and failed to develop general AI. Yes, there is a solution. But there is no silver bullet that can be applied to all problems. Some methods are better than others. But I think another major reason of the failures is that people think they can predict things without sufficient information. By approaching the problem this way, we compound the need for heuristics and the errors they produce because we simply don't have sufficient information to make a good decision with limited evidence. If approached correctly, the right solution would solve many more
[agi] What is so special with the number seven
Is there any predisposition to the Number 7 and our brains? Why do we have a scale with 7 notes? Why are there 7 colors in a rainbow.? Can this relate to how we perceive things? Seven days of a week. cheers, Deepak --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
[agi] How do we hear music
Why do we listen to a song sung in different scale and yet identify it as the same song.? Does it have something to do with the fundamental way in which we store memory? cheers, Deepak --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
deepakjnath wrote: Why do we listen to a song sung in different scale and yet identify it as the same song.? Does it have something to do with the fundamental way in which we store memory? For the same reason that gray looks green on a red background. You have more neurons that respond to differences in tones than to absolute frequencies. -- Matt Mahoney, matmaho...@yahoo.com From: deepakjnath deepakjn...@gmail.com To: agi agi@v2.listbox.com Sent: Thu, July 22, 2010 3:59:57 PM Subject: [agi] How do we hear music Why do we listen to a song sung in different scale and yet identify it as the same song.? Does it have something to do with the fundamental way in which we store memory? cheers, Deepak 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Comments On My Skepticism of Solomonoff Induction
On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.com wrote: The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? You give a precise statement of the probability in general terms, but then say that it is uncomputable. Then you ask if there is a paper that refutes it. Well, why would any serious mathematician bother to refute it since you yourself acknowledge that it is uncomputable and therefore unverifiable and therefore not a mathematical theorem that can be proven true or false? It isn't like you claimed that the mathematical statement is verifiable. It is as if you are making a statement and then ducking any responsibility for it by denying that it is even an evaluation. You honestly don't see the irregularity? My point is that the general mathematical community doesn't accept Solomonoff Induction, not that I have a paper that *refutes it,* whatever that would mean. Please give me a little more explanation why you say the fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. Why is the M in a bracket? On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.com wrote: Jim Bromer wrote: The fundamental method of Solmonoff Induction is trans-infinite. The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. How does this approximation invalidate Solomonoff induction? Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? -- Matt Mahoney, matmaho...@yahoo.com -- *From:* Jim Bromer jimbro...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Wed, July 21, 2010 3:08:13 PM *Subject:* Re: [agi] Comments On My Skepticism of Solomonoff Induction I should have said, It would be unwise to claim that this method could stand as an ideal for some valid and feasible application of probability. Jim Bromer On Wed, Jul 21, 2010 at 2:47 PM, Jim Bromer jimbro...@gmail.com wrote: The fundamental method of Solmonoff Induction is trans-infinite. Suppose you iterate through all possible programs, combining different programs as you go. Then you have an infinite number of possible programs which have a trans-infinite number of combinations, because each tier of combinations can then be recombined to produce a second, third, fourth,... tier of recombinations. Anyone who claims that this method is the ideal for a method of applied probability is unwise. Jim Bromer *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com/ *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] What is so special with the number seven
2010/7/22 deepakjnath deepakjn...@gmail.com Is there any predisposition to the Number 7 and our brains? Why do we have a scale with 7 notes? Why are there 7 colors in a rainbow.? Can this relate to how we perceive things? Seven days of a week. cheers, Deepak *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com You can pick any number and find things related to it. Besides, your anecdotes may be explained with physics or musical theory, for example. I don't know anything about music theory, but it seems that the chromatic scale has 12 notes. Also, it seems that Newton named 7 colors in the Rainbow to make it match the idea of the seven note scale ( http://en.wikipedia.org/wiki/Rainbow#Distinct_colours ) - Panu Horsmalahti --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
