[agi] Mechanical Analogy for Neural Operation!
Everyone has heard about the water analogy for electrical operation. I have a mechanical analogy for neural operation that just might be solid enough to compute at least some characteristics optimally. No, I am NOT proposing building mechanical contraptions, just using the concept to compute neuronal characteristics (or AGI formulas for learning). Suppose neurons were mechanical contraptions, that receive inputs and communicate outputs via mechanical movements. If one or more of the neurons connected to an output of a neuron, can't make sense of a given input given its other inputs, then its mechanism would physically resist the several inputs that didn't make mutual sense because its mechanism would jam, with the resistance possibly coming from some downstream neuron. This would utilize position to resolve opposing forces, e.g. one force being the observed inputs, and the other force being that they don't make sense, suggest some painful outcome, etc. In short, this would enforce the sort of equation over the present formulaic view of neurons (and AGI coding) that I have suggested in past postings may be present, and show that the math may not be all that challenging. Uncertainty would be expressed in stiffness/flexibility, computed limitations would be handled with over-running clutches, etc. Propagation of forces would come close (perfect?) to being able to identify just where in a complex network something should change to learn as efficiently as possible. Once the force concentrates at some point, it then gives, something slips or bends, to unjam the mechanism. Thus, learning is effected. Note that this suggests little difference between forward propagation and backwards propagation, though real-world wet design considerations would clearly prefer fast mechanisms for forward propagation, and compact mechanisms for backwards propagation. Epiphany or mania? Any thoughts? Steve --- 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] New KurzweilAI.net site... with my silly article sillier chatbot ;-p ;) ....
Have you guys talked to the army's artificial intelligence chat bot yet? http://sgtstar.goarmy.com/ActiveAgentUI/Welcome.aspx nothing really special other than the voice sounds really natural.. http://sgtstar.goarmy.com/ActiveAgentUI/Welcome.aspx On Thu, Jul 8, 2010 at 11:09 PM, Mike Archbold jazzbo...@gmail.com wrote: The concept of citizen science sounds great, Ben -- especially in this age. From my own perspective I feel like my ideas are good but it falls short always of the rigor of a proper scientist, so I don't have that pretense. The internet obviously helps out a lot.The plight of the solitary laborer is better than it used to be, I think, due to the availability of information/research. Mike Archbold On Mon, Jul 5, 2010 at 8:52 PM, Ben Goertzel b...@goertzel.org wrote: Check out my article on the H+ Summit http://www.kurzweilai.net/h-summit-harvard-the-rise-of-the-citizen-scientist and also the Ramona4 chatbot that Novamente LLC built for Ray Kurzweil a while back http://www.kurzweilai.net/ramona4/ramona.html It's not AGI at all; but it's pretty funny ;-) -- Ben -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC CTO, Genescient Corp Vice Chairman, Humanity+ Advisor, Singularity University and Singularity Institute External Research Professor, Xiamen University, China b...@goertzel.org “When nothing seems to help, I go look at a stonecutter hammering away at his rock, perhaps a hundred times without as much as a crack showing in it. Yet at the hundred and first blow it will split in two, and I know it was not that blow that did it, but all that had gone before.” --- 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/?; Powered by Listbox: http://www.listbox.com -- Carlos A Mejia Taking life one singularity at a time. www.Transalchemy.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] Mechanical Analogy for Neural Operation!
