Charles D. Hixsons post of 10/8/2007 5:50 PM, was quite impressive as a first reaction upon reading about NARS.
After I first read Pei Wangs A Logic of Categorization, it took me quite a while to know what I thought of it. It was not until I got answers to some of my basic questions from Pei though postings under the current thread title that I was able to start to understand it reasonably well. Since then I have been coming to understand that it is quite similar to some of my own previous thinking, and if it were used in a certain way, it would seem to have tremendous potential. But I still have some questions about it, such as (PEI, IF YOU ARE READING THIS I WOULD BE INTERESTED IN HEARING YOUR ANSWERS) --(1) How are episodes represented in NARS? --(2) How are complex pattern and sets of patterns with many interrelated elements represented in NARS? (I.e., how would NARS represents an auto mechanics understanding of automobiles? Would it be in terms of many thousands of sentences containing relational inheritance statements such as those shown on page 197 of A Logic of Categorization?) --(3) How are time and temporal patterns represented? --(4) How are specific mappings between the elements of a pattern and what they map to represented in NARS? --(5) How does NARS learn behaviors? --(6) Finally, this is a much larger question. Is it really optimal to limit your representational scheme to a language in which all sentences are based on the inheritance relation? With regard to Question (6): Categorization is essential. I dont question that. I believe the pattern is the essential source of intelligence. It is essential to implication and reasoning from experiences. NARSs categorization relates to patterns and relationships between patterns. It patterns are represented in a generalization hierarchy (where a property or set of properties can be viewed as a generalization), with a higher level pattern (i.e., category) being able to represent different species of itself in the different contexts where those different species are appropriate, thus, helping to solve two of the major problems in AI, that of non-literal matching and context appropriateness. All this is well and good. But without having had a chance to fully consider the subject it seems to me that there might be other aspects of reality and representation that -- even if they might all be reducible to representation in terms of categorization -- could perhaps be more easily thought of by us poor humans in terms of concepts other than categorization. For example, Novamente bases its inference and much of its learning on PTL, Probabilistic Term Logic, which is based on inheritance relations, much as is NARS. But both of Bens articles on Novamente spend a lot of time describing things in terms like hypergraph, maps, attractors, logical unification, PredicateNodes, genetic programming, and associative links. Yes, perhaps all these things could be thought of as categories, inheritance statements, and things derived from them of the type described in you paper A Logic of Catagorization, and such thoughts might provide valuable insights, but is that the most efficient way for us mortals to think of them and for a machine to represent them. I would be interested in hearing your answer to all these questions. ----- 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/?member_id=8660244&id_secret=51300772-e34770
