On Thursday 04 October 2007 10:56:59 am, Edward W. Porter wrote: > You appear to know more on the subject of current analogy drawing research > than me. So could you please explain to me what are the major current > problems people are having in trying figure out how to draw analogies > using a structure mapping approach that has a mechanism for coordinating > similarity slippage, an approach somewhat similar to Hofstadter approach > in Copycat? > Lets say we want a system that could draw analogies in real time when > generating natural language output at the level people can, assuming there > is some roughly semantic-net like representation of world knowledge, and > lets say we have roughly brain level hardware, what ever that is. What > are the current major problems?
The big problem is that structure mapping is brittlely dependent on representation, as Hofstadter complains; but that the FARG school hasn't really come up with a generative theory (every Copycat-like analogizer requires a pile of human-written Codelets which increases linearly with the knowledge base -- and thus there is a real problem building a Copycat that can learn its concepts). In my humble opinion, of course. Josh ----- 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=50021664-0a9ddc
