Which exact aspect are you relying on and how are you implementing it? The main thin is the restriction on domain, all of his scripts were very limiting, IE if you used a restaurant script and anything out of the ordinary happened, it would break. It was very fragile in this fashion, and such, most all scripts were hand-created and of limited use outside the test cases.
One way I looked at fixing those deficiencies is having many similar scripts allowed, and allowing an easy way for an english user to create a basic script. James Ratcliff Mark Waser <[EMAIL PROTECTED]> wrote: :-) A lot of the reason why I was asking is because I'm effectively somewhat (how's that for a pair of conditionals? :-) relying on Schank's approach not having any showstoppers that I'm not aware of -- so if anyone else is aware of any surprise show-stopper's in his work, I'd love to have some pointers. Thanks. ----- Original Message ----- From: "Jean-Paul Van Belle" To: Sent: Tuesday, June 05, 2007 3:56 PM Subject: Re: [agi] Minimally ambiguous languages Sorry yes you're right, I should and would not call Schank's approach discredited (though he does have his critics). FWIW I think he got much closer than most of the GOFAIers i.e. he's one of my old school AI heroes :) I thought for a long time his approach was one of the quickest ways to AGI and I still think anyone studying AGI should definitely study his approach closely. In the end any would-be AGIst (?:) will have to decide whether she adopts conceptual primitives or not - probably, apart from ideological arguments, mainly on the basis of how she decides to (have her AGI) ground its/his/her concepts (or not, as the case may be). Personally I'd say that a lot of mental acts do not reduce to his primitives easily (without losing a lot in the translation, to paraphrase a good movie:) and mental acts are quite important in my AGI architecture. Just personal opinion of course. =Jean-Paul ----- 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/?&; _______________________________________ James Ratcliff - http://falazar.com Looking for something... --------------------------------- Shape Yahoo! in your own image. Join our Network Research Panel today! ----- 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
