Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!wuarchive!gem.mps.ohio-state.edu!uakari.primate.wisc.edu!aplcen!boingo.med.jhu.edu!dave
From: dave@boingo.med.jhu.edu (David Heath)
Newsgroups: comp.ai.neural-nets
Subject: Minimum # of internal nodes to form boolean function
Message-ID: <1989Oct12.050402.9790@boingo.med.jhu.edu>
Date: 12 Oct 89 05:04:02 GMT
Reply-To: heath@cs.jhu.edu (David Heath)
Distribution: usa
Organization: The Johns Hopkins Hospital-Body CT Imaging Lab, Baltimore
Lines: 10


  I've been told that Robert Heicht Neilson recently proved that any
boolean function of n inputs to n outputs can be realized with a neural
net having n input nodes, n output nodes and 2n-1 intermediate nodes
(a total of 3 layers). Is there any truth to this statement? Please
forgive me if this has been discussed here before.


--------------------------------
Dave Heath	heath@cs.jhu.edu