Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!cs.utexas.edu!uunet!mcvax!unido!cosmo!jochenru@cosmo.UUCP
From: jochenru@cosmo.UUCP (Jochen Ruhland)
Newsgroups: comp.ai.neural-nets
Subject: 3-Layer versus Multi-Layer
Message-ID: <3417@cosmo.UUCP>
Date: 20 Jun 89 01:19:09 GMT
Sender: jochenru@cosmo.UUCP
Reply-To: jochenru@cosmo.UUCP (Jochen Ruhland)
Organization: CosmoNet, D-3000 Hannover 1, FRG
Lines: 9

During a local meeting here in Germany I heard somebody talking
about a theorem that a three layer perceptron is capable to
perform any given In/Out function with an maximum number of hidden
units in the network.
I forgot to ask where to look for the proof - so I'm asking here.
Response may be in german or english.

Thanks in advance
       Jochen