On Wed, Apr 30, 2008 at 7:36 PM, Russell Wallace
<[EMAIL PROTECTED]> wrote:
>
>  This isn't at all obvious to me, I have to admit! (Assuming we're
>  talking in a practically useful sense, not recapping something like
>  "logic gates are a special case of neurons".) Certainly biology had a
>  long hard job going from S to D, and human engineers haven't had much
>  success with it yet. I'd be very interested in how you propose to do
>  it?
>

Deliberative reasoning can be expressed as processing performed by an
inference circuit, a network that propagates activation and calculates
the result using logic gates. Particular deliberative algorithms can
be programmed into circuit's structure or external memory-environment
with which it interacts. 'Spacial', or pattern-recognizing processing
consists in selecting combinations of inputs on which to respond, or
in the same setting in 'gates' propagating activation only when a
particular pattern is recognized. This in special cases corresponds to
logic gates, when patterns describe crisp enough categories. The
integration between two modes is in figuring out how the process of
pattern-learning can build robust 'logic' circuits, and conversely how
'logic' circuits can be robust enough to be adaptive.

-- 
Vladimir Nesov
[EMAIL PROTECTED]

-------------------------------------------
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
http://www.listbox.com/member/?member_id=8660244&id_secret=101455710-f059c4
Powered by Listbox: http://www.listbox.com

Reply via email to