Path: news.mathworks.com!not-for-mail
From: <HIDDEN>
Newsgroups: comp.soft-sys.matlab
Subject: Question about number of layers in ANN
Date: Thu, 29 Oct 2009 08:15:23 +0000 (UTC)
Organization: The MathWorks, Inc.
Lines: 6
Message-ID: <hcbiur$5g7$1@fred.mathworks.com>
Reply-To: <HIDDEN>
NNTP-Posting-Host: webapp-05-blr.mathworks.com
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 8bit
X-Trace: fred.mathworks.com 1256804123 5639 172.30.248.35 (29 Oct 2009 08:15:23 GMT)
X-Complaints-To: news@mathworks.com
NNTP-Posting-Date: Thu, 29 Oct 2009 08:15:23 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 1669376
Xref: news.mathworks.com comp.soft-sys.matlab:580862


Dear All
I want to know, in Neural Networks, whether more layers will promise higher accuracy for classification?
I have tried using two networks to classify some images into classes. There are 100 variables in each sample, meaning that there are 100 input nodes. And for the Networks, The 1-layer network have 60 output nodes, and the 2-layers network have 20 hidden nodes in the hidden layers and 60 output nodes. 
But I found that the accuracy in the 1-layer network is higher than that in the 2-layer. I expected that the 2-layer may have higher accuracy because there are more parameters, so I am wondering whether there are bugs in my implementation. But I can't find any bugs up to now.
So can anyone tell me if that is my wrong expectation or other reasons so I have this result? And what is the relationship between the numbers of layers and the accuracy? How should I judge the optimal numbers of layers for neural networks?
Thank you