Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!news.mathworks.com!tank.news.pipex.net!pipex!lyra.csx.cam.ac.uk!warwick!bsmail!usenet
From: Max Ratcliffe <m.j.ratcliffe@bris.ac.uk>
Subject: generalisation outside data set
Message-ID: <DFGM2M.KD@uns.bris.ac.uk>
Sender: usenet@uns.bris.ac.uk (Usenet news owner)
Nntp-Posting-Host: pc19.aer.bris.ac.uk
Organization: University of Bristol, England
Date: Mon, 25 Sep 1995 11:47:09 GMT
Lines: 10

Hello, 

I have an application where I am having trouble generating a training
set broad enough to encompass the testing set, short of cheating, and
using a priori information.  Does anybody know of any method of 
improving out-of-range generalisation, or do I just using C-V, or 
whatever technique, as for generalisation between data sets, and hope
for the best?

Thanks, Max
