RE: [agi] Cosmodelia's posts: Music and Artificial Intelligence;Jane;
Spirit isn't emergent, and isn't everywhere, and isn't a figment of the imagination, and isn't supernatural. Spirit refers to a real thing, with a real explanation; it's just that the explanation is very, very difficult. -- Eliezer S. Yudkowsky http://singinst.org/ Well I think spirit is partially emergent... And I'm not sure it's difficult to explain *in itself* -- in some ways it's very simple However, I agree that the explanation for how spirit connects with intelligence appears to be very difficult. And I would also venture this: Experimenting with AGI's -- and with human neuromodification -- is going to teach us a LOT about this thing we call spirit ;-) !! Ben G --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] An Artificial General Intelligence in the Making
Title: Message Mapping NL into logical format is very hard; the hard part is not choosing the textual representation of the logic, the hard part is have the computer program understand the natural language in the first place!!! Yeah, I do have some ideas on how this could be accomplished, but they involve building a whole AGI and then teaching it language ;-) In fact, I plan to use a variant of KNOW to help teach Novamente English... by saying the same things to it in KNOW and English in parallel, one can help it learn the semantic mappings of simple English sentences. ben The KNOW document Ben posted a link too says: "Syntax to semantics mapping in the natural language module, in which the final result should be represented in this language;" This kind of capabilities would certainly be a huge advance over something like ARFF. If anyone works with ARFF, could he or she comment on the possibilities of such translation with the ARFF grammar? Does anyone who's familiar with the technical workings of knowledge representation language have any idea on how this kind of mapping could be accomplished? -Daniel *Daniel ColonneseComputer Science Dept. NCSU2718 Clark StreetRaleigh NC 27670Voice: (919) 451-3141Fax: (775) 361-4495http://www4.ncsu.edu:8030/~dcolonn/* -Original Message-From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Gus ConstanSent: Sunday, February 02, 2003 8:12 PMTo: [EMAIL PROTECTED]Subject: RE: [agi] An Artificial General Intelligence in the Making Hi Ben; Would you kindly provide a valid url for Knowledge Representation for Inference in your reference document www.goertzel.org/papers/KNOWSpecification.htm thanks Gus
RE: [agi] KNOW
Title: Message Thanks Pei. Post a link to your paper if possible. Do you think you lose anything when you go from a"predicate logic" system to a "subject-copula-predicate"? Specificallyit seems like it would bedifficult ( maybe impossible )to representconcepts of relevance and evidence as a acyclical graph. Is this anything like thedifference between axiom inference systems andnatural deduction systems? -Daniel -Original Message-From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Pei WangSent: Monday, February 03, 2003 9:34 AMTo: [EMAIL PROTECTED]Subject: [agi] KNOW Hi, The basic difference between KNOW and existing formal languages used for knowledge representation is that KNOWbelongs toa "term logic", while the others belong to "predicate logic". Atomic sentences in term logic have the format "subject-copula-predicate", while sentences in predicate logic have the format "predicate(arguments)". These two types of language are not equivalent at the level of object-language. The detailed comparison of the twois a long story. I'm working on a paper for it, and here is a brief summary: The term logic framework as the following advantages over thepredicate logicframework: \item Its syntactic structure is closer to that of a natural language.\item It is easier to represent various types of uncertainty in a uniform.\item The concept of evidence can be naturally defined.\item The inference rules are simple and natural.\item The inference rules guarantee the semantic relevance among premises and conclusions.\item Multiple types of non-deductive inference can be defined and justified in a unified manner.\item Inference process is unified with other processes, such as learning and categorization. Pei - Original Message - From: Daniel Colonnese To: [EMAIL PROTECTED] Sent: Monday, February 03, 2003 9:07 AM Subject: RE: [agi] An Artificial General Intelligence in the Making For those of us who are following the KNOW thread, could somebody comment on the capabilities of KNOW beyond existing knowledge representation language such as the ARFF format for the popular WEKA system. I've input data into such a system before and while existing systems have extensive grammar for representing logical relations they have very limited capabilities for more ambiguous knowledge. The KNOW document Ben posted a link too says: "Syntax to semantics mapping in the natural language module, in which the final result should be represented in this language;" This kind of capabilities would certainly be a huge advance over something like ARFF. If anyone works with ARFF, could he or she comment on the possibilities of such translation with the ARFF grammar? Does anyone who's familiar with the technical workings of knowledge representation language have any idea on how this kind of mapping could be accomplished? -Daniel *Daniel ColonneseComputer Science Dept. NCSU2718 Clark StreetRaleigh NC 27670Voice: (919) 451-3141Fax: (775) 361-4495http://www4.ncsu.edu:8030/~dcolonn/* -Original Message-From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Gus ConstanSent: Sunday, February 02, 2003 8:12 PMTo: [EMAIL PROTECTED]Subject: RE: [agi] An Artificial General Intelligence in the Making Hi Ben; Would you kindly provide a valid url for Knowledge Representation for Inference in your reference document www.goertzel.org/papers/KNOWSpecification.htm thanks Gus
Re: [agi] KNOW
