On Feb 4, 2008 7:38 PM, Bob Mottram <[EMAIL PROTECTED]> wrote: > Well if you take something like the "talking heads" experiment > (http://www.isrl.uiuc.edu/~amag/langev/cited2/steelsthetalkingheadsexperiment.html) > and ask what it would take to scale this up to human-like language > abilities inevitably you're always drawn back to the fact that the > images used are of a trivial nature.
Perhaps. However, I think there's at least as much work required to take a robot (with localisation + mapping if you like) and scale it up to communicate with human-like language. > There needs to be some kind of reliable pattern which you can > correlate your linguistics with. Uncertainties can be dealt with, but > if the pattern is completely unreliable from one observation to the > next you're lost. Simulation doesn't really deal with the problem, or > rather it deals with the problem by ignoring it. This is a very good point. Reliable patterns are important and dealing with uncertainty in your patterns is critical to real-world situations. That said though, it might be possible to make AGI without a decent ability to deal with uncertainty then program that in later. Its hard to tell. What do you guys think? -J ----- 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=93353273-22cd00
