> > But, as for specific places where I think that Novamente needs to fill in > the gaps ASAP to have a credible plan, I've already mentioned several -- > "scale-invariance > of knowledge, ways of determining and exploiting encapsulation and > modularity of knowledge without killing useful "leaky" abstractions, etc." > and a serious review of the "memory" design. >
I am extremely confident of Novamente's memory design regarding declarative and procedural knowledge. Tweaking the system for optimal representation of episodic knowledge may require some more thought. I have no idea what you mean by "scale invariance of knowledge" nor and only weak understanding of what you mean by "ways of determining and exploiting encapsulation and modularity of knowledge without killing useful "leaky" abstractions." In terms of determining modularity of knowledge, NM seeks to do this via various mechanisms, e.g. -- pattern-mining using PLN, MOSES and clustering on the AtomTable, to identify modularity of declarative knowledge within the existing knowledge base -- some specific program-tree-reduction heuristics to identify modularity w/in populations of program trees ... i.e. mechanisms which focus on procedural knowledge Exploiting modularity of knowledge once it's identified is easier, because modules once recognized may be explicitly represented as Atoms in the AtomTable and as Combo nodes w/ in Combo program trees. If you could give some specific examples of knowledge modules that concern you, this discussion might be more useful. -- 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/?member_id=8660244&id_secret=64167305-8145a8
