Path: utzoo!utgpu!jarvis.csri.toronto.edu!cs.utexas.edu!usc!ucsd!ogicse!decwrl!shelby!csli!ceb
From: ceb@csli.Stanford.EDU (Charles Buckley)
Newsgroups: comp.ai
Subject: Re: Building a brain, revisited
Message-ID: <11673@csli.Stanford.EDU>
Date: 10 Jan 90 00:58:39 GMT
References: <15439@well.UUCP>
Sender: ceb@csli.Stanford.EDU (Charles Buckley)
Distribution: comp
Organization: Center for the Study of Language and Information, Stanford U.
Lines: 29
In-reply-to: nagle@well.UUCP's message of 9 Jan 90 20:47:32 GMT

In article <15439@well.UUCP> nagle@well.UUCP (John Nagle) writes:

	We have the semiconductor technology to build a brain.

        [deleted: back-of-editor-buffer calculations describing a
         hypercube topology machine producing equivalent bit throughput, 
         based on a new "SuperChip" part from Motorola, which comes
         out to be of manageable, albeit ambitious size]

	 Agreed that we have no idea how to program such a piece of
         machinery to be intelligent.  But it could be built today.

I think you compare apples and oranges.  Sure, the raw compute power
could be marshalled - this has been true for some time, though as you
point out, it's getting to be within the scope of a realistic (?)
research initiative (;^/.

Brains do things that hypercubes don't though, which is learn, and
that learning is reflected in the topology.  Further, there's a
non-binary (analog) aspect to the information transmitted.

Might be interesting to redo the calculation including NN architecture
(such as those being developed at Bell Labs) and/or analog modules
(no-one is interested for these at the moment, so far I know).
NN-stuff doesn't adequately provide for the representation of time,
though, so you'd have to keep some TM aspects, and how it is organized?

Topology changes as a product of learning?  Seems quite open to me,
but I'd like to hear of efforts in this area.