Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!linus!decvax!harpo!floyd!clyde!ihnp4!zehntel!hplabs!sri-unix!SOO@RUTGERS.ARPA
From: SOO@RUTGERS.ARPA@sri-unix.UUCP
Newsgroups: net.ai
Subject: Top-Down? Bottom-Up?
Message-ID: <12282@sri-arpa.UUCP>
Date: Thu, 29-Sep-83 14:14:29 EDT
Article-I.D.: sri-arpa.12282
Posted: Thu Sep 29 14:14:29 1983
Date-Received: Thu, 6-Oct-83 04:33:15 EDT
Lines: 18

us, and try to determine what are natural subsystems into which
we can decompose a system that performs in the specified way.  I would argue
that progress in brain theory will depend on the cyclic interaction of these
two methodologies. ..."


"  The top-down approach complement bottom-up studies, for one cannot simply
wait until one knows all the neurons are and how they are connected to then
simulate the complete system. ..."

I believe that the similar philosophy applies to the machine learning study
too.

For those interested, the paper can be found in COINS techical report 81-31
by M. A. Arbib "A View of Brain Theory"


Von-Wun,