Ben> The issue is: how might NNs effectively represent abstract
Ben> knowledge?

...

Ben> So far as I know none of the brain-emulating would-be-AGI
Ben> architectures I have seen address this issue very well.  Hawkins'
Ben> architecture, for instance, doesn't really tell you how to
Ben> represent and manipulate an abstract function with variables...

Ben> Say, a category like "people who have the property that there is
Ben> exactly one big scary thing they are afraid of."  How does the
Ben> brain represent this?  How would a useful formal neural net model
Ben> represent this?

Ben,

I'd point you to Les Valiant's book Circuits of the Mind 
for a serious attempt to answer precisely such questions.

It's been years since I read it, and my recollection is
hazy, so I won't attempt much of a summary. The book
posits units of several (hundred?) neurons called neuroids
that act as finite state machines with various properties,
and then gives algorithms by which the whole system could be programmed
to learn, for example, concepts of exactly the type you ask.



-------
To unsubscribe, change your address, or temporarily deactivate your 
subscription, 
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]

Reply via email to