Title: Message - Original Message - From: Daniel Colonnese To: [EMAIL PROTECTED] Sent: Monday, February 03, 2003 11:57 AM Subject: RE: [agi] KNOW Thanks Pei. Post a link to your paper if possible. I'll do that whenthepaperis finished. Some of the arguments can be found in my previous publications, such as http://www.cogsci.indiana.edu/farg/peiwang/PUBLICATION/wang.abduction.ps. Do you think you lose anything when you go from a"predicate logic" system to a "subject-copula-predicate"? Specificallyit seems like it would bedifficult ( maybe impossible )to representconcepts of relevance and evidence as a acyclical graph. I believe that predicate logic is still better as a "mathematical logic", for binary deduction in a closed world where limitation on knowledge and resources can be ignored. Outside that domain, term logic is better. Is this anything like thedifference between axiom inference systems andnatural deduction systems? It is related to that, but much more. Pei -Daniel -Original Message-From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Pei WangSent: Monday, February 03, 2003 9:34 AMTo: [EMAIL PROTECTED]Subject: [agi] KNOW Hi, The basic difference between KNOW and existing formal languages used for knowledge representation is that KNOWbelongs toa "term logic", while the others belong to "predicate logic". Atomic sentences in term logic have the format "subject-copula-predicate", while sentences in predicate logic have the format "predicate(arguments)". These two types of language are not equivalent at the level of object-language. The detailed comparison of the twois a long story. I'm working on a paper for it, and here is a brief summary: The term logic framework as the following advantages over thepredicate logicframework: \item Its syntactic structure is closer to that of a natural language.\item It is easier to represent various types of uncertainty in a uniform.\item The concept of evidence can be naturally defined.\item The inference rules are simple and natural.\item The inference rules guarantee the semantic relevance among premises and conclusions.\item Multiple types of non-deductive inference can be defined and justified in a unified manner.\item Inference process is unified with other processes, such as learning and categorization. Pei - Original Message - From: Daniel Colonnese To: [EMAIL PROTECTED] Sent: Monday, February 03, 2003 9:07 AM Subject: RE: [agi] An Artificial General Intelligence in the Making For those of us who are following the KNOW thread, could somebody comment on the capabilities of KNOW beyond existing knowledge representation language such as the ARFF format for the popular WEKA system. I've input data into such a system before and while existing systems have extensive grammar for representing logical relations they have very limited capabilities for more ambiguous knowledge. The KNOW document Ben posted a link too says: "Syntax to semantics mapping in the natural language module, in which the final result should be represented in this language;" This kind of capabilities would certainly be a huge advance over something like ARFF. If anyone works with ARFF, could he or she comment on the possibilities of such translation with the ARFF grammar? Does anyone who's familiar with the technical workings of knowledge representation language have any idea on how this kind of mapping could be accomplished? -Daniel *Daniel ColonneseComputer Science Dept. NCSU2718 Clark StreetRaleigh NC 27670Voice: (919) 451-3141Fax: (775) 361-4495http://www4.ncsu.edu:8030/~dcolonn/* -Original Message-From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Gus ConstanSent: Sunday, February 02, 2003 8:12 PMTo: [EMAIL PROTECTED]Subject: RE: [agi] An Artificial General Intelligence in the Making Hi Ben; Would you kindly provide a valid url for Knowledge Representation for Inference in your reference document www.goertzel.org/papers/KNOWSpecification.htm thanks Gus
Re: [agi] An Artificial General Intelligence in the Making
Daniel, An ARFF file is just a collection of n-tuple data items where each tuple dimension has defined type information. It also has a dimension that is marked as being the class of the data item. So because it's basically just a big table of data you could in theory put any kind of information you like in there provided that you are a little creative in the encoding. However while you could do something like that with an ARFF file it probably doesn't make much sense. ARFF files carry with them the implicit assumption that the data items are more or less i.i.d. and that you suspect that there is some sort of explicit relationship between the dimensions; in particular you usually are interested in the abilty to predict the class dimension using the other dimensions. This is how Weka classifiers interpret the files. So in short: I'm sure you could jam KNOW data into an Arff file but I don't really see why doing so would make much sense. Cheers Shane Daniel Colonnese wrote: For those of us who are following the KNOW thread, could somebody comment on the capabilities of KNOW beyond existing knowledge representation language such as the ARFF format for the popular WEKA system. I've input data into such a system before and while existing systems have extensive grammar for representing logical relations they have very limited capabilities for more ambiguous knowledge. The KNOW document Ben posted a link too says: Syntax to semantics mapping in the natural language module, in which the final result should be represented in this language; This kind of capabilities would certainly be a huge advance over something like ARFF. If anyone works with ARFF, could he or she comment on the possibilities of such translation with the ARFF grammar? Does anyone who's familiar with the technical workings of knowledge representation language have any idea on how this kind of mapping could be accomplished? -Daniel --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
