Path: utzoo!utgpu!news-server.csri.toronto.edu!rutgers!usc!samsung!uunet!mcsun!unido!gmdzi!al
From: al@gmdzi.UUCP (Alexander Linden)
Newsgroups: comp.ai.neural-nets
Subject: Re: Input scaling alters my results; why?
Message-ID: <3200@gmdzi.UUCP>
Date: 13 Aug 90 16:51:34 GMT
References: <473@array.UUCP>
Organization: GMD, Sankt Augustin, F. R. Germany
Lines: 23

In article <473@array.UUCP>, ling@array.UUCP (Ling Guan) writes:
> ... 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?

I see the main reason for quicker convergence in the fact that weights
going from input units away can be updated twice as often. This is
because in $$w_ji = w_ji +\eta * \delta_j * a_i $$ the factor $a_i$
will have an effect on learning. When you use sparse-coding with mane
zeros this factor will be zero most of the time. But if you use -1
instead of 0, on each update each weight can learn.

Another thing is of course that you alter semantics of activations.
-1 has the opposite effect to +1 while 0 will have no effect. This
semantic seems in many cases more plausible.

Alexander Linden                    | TEL. (49 or 0) 2241/14-2537
Research Group for Adaptive Systems | FAX. (49 or 0) 2241/14-2618 or -2889
GMD                                 | TELEX 889469 gmd d
P. O. BOX 1240                      |            /  al@gmdzi.uucp
D-5205 St. Augustin 1               |     e-mail<   al@zi.gmd.dbp.de
Federal Republic of Germany         |            \  unido!gmdzi!al@uunet.uu.net
-------------------------------------------------------------------------------