Schemas are what maths can't handle - and are fundamental to AGI. Maths are what Mike can't handle - and are fundamental to AGI. -- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Re: Huge Progress on the Core of AGI
It's certainly not as simple as you claim. First, assigning a probability is not always possible, nor is it easy. The factors in calculating that probability are unknown and are not the same for every instance. Since we do not know what combination of observations we will see, we cannot have a predefined set of probabilities, nor is it any easier to create a probability function that generates them for us. That is just as exactly what I meant by quantitatively define the predictiveness... it would be proportional to the probability. Second, if you can define a program ina way that is always simpler when it is smaller, then you can do the same thing without a program. I don't think it makes any sense to do it this way. It is not that simple. If it was, we could solve a large portion of agi easily. On Thu, Jul 22, 2010 at 3:16 PM, Matt Mahoney matmaho...@yahoo.com wrote: David Jones wrote: But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. It isn't hard. To measure predictiveness, you assign a probability to each possible outcome. If the actual outcome has probability p, you score a penalty of log(1/p) bits. To measure simplicity, use the compressed size of the code for your prediction algorithm. Then add the two scores together. That's how it is done in the Calgary challenge http://www.mailcom.com/challenge/ and in my own text compression benchmark. -- Matt Mahoney, matmaho...@yahoo.com *From:* David Jones davidher...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Thu, July 22, 2010 3:11:46 PM *Subject:* Re: [agi] Re: Huge Progress on the Core of AGI Because simpler is not better if it is less predictive. On Thu, Jul 22, 2010 at 1:21 PM, Abram Demski abramdem...@gmail.com wrote: Jim, Why more predictive *and then* simpler? --Abram On Thu, Jul 22, 2010 at 11:49 AM, David Jones davidher...@gmail.com wrote: An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most accurate and predictive hypothesis. That is the ultimate and true measure of correctness. Also, since we can't measure every possible prediction or every last prediction (and we certainly can't predict everything), our measure of predictiveness can't possibly be right all the time! We have no choice but to use a heuristic of some kind. So, its clear to me that the right hypothesis is more predictive and then simpler. But, it is also clear that there
Re: [agi] How do we hear music
And maths will handle the examples given : same tunes - different scales, different instruments same face - cartoon, photo same logo - different parts [buildings/ fruits/ human figures] revealing them to be the same - how exactly? Or you could take two arseholes - same kind of object, but radically different configurations - maths will show them to belong to the same category, how? IOW do you have the slightest evidence for what you're claiming? And to which part of AGI, is maths demonstrably fundamental? Any idea? Or are you just praying? From: L Detetive Sent: Thursday, July 22, 2010 11:49 PM To: agi Subject: Re: [agi] How do we hear music Schemas are what maths can't handle - and are fundamental to AGI. Maths are what Mike can't handle - and are fundamental to AGI. -- L 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
Are you suggesting that I teach you some math? I learned it by myself, why can't you? Stop being lazy (and ridiculous), please. -- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
Mike Tintner trolled And maths will handle the examples given : same tunes - different scales, different instruments same face - cartoon, photo same logo - different parts [buildings/ fruits/ human figures] Unfortunately I forgot. The answer is somewhere down there: http://en.wikipedia.org/wiki/Eigenvalue,_eigenvector_and_eigenspace http://en.wikipedia.org/wiki/Pattern_recognition http://en.wikipedia.org/wiki/Curve_fitting http://en.wikipedia.org/wiki/System_identification revealing them to be the same - how exactly? Why should anybody explain that mystery to you? You are not an accepted member of the Grand Lodge of AGI Masons or its affiliates. Or you could take two arseholes - same kind of object, but radically different configurations - maths will show them to belong to the same category, how? How will you do it? By licking them? --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
You could add this one too, Jan: http://scholar.google.com.br/scholar?hl=enq=%22fourier-mellin+transform%22btnG=Searchas_sdt=2000as_ylo=as_vis=1 No more excuses for being lazy now. The answers for all proposed questions are inside those links. -- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
