Re: A Mind Ontology Project? [Re: [agi] method for joining efforts]
YKY, it looks like you removed the G0 page. Is this proprietary now too?http://www.geocities.com/genericai/-- Matt Mahoney, [EMAIL PROTECTED]- Original Message From: YKY (Yan King Yin) [EMAIL PROTECTED]To: agi@v2.listbox.comSent: Monday, October 16, 2006 9:37:23 PMSubject: Re: A Mind Ontology Project? [Re: [agi] method for joining efforts] Re the Mind Ontology page: I have written a "glossary of terms" pertinent to our discussions, including Ben's suggestion of the terms: -- perception -- emergence -- symbol grounding -- logic and I also added many of the terms in my architecture (which is not meant to be final, only as aproposal forfurther discussion). I find no use of "emergence" so I left it undefined =P I suggest thatweb page's content should be proprietary to Novamente, because it contains some of myideas of G0 in it. [I'd be happy to let Ben use all these ideas perhaps in exchange of a small amount of Novamente shares. Anyway, many of my ideas came from discussions with Ben and members of this list.] Secondly, I'm not sure what the "ontology" is supposed to mean except as a clarification of terms. If so I guess a few web pages would suffice for this purpose. Thirdly -- an important point -- I think Ben should focus on dividing the architecture into modules that can be researched and developed(relatively) independently. This is very important because even if Ben's brain has ideas that are better than each of our brains', his ideas will not be better than all ofours combined. So it would be a tremendous step forward if we could decide on a broad way of separating the modules. This I will propose on the page. Personally, I wish to specialize on pattern recognition and perhaps vision (since Ben is also doing some vision). YKY This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED] This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
[agi] Lojban++
That's right... I need to update the AGIRI site to reflect the replacement of Loglish with Lojban++, which is a better thought out proposal along the same conceptual linesSee the document http://www.goertzel.org/papers/lojbanplusplus.pdffor information on the Lojban++ project, which I think is a very sound one that would benefit AGI projects across the board...-- Ben G On 10/16/06, Brandon Reinhart [EMAIL PROTECTED] wrote: I imagine so, although the project proposals haven't been updated to reflect this. Ben can provide more clarity. Brandon From: Josh Treadwell [mailto:[EMAIL PROTECTED]] Sent: Monday, October 16, 2006 6:08 PM To: agi@v2.listbox.com Subject: Re: A Mind Ontology Project? [Re: [agi] method for joining efforts] The second project that hasn't started yet is the Loglish language parser project. The goal of this project would be to build a richly featured parser library for Loglish, a composite-language of Lojban and English designed by Dr. Goertzel. (More information on Loglish here: http://www.agiri.org/forum/index.php?showtopic=125 ) This project requires a lot of specific domain knowledge: parser generators, computational linguistics, formal logic, etc. Is this referring to Ben's lojban++ or loglish? I wasn't sure if there was a difference. It seems lojban++ is an update to his loglish proposition: http://www.goertzel.org/papers/lojbanplusplus.pdf -- Josh Treadwell This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED] This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED] -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: A Mind Ontology Project? [Re: [agi] method for joining efforts]
Hi,sary of terms pertinent to our discussions, including Ben's suggestion of the terms: -- perception -- emergence -- symbol grounding -- logicOf course, those were just four terms selected at random and not intended as terms having any special role in the ontology of mind...I remain psyched about the idea of building a Mind Ontology and presenting it in wiki format, but may not have time to actually get the ontology started for a few more weeks. I suggest thatweb page's content should be proprietary to Novamente, because it contains some of myideas of G0 in it. [I'd be happy to let Ben use all these ideas perhaps in exchange of a small amount of Novamente shares. Anyway, many of my ideas came from discussions with Ben and members of this list.] Well, the idea of a Mind Ontology wiki online is definitely **not** tied to any motivations of proprietariness!!! The Mind Ontology wiki is intended to be a public resource and a collective pursuit If I want to keep ideas secret, then I will not publish those ideas on a wiki or anywhere else!! (As an example, the high level overview of the Novamente AI design has been published, but the details have not been published, intentionally). Secondly, I'm not sure what the ontology is supposed to mean except as a clarification of terms. If so I guess a few web pages would suffice for this purpose. When I get time to start building the Mind Ontology, I will also write some brief text explaining the purpose.An ontology is more than just a clarification of terms, it also represents a whole bunch of specific decisions regarding how to analyze a given domain of knowledge (in this case a whole bunch of intersecting domains of knowledge). There are a lot of ways to chop a body of knowledge and thought into pieces, and how you decide to do it is important in terms of how prior and future thinking regarding that body of knowledge is directed and structured... Thirdly -- an important point -- I think Ben should focus on dividing the architecture into modules that can be researched and developed(relatively) independently. This is very important because even if Ben's brain has ideas that are better than each of our brains', his ideas will not be better than all ofours combined. So it would be a tremendous step forward if we could decide on a broad way of separating the modules. This I will propose on the page. Personally, I wish to specialize on pattern recognition and perhaps vision (since Ben is also doing some vision). Modularization of AI architecture is a different topic than Mind Ontology, though of course closely related The Mind Ontology I seed will contain implicit within it some ideas about how to modularize AI architecture... But of course, the degree to which an AI architecture can be divided into modules in practice (rather than conceptually) depends on a whole lot of pragmatic issues, as well as on cognitive theory Novamente is modular only in a limited sense: it does divide into modules, but the requirements for an algorithm to be plugged into to Novamente as a module are fairly specific, it's not as though we could just plug in any good vision algorithm as an NM vision module, for example... One of the goals of the Mind Ontology, of course, is to provide a common basis for discussion within which this sort of discussion can perhaps be carried out more clearly...ben This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Interesting Resources
