Hi I have slightly updated my AGI design page: http://www.geocities.com/GenericAI/Intro.htm
The basic ideas remain the same, in short, separation of knowledge from behavior, use of a 4D representation of space-time, and recursive application of compression based on local feature extraction (dictionaries). I think one problem that may have plagued traditional AI is that it is usually based on a calculus (such as symbolic logic) and tries to solve problems by performing searches in the algorithmic space defined by that calculus. As a result of this, there is a gap between the sensorium and the more abstract calculus. This can actually be traced back to Leibniz who invented logic in order to characterize *abstract* thought. I'm still trying to see if my compression-based AGI is feasible. I think the first experiment would be to implement a kind of "generic memory" that can store arbitrary items. Just wondering if other groups may be interested in using this module in their AGI... YKY ____________________________________________________________ Find what you are looking for with the Lycos Yellow Pages http://r.lycos.com/r/yp_emailfooter/http://yellowpages.lycos.com/default.asp?SRC=lycos10 ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
