On 7/2/07, Vladimir Nesov <[EMAIL PROTECTED]> wrote:
Btw, this analogy just came to me: there's this AGISim thing going for Novamente. Are all meaningful concepts created within the system and utilized for its reasoning have each been manually provided be teacher as atomic tags? Or it just has a bunch of modality-provided tags, like 'left', 'right', 'big', 'box' and comes up by itself with complex situation concepts (like 'fetch'), subsequently used as atomic entities in multiple situations?
This is a question for Ben. In NARS, all atomic concepts are initially tagged by the teacher with English words, though their internal meanings are not exactly the same as what they mean to human speakers of English. System-generated concepts are tagged as structures of simpler concepts, though their meaning will gradually become independent.
Teching anything complex looks difficult without a language (character-based or otherwise) - no way to describe reasoning, hence it must learn much all by itself...
Indeed. Most people will agree that some kind of "language" is necessary for AGI, though there is little consensus on its exact form. Pei ----- 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=231415&user_secret=e9e40a7e