Mark, Yes I am attending UT, and the NERO project is very interresting, there is a large storyboard in the hall with pictures of the virtual world of combat and going through and explaining a lot about the system. The graphical Vr is downloadable as well where you can test it out.James RatcliffMark Waser [EMAIL PROTECTED] wrote:I just ran across the following references in Neuro-Evolution (including evolving topologies in neural networks) and figured that they might be interesting to others on this list: http://nn.cs.utexas.edu/project-view.php?RECORD_KEY(Projects)=ProjIDProjID(Projects)=14 http://www.cs.ucf.edu/~kstanley/ http://nerogame.org/ Mark This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED] Thank YouJames Ratcliffhttp://falazar.com All-new Yahoo! Mail - Fire up a more powerful email and get things done faster. This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] G0 theory completed
Both of these issues can be augmented and assited greatly just using some simple statistical learning as well. For the Ball kicks Boy example you can easily scan through a collection of books and extract a generalization of Person kicks Object, or Animal kicks Object as a template for the action, and question the user or input if you see something off like Ball kicks Boy. This really gives you alot more control than you would have otherwise, and structures a large amount of the information given. This with a good ability to oversee and correct the system would allow it to learn ALOT of information very rapidly, and with increasing correctness. Cyc goes a bit too far off the deep end Im afraid, with trying to hand encode every bit of knowledge, and they have begun work to extract it from text, and use assisted learning for better benefit. You cannot get all common sense knowledge this way, and there are many things that it wont do, but much of human information is stored in simple, easy to use phrases For example, just viewing the usage of "cabbage" and "cabbage patch kid" would quickly lead an AI like this to the fact that one is a vegetable, and one is a doll/toy. One of the most major components I see missing, and necessary for any AGI, is a complex and suffecient teaching mechanism. Something akin to a child, where you can hold their hand, and explain things to them, simply and by example and without devolving into a machine language.James RatlciffI think there is no shortcut to knowledge acquisition. Doug Lanet has argued that much of common sense knowledge is missing fromthe internet. For example a Google search of "water flowing downhill" returns 987 hits versus 1480 hits for "water flowing uphill". He argued that adult speech assumes common sense knowledge andthus is a badsource of common sense. There are multiple reasons why Cyc is not yet successful -- lack of sensory input (vision),not good enough to converse innatural language, inference engine not advanced enough, no probabilities or fuzzy logic, etc. It's like the failure ofearly gliders to fly,which doesn'tmean thatflying with planes is impossible.YKYMatt Mahoney [EMAIL PROTECTED] wrote: First order logic is powerful, but that does not mean it is correct. I think it is an oversimplification, and we are discarding something essential for the sake of computational efficiency. The fact that you can represent Kicks(x,y) means that you can represent nonsense statements like "ball kicks boy". This is not how people think. A person reading such a statement will probably reverse the order of the words because it makes more sense that way. How would a symbolic system do that?- Original Message From: YKY (Yan King Yin) [EMAIL PROTECTED]To: agi@v2.listbox.comSent: Monday, October 9, 2006 2:23:59 PMSubject: Re: [agi] G0 theory completedMatt: (Sorry about the delay... I was busy advertising in other groups..) But now that you have completed your theory on how to build AGI, what do you do next?Which parts will you write yourself and which parts will you contract out? Ideally, any part that can be "out-sourced" should be out-sourced. At this stage let's see who are interested in this approach...? I still think there are still some fundamental problems to be solved.Your system is based on first order logic.(You said that is not a fixed design feature, but without a data structure you don't have a design).I am not aware of any system that has successfully integrated FOL (or its augmented variants) with sensory/motor data or language. For sensory processing, I think the main reason is that FOL is not probabilistic. We need to combine probability with FOL, which is not that hard. A Bayesian networkcan be viewed as propositional logic + probability. For natural language, perhaps the reason is thatthey have only focused on inference and ignoredpattern recognition, which, as I argued, is the basis ofdealing withthe semantics of words. All such systems require human programmers to explicity encode knowledge.You have many examples of how various types of knowledge can be represented.Books and papers on knowledge representation are full of similar examples.What these examples all lack is an explicit algorithm for acquiring such knowledge.Sure, humans can do it easily, but if you make your learning mechanism this smart, then you have already solved AGI.If it took anything less than human knowledge to do it, then surely systems like Cyc would have been built this way.Why spend 20 years hand coding millions of rules instead of a few days crunching a terabyte of text off the Internet? I think there is no shortcut to knowledge acquisition. Doug Lanet has argued that much of common sense knowledge is missing fromthe internet. For example a Google search of "water flowing downhill" returns 987 hits versus 1480 hits for "water flowing uphill". He argued that adult speech assumes common sense knowledge andthus is a badsource of common