One tangential comment. You're still thinking linearly. Machines are linear chains of parts. Cause-and-effect thinking made flesh/metal. With organisms, however you have whole webs of parts acting more or less simultaneously. We will probably need to bring that organic thinking/framework - field vs chain thinking? - into the design of AGI machines, robots. In relation to your subject, you see, incoming information is actually analysed by the human system on multiple levels and in terms often of multiple domain associations simultaneously. And that's why we often get confused - and don't always not understand. Sometimes we do know clearly what we don't understand - what does that word [actually] mean? But sometimes we attend to a complex argument and we know it doesn't really make sense to us, but we don't know which part[s] of it don't make sense or why - and we have to patiently and gradually unravel that knot of confusion. From: Steve Richfield Sent: Monday, July 12, 2010 7:02 AM To: agi Subject: [agi] Mechanical Analogy for Neural Operation! Everyone has heard about the water analogy for electrical operation. I have a mechanical analogy for neural operation that just might be solid enough to compute at least some characteristics optimally. No, I am NOT proposing building mechanical contraptions, just using the concept to compute neuronal characteristics (or AGI formulas for learning). Suppose neurons were mechanical contraptions, that receive inputs and communicate outputs via mechanical movements. If one or more of the neurons connected to an output of a neuron, can't make sense of a given input given its other inputs, then its mechanism would physically resist the several inputs that didn't make mutual sense because its mechanism would jam, with the resistance possibly coming from some downstream neuron. This would utilize position to resolve opposing forces, e.g. one force being the observed inputs, and the other force being that they don't make sense, suggest some painful outcome, etc. In short, this would enforce the sort of equation over the present formulaic view of neurons (and AGI coding) that I have suggested in past postings may be present, and show that the math may not be all that challenging. Uncertainty would be expressed in stiffness/flexibility, computed limitations would be handled with over-running clutches, etc. Propagation of forces would come close (perfect?) to being able to identify just where in a complex network something should change to learn as efficiently as possible. Once the force concentrates at some point, it then gives, something slips or bends, to unjam the mechanism. Thus, learning is effected. Note that this suggests little difference between forward propagation and backwards propagation, though real-world wet design considerations would clearly prefer fast mechanisms for forward propagation, and compact mechanisms for backwards propagation. Epiphany or mania? Any thoughts? Steve 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] Mechanical Analogy for Neural Operation!
Steve Richfield wrote: No, I am NOT proposing building mechanical contraptions, just using the concept to compute neuronal characteristics (or AGI formulas for learning). Funny you should mention that. Ross Ashby actually built such a device in 1948 called a homeostat ( http://en.wikipedia.org/wiki/Homeostat ), a fully interconnected neural network with 4 neurons using mechanical components and vacuum tubes. Synaptic weights were implemented by motor driven water filled potentiometers in which electrodes moved through a tank to vary the electrical resistance. It implemented a type of learning algorithm in which weights were varied using a rotating switch wired randomly using the RAND book of a million random digits. He described the device in his 1960 book, Design for a Brain. -- Matt Mahoney, matmaho...@yahoo.com From: Steve Richfield steve.richfi...@gmail.com To: agi agi@v2.listbox.com Sent: Mon, July 12, 2010 2:02:20 AM Subject: [agi] Mechanical Analogy for Neural Operation! Everyone has heard about the water analogy for electrical operation. I have a mechanical analogy for neural operation that just might be solid enough to compute at least some characteristics optimally. No, I am NOT proposing building mechanical contraptions, just using the concept to compute neuronal characteristics (or AGI formulas for learning). Suppose neurons were mechanical contraptions, that receive inputs and communicate outputs via mechanical movements. If one or more of the neurons connected to an output of a neuron, can't make sense of a given input given its other inputs, then its mechanism would physically resist the several inputs that didn't make mutual sense because its mechanism would jam, with the resistance possibly coming from some downstream neuron. This would utilize position to resolve opposing forces, e.g. one force being the observed inputs, and the other force being that they don't make sense, suggest some painful outcome, etc. In short, this would enforce the sort of equation over the present formulaic view of neurons (and AGI coding) that I have suggested in past postings may be present, and show that the math may not be all that challenging. Uncertainty would be expressed in stiffness/flexibility, computed limitations would be handled with over-running clutches, etc. Propagation of forces would come close (perfect?) to being able to identify just where in a complex network something should change to learn as efficiently as possible. Once the force concentrates at some point, it then gives, something slips or bends, to unjam the mechanism. Thus, learning is effected. Note that this suggests little difference between forward propagation and backwards propagation, though real-world wet design considerations would clearly prefer fast mechanisms for forward propagation, and compact mechanisms for backwards propagation. Epiphany or mania? Any thoughts? Steve 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
[agi] Cash in on robots
