Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!samsung!noose.ecn.purdue.edu!stable.ecn.purdue.edu!muttiah
From: muttiah@stable.ecn.purdue.edu (Ranjan S Muttiah)
Newsgroups: comp.ai.neural-nets
Subject: normalizing
Message-ID: <1991Apr25.182305.7628@noose.ecn.purdue.edu>
Date: 25 Apr 91 18:23:05 GMT
Sender: root@noose.ecn.purdue.edu (ECN System Management)
Organization: Purdue University Engineering Computer Network
Lines: 13

Say you have a set X that has the following values:

	X = {5, 6, 7, 8, 10}.

X is known to have a maximum value of 20.

So, for input to a typical network, do I normalize such as:

	X_new = {5/10, 6/10 ... }

or as:

	X_new = {5/20, 6/20, .... }