From: <HIDDEN>
Newsgroups: comp.soft-sys.matlab
Subject: Re: Outputs in Elman Network
Date: Wed, 12 Jun 2013 10:04:11 +0000 (UTC)
Organization: The MathWorks, Inc.
Lines: 9
Message-ID: <kp9h2r$sle$>
References: <kod3j2$mpf$> <koupjg$j79$>
Reply-To: <HIDDEN>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
X-Trace: 1371031451 29358 (12 Jun 2013 10:04:11 GMT)
NNTP-Posting-Date: Wed, 12 Jun 2013 10:04:11 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 4346915
Xref: comp.soft-sys.matlab:797187

I've changed Elman to NARX and the problem is solved. But I'm still thinking why the output is so small.

To answer your question: >I don't know why, the output is really really small if we compare it with the target or even >the input. Can it be the weights or the bias? Or maybe the train option? 

Do you mean max(abs(cell2mat(Y))) << max(abs(cell2mat(T))) ?

Yes. Cell2mat(Y) <<<<<<<< cell2mat(T). But with the NARX, this doesn't happen. I don't know why.

Thanks for answering.