http://www.moneyweek.com/investment-advice/cash-in-on-the-robot-revolution-49024.aspx?utm_source=newsletterutm_medium=emailutm_campaign=Money%2BMorning http://www.moneyweek.com/investment-advice/share-tips-five-ways-into-the-robotics-sector-49025.aspx --- 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, I tend to think of probability theory and statistics as different things. I'd agree that statistics is not enough for AGI, but in contrast I think probability theory is a pretty good foundation. Bayesianism to me provides a sound way of integrating the elegance/utility tradeoff of explanation-based reasoning into the basic fabric of the uncertainty calculus. Others advocate different sorts of uncertainty than probabilities, but so far what I've seen indicates more a lack of ability to apply probability theory than a need for a new type of uncertainty. What other methods do you favor for dealing with these things? --Abram On Sun, Jul 11, 2010 at 12:30 PM, David Jones davidher...@gmail.com wrote: Thanks Abram, I know that probability is one approach. But there are many problems with using it in actual implementations. I know a lot of people will be angered by that statement and retort with all the successes that they have had using probability. But, the truth is that you can solve the problems many ways and every way has its pros and cons. I personally believe that probability has unacceptable cons if used all by itself. It must only be used when it is the best tool for the task. I do plan to use some probability within my approach. But only when it makes sense to do so. I do not believe in completely statistical solutions or completely Bayesian machine learning alone. A good example of when I might use it is when a particular hypothesis predicts something with 70% accuracy, well it may be better than any other hypothesis we can come up with so far. So, we may use that hypothesis. But, the 30% unexplained errors should be explained if possible with the resources and algorithms available, if at all possible. This is where my method differs from statistical methods. I want to build algorithms that resolve the 30% and explain it. For many problems, there are rules and knowledge that will solve them effectively. Probability should only be used when you cannot find a more accurate solution. Basically we should use probability when we don't know the factors involved, can't find any rules to explain the phenomena or we don't have the time and resources to figure it out. So you must simply guess at the most probable event without any rules for figuring out which event is more applicable under the current circumstances. So, in summary, probability definitely has its place. I just think that explanatory reasoning and other more accurate methods should be preferred whenever possible. Regarding learning the knowledge being the bigger problem, I completely agree. That is why I think it is so important to develop machine learning that can learn by direct observation of the environment. Without that, it is practically impossible to gather the knowledge required for AGI-type applications. We can learn this knowledge by analyzing the world automatically and generally through video. My step by step approach for learning and then applying the knowledge for agi is as follows: 1) Understand and learn about the environment(through Computer Vision for now and other sensory perceptions in the future) 2) learn about your own actions and how they affect the environment 3) learn about language and how it is associated with or related to the environment. 4) learn goals from language(such as through dedicated inputs). 5) Goal pursuit 6) Other Miscellaneous capabilities as needed Dave On Sat, Jul 10, 2010 at 8:40 PM, Abram Demski abramdem...@gmail.comwrote: David, Sorry for the slow response. I agree completely about expectations vs predictions, though I wouldn't use that terminology to make the distinction (since the two terms are near-synonyms in English, and I'm not aware of any technical definitions that are common in the literature). This is why I think probability theory is necessary: to formalize this idea of expectations. I also agree that it's good to utilize previous knowledge. However, I think existing AI research has tackled this over and over; learning that knowledge is the bigger problem. --Abram *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] New KurzweilAI.net site... with my silly article sillier chatbot ;-p ;) ....
These video/rendered chatbots have huge potential and will be taken in many different directions. They are gradually over time approaching a p-zombie-esque situation. They add multi-modal communication - body/facial language/expression and prosody. So even if the text alone is not too good the simultaneous rending of the multi-channel information adds some sort of legitimacy. Though in these simple cases the bot only takes text as input so much of the communication complexity http://en.wikipedia.org/wiki/Communication_complexity is running semi half-duplex. John From: The Wizard [mailto:key.unive...@gmail.com] Sent: Monday, July 12, 2010 1:02 AM To: agi Subject: Re: [agi] New KurzweilAI.net site... with my silly article sillier chatbot ;-p ;) Have you guys talked to the army's artificial intelligence chat bot yet? http://sgtstar.goarmy.com/ActiveAgentUI/Welcome.aspx nothing really special other than the voice sounds really natural.. On Thu, Jul 8, 2010 at 11:09 PM, Mike Archbold jazzbo...@gmail.com wrote: The concept of citizen science sounds great, Ben -- especially in this age. From my own perspective I feel like my ideas are good but it falls short always of the rigor of a proper scientist, so I don't have that pretense. The internet obviously helps out a lot.The plight of the solitary laborer is better than it used to be, I think, due to the availability of information/research. Mike Archbold On Mon, Jul 5, 2010 at 8:52 PM, Ben Goertzel b...@goertzel.org wrote: Check out my article on the H+ Summit http://www.kurzweilai.net/h-summit-harvard-the-rise-of-the-citizen-scientist and also the Ramona4 chatbot that Novamente LLC built for Ray Kurzweil a while back http://www.kurzweilai.net/ramona4/ramona.html It's not AGI at all; but it's pretty funny ;-) -- Ben -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC CTO, Genescient Corp Vice Chairman, Humanity+ Advisor, Singularity University and Singularity Institute External Research Professor, Xiamen University, China b...@goertzel.org When nothing seems to help, I go look at a stonecutter hammering away at his rock, perhaps a hundred times without as much as a crack showing in it. Yet at the hundred and first blow it will split in two, and I know it was not that blow that did it, but all that had gone before. --- 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/? 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/? https://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com -- Carlos A Mejia Taking life one singularity at a time. www.Transalchemy.com agi | https://www.listbox.com/member/archive/303/=now Archives https://www.listbox.com/member/archive/rss/303/ | https://www.listbox.com/member/?; Modify 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] Mechanical Analogy for Neural Operation!
