Path: utzoo!attcan!utgpu!news-server.csri.toronto.edu!clyde.concordia.ca!uunet!know!zaphod.mps.ohio-state.edu!samsung!munnari.oz.au!rgg
From: rgg@munnari.oz.au (Rupert Graham Goldie)
Newsgroups: comp.ai.neural-nets
Subject: Problem teaching an NN to add.
Keywords: addition
Message-ID: <5516@munnari.oz.au>
Date: 17 Sep 90 06:36:58 GMT
Sender: news@cs.mu.oz.au
Lines: 27

I  have been trying to train a neural network to add two 4 bit numbers with 
little success and I was wondering if anyone else has tried to do this and
succeeded. I first tried using  binary representation for the numbers and
with little success with that I then tried representing the numbers by the
number of neurons activated (ie 2 is represented by 1.0 1.0 0.0 .... 0.0).
This representation wasn't much more successful.
  This problem set has 256 example patterns and so I have tried training with
32 to 256 patterns in the training set. With up to about 60 patterns I was able
to get the net to converge but the resulting network doesn't generalize very 
well to non-training set examples. I have tried training with larger sets for
up to 15000 epochs but the total error just appears to oscillate and not to 
be approaching zero.
 I have been using between 10 and 80 hidden units with quickprop and have tried
cascade-correlation with upto 160 new nodes. The latter has been spectacularly
unsuccessful. With quickprop I mainly have one hidden layer but have also
tried using more, also with little success.

 If there is any interest I could post the short C program I use to generate 
the training sets so that others can try this too. 
 Thanks, 

		Rupert
----
Rupert G. Goldie				rgg@munmurra.cs.mu.OZ.AU
Computer Science Honours Student, University of Melbourne

"necessity is a mother"