Hi, Sometimes outrageous comments are a catalyst for better ideas. On Fri, 2010-07-23 at 01:48 +0200, Jan Klauck wrote: Mike Tintner trolled And maths will handle the examples given : same tunes - different scales, different instruments same face - cartoon, photo same logo - different parts [buildings/ fruits/ human figures] Unfortunately I forgot. The answer is somewhere down there: http://en.wikipedia.org/wiki/Eigenvalue,_eigenvector_and_eigenspace http://en.wikipedia.org/wiki/Pattern_recognition http://en.wikipedia.org/wiki/Curve_fitting http://en.wikipedia.org/wiki/System_identification No-one has successfully integrated these concepts into a working AGI, despite numerous attempts. Even though these concept feel general, when implemented, only narrow or affected by combinatorial explosion have succeeded. revealing them to be the same - how exactly? Why should anybody explain that mystery to you? You are not an accepted member of the Grand Lodge of AGI Masons or its affiliates. Or you could take two arseholes - same kind of object, but radically different configurations - maths will show them to belong to the same category, how? How will you do it? By licking them? Personal attacks only weaken your arguments. --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
No-one has successfully integrated these concepts into a working AGI, So I could say for ANY method. -- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Comments On My Skepticism of Solomonoff Induction
Jim Bromer wrote: Please give me a little more explanation why you say the fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. Why is the M in a bracket? By |M| I mean the length of the program M in bits. Why 2^-|M|? Because each bit means you can have twice as many programs, so they should count half as much. Being uncomputable doesn't make it wrong. The fact that there is no general procedure for finding the shortest program that outputs a string doesn't mean that you can never find it, or that for many cases you can't approximate it. You apply Solomonoff induction all the time. What is the next bit in these sequences? 1. 0101010101010101010101010101010 2. 11001001110110101010001 In sequence 1 there is an obvious pattern with a short description. You can find a short program that outputs 0 and 1 alternately forever, so you predict the next bit will be 1. It might not be the shortest program, but it is enough that alternate 0 and 1 forever is shorter than alternate 0 and 1 15 times followed by 00 that you can confidently predict the first hypothesis is more likely. The second sequence is not so obvious. It looks like random bits. With enough intelligence (or computation) you might discover that the sequence is a binary representation of pi, and therefore the next bit is 0. But the fact that you might not discover the shortest description does not invalidate the principle. It just says that you can't always apply Solomonoff induction and get the number you want. Perhaps http://en.wikipedia.org/wiki/Kolmogorov_complexity will make this clear. -- Matt Mahoney, matmaho...@yahoo.com From: Jim Bromer jimbro...@gmail.com To: agi agi@v2.listbox.com Sent: Thu, July 22, 2010 5:06:12 PM Subject: Re: [agi] Comments On My Skepticism of Solomonoff Induction On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.com wrote: The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? You give a precise statement of the probability in general terms, but then say that it is uncomputable. Then you ask if there is a paper that refutes it. Well, why would any serious mathematician bother to refute it since you yourself acknowledge that it is uncomputable and therefore unverifiable and therefore not a mathematical theorem that can be proven true or false? It isn't like you claimed that the mathematical statement is verifiable. It is as if you are making a statement and then ducking any responsibility for it by denying that it is even an evaluation. You honestly don't see the irregularity? My point is that the general mathematical community doesn't accept Solomonoff Induction, not that I have a paper that refutes it, whatever that would mean. Please give me a little more explanation why you say the fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. Why is the M in a bracket? On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.com wrote: Jim Bromer wrote: The fundamental method of Solmonoff Induction is trans-infinite. The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. How does this approximation invalidate Solomonoff induction? Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? -- Matt Mahoney, matmaho...@yahoo.com From: Jim Bromer jimbro...@gmail.com To: agi agi@v2.listbox.com Sent: Wed, July 21, 2010 3:08:13 PM Subject: Re: [agi] Comments On My Skepticism of Solomonoff Induction I should have said, It would be unwise to claim that this method could stand as an ideal for some valid and feasible application of probability. Jim Bromer On Wed, Jul 21, 2010 at 2:47 PM, Jim Bromer jimbro...@gmail.com wrote: The fundamental method of Solmonoff Induction is trans-infinite. Suppose you iterate through all possible programs, combining different programs as you go. Then you have an infinite number of possible programs which have a trans-infinite number of combinations, because each tier of combinations can then be recombined to produce a second, third, fourth,... tier of recombinations. Anyone who claims that this method is the ideal for a method of applied probability is unwise.
