Path: news.mathworks.com!not-for-mail
From: "Arga Ridhalla" <arga.ridhalla@yahoo.co.id>
Newsgroups: comp.soft-sys.matlab
Subject: What activation function should I choose?
Date: Thu, 31 Jan 2013 14:48:08 +0000 (UTC)
Organization: Institut Teknologi Bandung
Lines: 4
Message-ID: <kee078$ftj$1@newscl01ah.mathworks.com>
Reply-To: "Arga Ridhalla" <arga.ridhalla@yahoo.co.id>
NNTP-Posting-Host: www-03-blr.mathworks.com
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
X-Trace: newscl01ah.mathworks.com 1359643688 16307 172.30.248.48 (31 Jan 2013 14:48:08 GMT)
X-Complaints-To: news@mathworks.com
NNTP-Posting-Date: Thu, 31 Jan 2013 14:48:08 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 3719384
Xref: news.mathworks.com comp.soft-sys.matlab:787848

Hi everybody!
I use Neural Network Toolbox for a time series prediction (using NARX with 'traingdm' training function), and now I'm still confuse to choose an activation function for input and output layer. I have normalized all variables (including target variable) so now the values range between 0-1. What activation function should I choose for input and output layer? Is it tansig, logsig, or purelin? And what's the difference between them?

Thanks for the answers and sorry for my bad English.