Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!uupsi!sunic!dkuug!daimi!steensj
From: steensj@daimi.aau.dk (Steen Sj|gaard)
Newsgroups: comp.ai.neural-nets
Subject: testing generalization i NN
Keywords: generalization problems, benchmark problems
Message-ID: <1991Apr4.130549.12904@daimi.aau.dk>
Date: 4 Apr 91 13:05:49 GMT
Sender: steensj@daimi.aau.dk (Steen Sj|gaard)
Organization: DAIMI: Computer Science Department, Aarhus University, Denmark
Lines: 29

Hi,

I am working on a project which deals with different network architectures and 
generalization. 
What I'm most interested in is to find out if there are any general ways to
determine the connectivity/arrangement of the "necessary" number of hidden 
units, when the main subject of interest is the networks' generalization 
ability. However, I desperately need a "well-sized" generalization problem
to train and test the different networks on. (By "well-sized" I mean a problem
which definitely is more complex (and realistic) than xor, parity and similar
toy-problems, but on the other hand also less complex/time-consuming  than 
NetTalk, e.g.)
I have talked to a lot of people about such a problem, but nobody seems to 
know of a "standard" or benchmark problem when it comes to analyzing 
generalization in neural networks. 

As I am sure that I am not the only one who finds this interesting, I would
therefore like to advertise for problems which actually have been successfully
applied to investigate the generalization ability of neural networks.

Any comments, ideas, suggestions, experiences????

                                              Thanks in advance
                  
                                              Steen Sjoegaard
                                              Comp. Sci. Dept.
                                              Aarhus University
                                              DK-8000, Denmark
                                              Email: steensj@daimi.aau.dk