Re: [agi] Comments On My Skepticism of Solomonoff Induction
Thanks for the explanation. I want to learn more about statistical modelling and compression but I will need to take my time on it. But no, I don't apply Solomonoff Induction all the time, I never apply it. I am not being petty, it's just that you have taken a coincidence and interpreted it the way you want to. On Thu, Jul 22, 2010 at 9:33 PM, Matt Mahoney matmaho...@yahoo.com wrote: Jim Bromer wrote: Please give me a little more explanation why you say the fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. Why is the M in a bracket? By |M| I mean the length of the program M in bits. Why 2^-|M|? Because each bit means you can have twice as many programs, so they should count half as much. Being uncomputable doesn't make it wrong. The fact that there is no general procedure for finding the shortest program that outputs a string doesn't mean that you can never find it, or that for many cases you can't approximate it. You apply Solomonoff induction all the time. What is the next bit in these sequences? 1. 0101010101010101010101010101010 2. 11001001110110101010001 In sequence 1 there is an obvious pattern with a short description. You can find a short program that outputs 0 and 1 alternately forever, so you predict the next bit will be 1. It might not be the shortest program, but it is enough that alternate 0 and 1 forever is shorter than alternate 0 and 1 15 times followed by 00 that you can confidently predict the first hypothesis is more likely. The second sequence is not so obvious. It looks like random bits. With enough intelligence (or computation) you might discover that the sequence is a binary representation of pi, and therefore the next bit is 0. But the fact that you might not discover the shortest description does not invalidate the principle. It just says that you can't always apply Solomonoff induction and get the number you want. Perhaps http://en.wikipedia.org/wiki/Kolmogorov_complexity will make this clear. -- Matt Mahoney, matmaho...@yahoo.com -- *From:* Jim Bromer jimbro...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Thu, July 22, 2010 5:06:12 PM *Subject:* Re: [agi] Comments On My Skepticism of Solomonoff Induction On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.comwrote: The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? You give a precise statement of the probability in general terms, but then say that it is uncomputable. Then you ask if there is a paper that refutes it. Well, why would any serious mathematician bother to refute it since you yourself acknowledge that it is uncomputable and therefore unverifiable and therefore not a mathematical theorem that can be proven true or false? It isn't like you claimed that the mathematical statement is verifiable. It is as if you are making a statement and then ducking any responsibility for it by denying that it is even an evaluation. You honestly don't see the irregularity? My point is that the general mathematical community doesn't accept Solomonoff Induction, not that I have a paper that *refutes it,*whatever that would mean. Please give me a little more explanation why you say the fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. Why is the M in a bracket? On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.comwrote: Jim Bromer wrote: The fundamental method of Solmonoff Induction is trans-infinite. The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. How does this approximation invalidate Solomonoff induction? Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? -- Matt Mahoney, matmaho...@yahoo.com -- *From:* Jim Bromer jimbro...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Wed, July 21, 2010 3:08:13 PM *Subject:* Re: [agi] Comments On My Skepticism of Solomonoff Induction I should have said, It would be unwise to claim that this method could stand as an ideal for some valid and feasible application of probability. Jim Bromer On Wed, Jul 21, 2010 at 2:47 PM, Jim Bromer jimbro...@gmail.com wrote: The fundamental method of Solmonoff Induction is trans-infinite.