Hi, I pretty much always think of a NN as a physical device. I think the first binary computer was dreamt up with balls going through the system with ball representing 1's and 0's. The idea was written down but never built. Jamming balls that give way at a certain point is the same as using . ie When more than 6 balls jam up, the pressure is released, sending a 1 or a value 6 balls. Addition can be a little different in such systems. ie a value 6 + a value 3 = a value 9. On Sun, 2010-07-11 at 23:02 -0700, Steve Richfield wrote: Everyone has heard about the water analogy for electrical operation. I have a mechanical analogy for neural operation that just might be solid enough to compute at least some characteristics optimally. No, I am NOT proposing building mechanical contraptions, just using the concept to compute neuronal characteristics (or AGI formulas for learning). Suppose neurons were mechanical contraptions, that receive inputs and communicate outputs via mechanical movements. If one or more of the neurons connected to an output of a neuron, can't make sense of a given input given its other inputs, then its mechanism would physically resist the several inputs that didn't make mutual sense because its mechanism would jam, with the resistance possibly coming from some downstream neuron. This would utilize position to resolve opposing forces, e.g. one force being the observed inputs, and the other force being that they don't make sense, suggest some painful outcome, etc. In short, this would enforce the sort of equation over the present formulaic view of neurons (and AGI coding) that I have suggested in past postings may be present, and show that the math may not be all that challenging. Uncertainty would be expressed in stiffness/flexibility, computed limitations would be handled with over-running clutches, etc. Propagation of forces would come close (perfect?) to being able to identify just where in a complex network something should change to learn as efficiently as possible. Once the force concentrates at some point, it then gives, something slips or bends, to unjam the mechanism. Thus, learning is effected. Note that this suggests little difference between forward propagation and backwards propagation, though real-world wet design considerations would clearly prefer fast mechanisms for forward propagation, and compact mechanisms for backwards propagation. Epiphany or mania? Any thoughts? Steve 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
[agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
Hi, I'm interested in combining the simplest, most derivable operations ( eg operations that cannot be defined by other operations) for creating seed AGI's. The simplest operations combined in a multitude ways can form extremely complex patterns, but the underlying logic may be simple. I wonder if varying combinations of the smallest set of operations: { , memory (= for memory assignment), ==, (a logical way to combine them), (input, output), () brackets } can potentially learn and define everything. Assume all input is from numbers. We want the smallest set of elements, because less elements mean less combinations which mean less chance of hitting combinatorial explosion. helps for generalisation, reducing combinations. memory(=) is for hash look ups, what should one remember? What can be discarded? == This does a comparison between 2 values x == y is 1 if x and y are exactly the same. Returns 0 if they are not the same. (a logical way to combine them) Any non-narrow algorithm that reduces the raw data into a simpler state will do. Philosophically like Solomonoff Induction. This is the hardest part. What is the most optimal way of combining the above set of operations? () brackets are used to order operations. Conditionals (only if statements) + memory assignment are the only valid form of logic - ie no loops. Just repeat code if you want loops. If you think that the set above cannot define everything, then what is the smallest set of operations that can potentially define everything? -- Some proofs / Thought experiments : 1) Can , ==, (), and memory define other logical operations like (AND gate) ? I propose that x==y==1 defines xy xy x==y==1 00 = 0 0==0==1 = 0 10 = 0 1==0==1 = 0 01 = 0 0==1==1 = 0 11 = 1 1==1==1 = 1 It means can be completely defined using == therefore is not one of the smallest possible general concepts. can be potentially learnt from ==. - 2) Write a algorithm that can define 1 using only ,==, (). Multiple answers a) discrete 1 could use x == 1 b) continuous 1.0 could use this rule For those not familiar with C++, ! means not (x 0.9) !(x 1.1) expanding gives ( getting rid of ! and ) (x 0.9) == ((x 1.1) == 0) == 1note !x can be defined in terms of == like so x == 0. (b) is a generalisation, and expansion of the definition of (a) and can be scaled by changing the values 0.9 and 1.1 to fit what others would generally define as being 1. --- 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