The idea that I might write the program to actually look for a
context-free grammar and to look for context-sensitive grammars is
really interesting.  Of course, I have thought about this implicitly
without making a clear definition of the kinds of grammars that the
program would look for, or even that they would be looking for
grammars, but by looking at this under such sharp illumination I am
really starting to wonder about the range of the potential.  There is
no question in my mind that I will be able to achieve my primary goal:
create a simple AGI program that would learn a very simple language
that would help it to make inferences and to integrate different types
of information in ways that goes beyond the contemporary AGI programs.
(It would not be able to learn much about chess or to learn to play
Jeopardy but it would solve the problem of conceptual integration in
new ways.)
-- 
Jim Bromer


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to