Re: [agi] Re: Huge Progress on the Core of AGI
ps-- Sorry for accidentally calling you Jim! On Thu, Jul 22, 2010 at 1:21 PM, Abram Demski abramdem...@gmail.com wrote: Jim, Why more predictive *and then* simpler? --Abram On Thu, Jul 22, 2010 at 11:49 AM, David Jones davidher...@gmail.comwrote: An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most accurate and predictive hypothesis. That is the ultimate and true measure of correctness. Also, since we can't measure every possible prediction or every last prediction (and we certainly can't predict everything), our measure of predictiveness can't possibly be right all the time! We have no choice but to use a heuristic of some kind. So, its clear to me that the right hypothesis is more predictive and then simpler. But, it is also clear that there will never be a single measure of this that can be applied to all problems. I hope to eventually find a nice model for how to apply it to different problems though. This may be the reason that so many people have tried and failed to develop general AI. Yes, there is a solution. But there is no silver bullet that can be applied to all problems. Some methods are better than others. But I think another major reason of the failures is that people think they can predict things without sufficient information. By approaching the problem this way, we compound the need for heuristics and the errors they produce because we simply don't have sufficient information to make a good decision with limited evidence. If approached correctly, the right solution would solve many more problems with the same efforts than a poor solution would. It would also eliminate some of the difficulties we currently face if sufficient data is available to learn from. In addition to all this theory about better hypotheses, you have to add on the need to solve problems in reasonable time. This also compounds the difficulty of the problem and the complexity of solutions. I am always fascinated by the extraordinary difficulty and complexity of this problem. The more I learn about it, the more I appreciate it. Dave *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com -- Abram Demski http://lo-tho.blogspot.com/ http://groups.google.com/group/one-logic
[agi] Huge Progress on the Core of AGI
I have to say that I am proud of David Jone's efforts. He has really matured during these last few months. I'm kidding but I really do respect the fact that he is actively experimenting. I want to get back to work on my artificial imagination and image analysis programs - if I can ever figure out how to get the time. As I have read David's comments, I realize that we need to really leverage all sorts of cruddy data in order to make good agi. But since that kind of thing doesn't work with sparse knowledge, it seems that the only way it could work is with extensive knowledge about a wide range of situations, like the knowledge gained from a vast variety of experiences. This conjecture makes some sense because if wide ranging knowledge could be kept in superficial stores where it could be accessed quickly and economically, it could be used efficiently in (conceptual) model fitting. However, as knowledge becomes too extensive it might become too unwieldy to find what is needed for a particular situation. At this point indexing becomes necessary with cross-indexing references to different knowledge based on similarities and commonalities of employment. Here I am saying that relevant knowledge based on previous learning might not have to be totally relevant to a situation as long as it could be used to run during an ongoing situation. From this perspective then, knowledge from a wide variety of experiences should actually be composed of reactions on different conceptual levels. Then as a piece of knowledge is brought into play for an ongoing situation, those levels that seem best suited to deal with the situation could be promoted quickly as the situation unfolds, acting like an automated indexing system into other knowledge relevant to the situation. So the ongoing process of trying to determine what is going on and what actions should be made would simultaneously act like an automated index to find better knowledge more suited for the situation. Jim Bromer --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Re: Huge Progress on the Core of AGI
David, What are the different ways you are thinking of for measuring the predictiveness? I can think of a few different possibilities (such as measuring number incorrect vs measuring fraction incorrect, et cetera) but I'm wondering which variations you consider significant/troublesome/etc. --Abram On Thu, Jul 22, 2010 at 7:12 PM, David Jones davidher...@gmail.com wrote: It's certainly not as simple as you claim. First, assigning a probability is not always possible, nor is it easy. The factors in calculating that probability are unknown and are not the same for every instance. Since we do not know what combination of observations we will see, we cannot have a predefined set of probabilities, nor is it any easier to create a probability function that generates them for us. That is just as exactly what I meant by quantitatively define the predictiveness... it would be proportional to the probability. Second, if you can define a program ina way that is always simpler when it is smaller, then you can do the same thing without a program. I don't think it makes any sense to do it this way. It is not that simple. If it was, we could solve a large portion of agi easily. On Thu, Jul 22, 2010 at 3:16 PM, Matt Mahoney matmaho...