From: J.Andrew Rogers <[EMAIL PROTECTED]>
>> I think (as Ben pointed out also) one of the major challenges in
>> AGI is to teach it to learn complex cognitive *procedures* (versus
>> learning of static *concepts* which is a well established area).
>
>
>A distinction with only a minor difference. How is a "procedure"
>different from "static concept" from a theoretical standpoint?
That's a very good point, and may have profound implications. I'm
mostly studying neural networks and the bad thing about them is
that time is treated as an aspect distinct from data, so it
somewhat clouded my thinking =/
Time can be treated just like another spatial dimension, with the
special property that correlation should be detected in only one
direction (ie the direction of time, and thus causality).
For example, in the sequence:
{ drank coffee, couldn't sleep, drank coffee the next day, ... }
Only the correlation between the first 2 items should be detected.
But even this may be redundant, as the concept of causality *itself*
can be defined as such a correlation, totally removing the need
for special considerations.
AGI = pattern recognition.
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]
