From: John Young <jya@pipeline.com>
To: cypherpunks@toad.com
Message Hash: 9140ffc3f0384f4ff84b52a84e2a4c1b7b5576fe814870612e3b94c4dcc62e73
Message ID: <199511102323.SAA06186@pipe2.nyc.pipeline.com>
Reply To: N/A
UTC Datetime: 1995-11-10 23:54:53 UTC
Raw Date: Sat, 11 Nov 1995 07:54:53 +0800
From: John Young <jya@pipeline.com>
Date: Sat, 11 Nov 1995 07:54:53 +0800
To: cypherpunks@toad.com
Subject: Re: coding and nnet's
Message-ID: <199511102323.SAA06186@pipe2.nyc.pipeline.com>
MIME-Version: 1.0
Content-Type: text/plain
Bruce Schneier comments:
Neural Networks
Neural nets aren't terribly useful for cryptanalysis,
primarily because of the shape of the solution space.
Neural nets work best with problems that have a continuity
of solutions, some better than others. This allows a neural
net to learn, proposing better and better solutions as it
does. Breaking an algorithm provides for very little in the
way of learning opportunities: You either recover the key
or you don't. (At least this is true if the algorithm is
any good.) Neural nets work well in structured environments
where there is something to learn, but not in the
high-entropy, seemingly random world of cryptography.
"Applied Cryptography," second edition, 1996, p. 155.
Return to November 1995
Return to “John Young <jya@pipeline.com>”
1995-11-10 (Sat, 11 Nov 1995 07:54:53 +0800) - Re: coding and nnet’s - John Young <jya@pipeline.com>