From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!uunet!snorkelwacker.mit.edu!news.media.mit.edu!minsky Tue May 12 15:50:01 EDT 1992
Article 5515 of comp.ai.philosophy:
Newsgroups: comp.ai.philosophy
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!uunet!snorkelwacker.mit.edu!news.media.mit.edu!minsky
>From: minsky@media.mit.edu (Marvin Minsky)
Subject: Re: penrose
Message-ID: <1992May9.151203.6209@news.media.mit.edu>
Sender: news@news.media.mit.edu (USENET News System)
Cc: minsky
Organization: MIT Media Laboratory
References: <1992May1.025230.8835@news.media.mit.edu> <1992May6.220605.26774@unixg.ubc.ca> <zlsiida.197@fs1.mcc.ac.uk>
Date: Sat, 9 May 1992 15:12:03 GMT
Lines: 13

In article <zlsiida.197@fs1.mcc.ac.uk> zlsiida@fs1.mcc.ac.uk (dave budd) writes:
>Is there an easy-to-follow proof that any neural net can be equivalenced to 
>a Turing machine?

Depends of what you accept as a neural net.  Otherwise, here's a
simple proof:

  1. Simulate the neural net on a digital computer.
  2. Simulate that computer on a Turing machine.

Of course, the reverse may not hold, so we can't argue "equivalence".

.


