Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!wuarchive!uunet!aplcen!unmvax!ariel.unm.edu!wayback.unm.edu!bill
From: bill@wayback.unm.edu (william horne)
Newsgroups: comp.ai.neural-nets
Subject: Re: Input scaling alters my results; why?
Message-ID: <1990Aug13.181137.27405@ariel.unm.edu>
Date: 13 Aug 90 18:11:37 GMT
References: <473@array.UUCP>
Sender: usenet@ariel.unm.edu (USENET News System)
Organization: University of New Mexico, Albuquerque
Lines: 19

In article <473@array.UUCP> ling@array.UUCP (Ling Guan) writes:
>I am currently using NN to do recognition of objects in
>xray images. The NN I use is a standard backpropagation net with
>cumulative generalized delta training rule. I found that the
>classification results depend on how the inputs are scaled. For
>example, scaling the inputs to between -1 and 1 gives better
>results than to between 0 and 1. I can't find any explanation for
>this outcome. Anybody can give me comments or explanations?
>

We have found by looking at 3 dimensional plots of the error
surface that if the data is not centered about the origin, then the
there is often a steep "wall" where the weight trajectory bounces
off of during learning.  However, when the data is centered about
the origin the walls become less steep, and the surface is easier
to search.  This may imply that all input data should be normalized
to be centered about the origin.

-bill