Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!cs.utexas.edu!ut-emx!walt.cc.utexas.edu!rohit
From: rohit@walt.cc.utexas.edu (rohit vidwans)
Newsgroups: comp.ai.neural-nets
Subject: learning a step function using back propogation
Keywords: back propogation learning
Message-ID: <16671@ut-emx.UUCP>
Date: 6 Aug 89 23:09:39 GMT
Sender: news@ut-emx.UUCP
Reply-To: rohit@walt.cc.utexas.edu (rohit vidwans)
Distribution: usa
Organization: The University of Texas at Austin, Austin, Texas
Lines: 15

Hi,
I am trying to teach a network to accept as input a step function
and return as output the same step function or a scaled version of the
same. I have tried single and multiple inputs and outputs with
multiple hidden layers for my network..but am having no luck 
whatsoever...I am using back propogation learning and my hidden
layers use the sigmoidal function.

if anybody has any suggestions to make please post reply on net
or send mail to above address.

Neural Network Group
Chemical Engineering Department
University of Texas at Austin