Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!pacific.mps.ohio-state.edu!linac!mp.cs.niu.edu!ux1.cso.uiuc.edu!honda.ece.uiuc.edu!andy
From: andy@honda.ece.uiuc.edu (Andy Bereson)
Newsgroups: comp.ai.neural-nets
Subject: Re: generalization in NN's
Keywords: ldf generalization
Message-ID: <1991Apr3.172206.23469@ux1.cso.uiuc.edu>
Date: 3 Apr 91 17:22:06 GMT
References: <1991Apr2.205240.24668@milton.u.washington.edu>
Sender: usenet@ux1.cso.uiuc.edu (News)
Reply-To: bereson@cs.uiuc.edu
Organization: University of Illinois at Urbana
Lines: 29

> 
> I have a problem with the ability of a neural net to generalize.
> 
> When I use a simple linear discriminant function with seperate
> covariance matrices and compare that against a NN with 6 input,
> 12 hidden and 4 output nodes. Here's what I get for correct
> 
> 			LDF	NN
> train			48.5	59.0
> test			42.0	37.0
> 

A linear discriminant function is similar to back-prop with no hidden
units, and that does better than your twelve hidden units.  It sounds
like you may be using too many units.  This is a common cause for under-
generalization.  

> And no matter how long I let the NN run, and no matter what
> number of hidden layer nodes, I always get about the same 
> results.

after some amount of training the ability of the network to predict new
examples will begin to degrade.  Further training will only worsen
this problem.  Reducing the number of units and the number of training
epochs will help solve this problem. 

Good luck

Andy