@yahoo.com wrote: David Jones wrote: But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. It isn't hard. To measure predictiveness, you assign a probability to each possible outcome. If the actual outcome has probability p, you score a penalty of log(1/p) bits. To measure simplicity, use the compressed size of the code for your prediction algorithm. Then add the two scores together. That's how it is done in the Calgary challenge http://www.mailcom.com/challenge/ and in my own text compression benchmark. -- Matt Mahoney, matmaho...@yahoo.com *From:* David Jones davidher...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Thu, July 22, 2010 3:11:46 PM *Subject:* Re: [agi] Re: Huge Progress on the Core of AGI Because simpler is not better if it is less predictive. On Thu, Jul 22, 2010 at 1:21 PM, Abram Demski abramdem...@gmail.com wrote: Jim, Why more predictive *and then* simpler? --Abram On Thu, Jul 22, 2010 at 11:49 AM, David Jones davidher...@gmail.com wrote: An Update I think the following gets to the heart of general AI and what it takes to achieve it. It also provides us with evidence as to why general AI is so difficult. With this new knowledge in mind, I think I will be much more capable now of solving the problems and making it work. I've come to the conclusion lately that the best hypothesis is better because it is more predictive and then simpler than other hypotheses (in that order more predictive... then simpler). But, I am amazed at how difficult it is to quantitatively define more predictive and simpler for specific problems. This is why I have sometimes doubted the truth of the statement. In addition, the observations that the AI gets are not representative of all observations! This means that if your measure of predictiveness depends on the number of certain observations, it could make mistakes! So, the specific observations you are aware of may be unrepresentative of the predictiveness of a hypothesis relative to the truth. If you try to calculate which hypothesis is more predictive and you don't have the critical observations that would give you the right answer, you may get the wrong answer! This all depends of course on your method of calculation, which is quite elusive to define. Visual input from screenshots, for example, can be somewhat malicious. Things can move, appear, disappear or occlude each other suddenly. So, without sufficient knowledge it is hard to decide whether matches you find between such large changes are because it is the same object or a different object. This may indicate that bias and preprogrammed experience should be introduced to the AI before training. Either that or the training inputs should be carefully chosen to avoid malicious input and to make them nice for learning. This is the correspondence problem that is typical of computer vision and has never been properly solved. Such malicious input also makes it difficult to learn automatically because the AI doesn't have sufficient experience to know which changes or transformations are acceptable and which are not. It is immediately bombarded with malicious inputs. I've also realized that if a hypothesis is more explanatory, it may be better. But quantitatively defining explanatory is also elusive and truly depends on the specific problems you are applying it to because it is a heuristic. It is not a true measure of correctness. It is not loyal to the truth. More explanatory is really a heuristic that helps us find hypothesis that are more predictive. The true measure of whether a hypothesis is better is simply the most
Re: [agi] Comments On My Skepticism of Solomonoff Induction
Jim, Sorry for the short quip... I should have thought about how it would sound before sending. --Abram On Wed, Jul 21, 2010 at 4:36 PM, Jim Bromer jimbro...@gmail.com wrote: You claim that I have not checked how Solomonoff Induction is actually defined, but then don't bother mentioning how it is defined as if it would be too much of an ordeal to even begin to try. It is this kind of evasive response, along with the fact that these functions are incomputable, that make your replies so absurd. On Wed, Jul 21, 2010 at 4:01 PM, Abram Demski abramdem...@gmail.comwrote: Jim, This argument that you've got to consider recombinations *in addition to* just the programs displays the lack of mathematical understanding that I am referring to... you appear to be arguing against what you *think* solomonoff induction is, without checking how it is actually defined... --Abram On Wed, Jul 21, 2010 at 2:47 PM, Jim Bromer jimbro...@gmail.comwrote: The fundamental method of Solmonoff Induction is trans-infinite. Suppose you iterate through all possible programs, combining different programs as you go. Then you have an infinite number of possible programs which have a trans-infinite number of combinations, because each tier of combinations can then be recombined to produce a second, third, fourth,... tier of recombinations. Anyone who claims that this method is the ideal for a method of applied probability is unwise. Jim Bromer *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com/ -- Abram Demski http://lo-tho.blogspot.com/ http://groups.google.com/group/one-logic *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com/ *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com -- Abram Demski http://lo-tho.blogspot.com/ http://groups.google.com/group/one-logic --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Comments On My Skepticism of Solomonoff Induction
