Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!think.com!mintaka!bloom-beacon!eru!hagbard!sunic!mcsun!hp4nl!sci.kun.nl
From: mderksen@sci.kun.nl (M. Derksen)
Newsgroups: comp.ai.neural-nets
Subject: Backprop with additional noisy inputfeature
Message-ID: <3559@wn1.sci.kun.nl>
Date: 14 May 91 10:30:15 GMT
Sender: root@sci.kun.nl
Organization: University of Nijmegen, The Netherlands
Lines: 31

Dear neural netters,

Can someone explain me why an additional noisy inputfeature results in a
better prediction performance (generalization). 

I've add an extra input unit to a multilayer feedforward network. 

1. In the training phase, a noisy signal (gaussian distribution with 
   zero mean and variable standard deviation) is feed into the extra
   input unit. 

2. In the test phase, a signal value of zero is feed into this unit. 

I've done some experiments and received a significant better prediction 
performance. 

I came to this 'improvement' a few months ago, when there was a discussion 
on the net about an additional noisy vector to the patterns in the 
trainingset.

Marco.

###############################################################################
#                                                                             #
#     Catholic University of Nijmegen         Ing. M.W.J. Derksen             #
#     Laboratory for Analytical Chemistry     Tel: 080-653158                 #
#     Faculty of Science                      Fax: 080-652653                 #
#     Toernooiveld 1                          Telex: 48228 wina nl            #
#     6525 ED Nijmegen, the Netherlands       E-mail: mderksen@sci.kun.nl     #
#                                                                             #
###############################################################################