On 12/8/06, Bob Mottram <[EMAIL PROTECTED]> wrote:

Hinton basically seems to be using the same kind of architecture as Edelman,
in that you have both bottom-up and top-down streams of information (or I
often just call this feed-forward and feed-back to keep the terminology more
consistent with other stuff), with multiple sensory heirachies being
integrated using a bidirectional associative method similar to the idea of
re-entry.  To some extent the system isn't just passively observing the
environment but is also trying to impose order upon its observations from
the top down (the feed-forward part).

I tried and tried but never figured out what Edelman meant by "re-entry".
Can somebody explain it?

-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?list_id=303

Reply via email to