Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!samsung!uunet!mcsun!hp4nl!donau!duteca.et.tudelft.nl!kooijman
From: kooijman@duteca.et.tudelft.nl (Richard Kooijman)
Newsgroups: comp.ai.neural-nets
Subject: Re: Need activation levels in backprop nets be between 0 and 1?
Keywords: backpropagation networks, activation levels
Message-ID: <1991Jun22.134650.22173@donau.et.tudelft.nl>
Date: 22 Jun 91 13:46:50 GMT
References: <80657@eerie.acsu.Buffalo.EDU>
Sender: news@donau.et.tudelft.nl (UseNet News System)
Organization: Delft University of Technology, Dep. of Electrical engineering
Lines: 26
Nntp-Posting-Host: duteca.et.tudelft.nl

bettingr@acsu.buffalo.edu (Keith E. Bettinger) writes:

>In backpropagation networks, is it *inherent* in the equations involved
>that the activation range be on the unit interval [0,1] or the
>integer unit interval [-1,1]?

You should have no troubles using these ranges even for real-valued input
and output. I have done several experiments that all worked except for
networks that didn't have enough hidden units to deal with the problem.

I have tested other ranges too, and came to the conclusion that if you
use values that are the slightest bit higher than 1, you'll get in trouble.

If you use the least square error function you can't use any ranges
outside [-1,1] because the learning rule would not be able anymore
to correct a value to one because errors for a desired output of 1 and 
actual outputs of 0.8 or 1.2 can't be distingished.

Before I wrote this reply I couldn't figure out why you can't use ranges
outside [-1,1], but now I get it.
The result is that I wrote this message without much thought, so I can be
mistaken.

I hope I helped you anyway,

Richard.