On Thu, May 1, 2008 at 12:46 AM, Russell Wallace
<[EMAIL PROTECTED]> wrote:
>
>  *nods* So basically you propose to follow in evolution's footsteps in
>  starting with S, layering some level of D on top of it, then getting
>  the rest of the way by connecting up external devices to fill in the
>  rest of the D functionality. Fair enough.
>

Correct, except that it's inspired not so much by evolution's way, but
by a search for simple enough mechanism that would be able to achieve
required competencies in the end. If you remember my early ramblings,
I started from frame representations, and gradually worked my way
towards these networks, currently with just linear classifiers at
nodes...

-- 
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