Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!linus!decvax!harpo!seismo!hao!hplabs!sri-unix!Fahlman@CMU-CS-C.ARPA
From: Fahlman@CMU-CS-C.ARPA@sri-unix.UUCP
Newsgroups: net.ai
Subject: NETL
Message-ID: <4445@sri-arpa.UUCP>
Date: Thu, 18-Aug-83 22:01:00 EDT
Article-I.D.: sri-arpa.4445
Posted: Thu Aug 18 22:01:00 1983
Date-Received: Wed, 24-Aug-83 01:22:39 EDT
Lines: 45

From:  Scott E. Fahlman <Fahlman@CMU-CS-C.ARPA>


I've only got time for a very quick response to Alan Glasser's query 
about NETL.  Since the book was published we have done the following:

1. Our group at CMU has developed several design sketches for
practical NETL machine implementations of about a million porcessing
elements.  We haven't built one yet, for reasons described below.

2. David B. McDonald has done a Ph.D.thesis on noun group
understanding (things like "glass wine glass") using a NETL-type
network to hold the necessary world knowledge.  (This is available as
a CMU Tech Report.)

3. David Touretzky has done a through logical analysis of NETL-style 
inheritance with exceptions, and is currently writing up his thesis on
this topic.

4. I have been studying the fundamental strengths and limitations of 
NETL-like marker-passing compared to other kinds of massively parallel
computation.  This has gradually led me to prefer an architecture that
passes numers or continuous values to the single-bit marker-passing of
NETL.

For the past couple of years, I've been putting most of my time into
the Common Lisp effort -- a brief foray into tool building that got
out of hand -- and this has delayed any plans to begin work on a NETL
machine.  Now that our Common Lisp is nearly finished, I can think
again about starting a hardware project, but something more exciting
than NETL has come along: the Boltzmann Machine architecture that I am
working on with Geoff Hinton of CMU and Terry Sejnowski of
Johns-Hopkins.  We will be presenting a paper on this at AAAI.

Very briefly, the Boltzmann machine is a massively parallel
architecture in which each piece of knowledge is distributed over many
units, unlike NETL in which concepts are associated with particular
pieces of hardware.  If we can make it work, this has interesting
implications for reliable large-scale implementation, and it is also a
much more plausible model for neural processing than is something like
NETL.

So that's what has happened to NETL.

-- Scott Fahlman (FAHLMAN@CMU-CS-C)