PM:  Jim, Where are the pictures?  You need to visualize your "Cognitive 
Structures" 
so we can see what you mean.

Very brief statement of a revolutionary idea. The current AI view exemplified 
by Jim et al’s ideas of conceptual graphs and other structures, is that 
intelligence is essentially a matter of checking and combining boxes.

If the incoming y checks against your inner y box, you do x. If y, c, and d 
check, then you do x, b and c. You basically check and combine boxes. The 
Turing machine depends on this.

Not so. Human, real world intelligence is primarily drawing pictures – 
primarily graphic pictures. To understand a train-shaped clock, your brain 
draws the comparison. To understand “The block of concrete stopped the train”, 
your brain draws a picture and draws a conclusion.

Technically, intelligence is almost always about: “what can you draw from 
that...?”

The brain is primarily and overwhelmingly an artist, not a logician.  (Hence 
the impossibility of the present approach to Visual Object Recognition for 
anything but boxily similar objects).

Now how can we produce a drawing machine?



-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com

Reply via email to