Jim, Aha! So you *are* a constructivist or intuitionist or finitist of some variety? This would explain the miscommunication... you appear to hold the belief that a structure needs to be computable in order to be well-defined. Is that right? If that's the case, then you're not really just arguing against Solomonoff induction in particular, you're arguing against the entrenched framework of thinking which allows it to be defined-- the so-called classical mathematics. If this is the case, then you aren't alone. --Abram On Thu, Jul 22, 2010 at 5:06 PM, Jim Bromer jimbro...@gmail.com wrote: On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.comwrote: The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? You give a precise statement of the probability in general terms, but then say that it is uncomputable. Then you ask if there is a paper that refutes it. Well, why would any serious mathematician bother to refute it since you yourself acknowledge that it is uncomputable and therefore unverifiable and therefore not a mathematical theorem that can be proven true or false? It isn't like you claimed that the mathematical statement is verifiable. It is as if you are making a statement and then ducking any responsibility for it by denying that it is even an evaluation. You honestly don't see the irregularity? My point is that the general mathematical community doesn't accept Solomonoff Induction, not that I have a paper that *refutes it,*whatever that would mean. Please give me a little more explanation why you say the fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. Why is the M in a bracket? On Wed, Jul 21, 2010 at 8:47 PM, Matt Mahoney matmaho...@yahoo.comwrote: Jim Bromer wrote: The fundamental method of Solmonoff Induction is trans-infinite. The fundamental method is that the probability of a string x is proportional to the sum of all programs M that output x weighted by 2^-|M|. That probability is dominated by the shortest program, but it is equally uncomputable either way. How does this approximation invalidate Solomonoff induction? Also, please point me to this mathematical community that you claim rejects Solomonoff induction. Can you find even one paper that refutes it? -- Matt Mahoney, matmaho...@yahoo.com -- *From:* Jim Bromer jimbro...@gmail.com *To:* agi agi@v2.listbox.com *Sent:* Wed, July 21, 2010 3:08:13 PM *Subject:* Re: [agi] Comments On My Skepticism of Solomonoff Induction I should have said, It would be unwise to claim that this method could stand as an ideal for some valid and feasible application of probability. Jim Bromer On Wed, Jul 21, 2010 at 2:47 PM, Jim Bromer jimbro...@gmail.com wrote: The fundamental method of Solmonoff Induction is trans-infinite. Suppose you iterate through all possible programs, combining different programs as you go. Then you have an infinite number of possible programs which have a trans-infinite number of combinations, because each tier of combinations can then be recombined to produce a second, third, fourth,... tier of recombinations. Anyone who claims that this method is the ideal for a method of applied probability is unwise. Jim Bromer *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com/ *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com/ *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com -- Abram Demski http://lo-tho.blogspot.com/ http://groups.google.com/group/one-logic --- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
So you must explain how a mathematical approach, wh. is all about recognizing patterns, can apply to objects wh. do not fit patterns. No, we mustn't. You must read the links we've posted or stop asking the same things again and again. The answers are all there. -- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] How do we hear music
On Thu, Jul 22, 2010 at 12:59 PM, deepakjnath deepakjn...@gmail.com wrote: Why do we listen to a song sung in different scale and yet identify it as the same song.? Does it have something to do with the fundamental way in which we store memory? Probably due to evolution? Maybe at some point prior to words pitch was used in some variation. You (an astrolopithicus etc, the spelling is f-ed up, I know) is not going to care what key you are singing Watch out for that sabertooth tiger in. If you got messed up like that, can't hear the same song in a different key, you are cancelled out in evolution. Just a guess. Mike Archbold cheers, Deepak *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com