Path: utzoo!utgpu!utstat!jarvis.csri.toronto.edu!mailrus!cs.utexas.edu!tut.cis.ohio-state.edu!pt.cs.cmu.edu!andrew.cmu.edu!ps2x+
From: ps2x+@andrew.cmu.edu (Peter John Skelly)
Newsgroups: comp.ai.neural-nets
Subject: Re: back propagation problems....
Message-ID: <sZKaRH200Xoe40l0h3@andrew.cmu.edu>
Date: 10 Nov 89 06:14:43 GMT
References: <89312.121049LAL102@PSUVM.BITNET>
Organization: Class of '91, Carnegie Mellon, Pittsburgh, PA
Lines: 7
In-Reply-To: <89312.121049LAL102@PSUVM.BITNET>

I preformed similar experiments and had similar problems with the
network forgetting previously learned data.  I was able to make it
perform differently(sometimes better, sometimes not) by changing the
transfer function.  I was at first using just a basic step function, but
better results were obtained by using a sigmoid, or a sigmoid
approximation.
-Pete Skelly