Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!swrinde!elroy.jpl.nasa.gov!jato!huey!greg
From: greg@huey.Jpl.Nasa.GOV (Greg Wanish)
Newsgroups: comp.ai.neural-nets
Subject: solving the XOR problem with Rumelhart's neural net
Keywords: neural nets, logic gates
Message-ID: <1991Jun24.182310.11745@jato.jpl.nasa.gov>
Date: 24 Jun 91 18:23:10 GMT
Sender: nobody@jato.jpl.nasa.gov
Reply-To: greg@huey.Jpl.Nasa.GOV (Greg Wanish)
Organization: Spatial Interferometry Group, JPL
Lines: 11
Nntp-Posting-Host: hadass.jpl.nasa.gov

Has anyone been able to recreate Rumelhart's performance for the XOR problem? 
I am referring to the results published in PDP Vol. 1,  Chapter 8: "Learning Internal
Representations".  A student in his lab, Yves Chauvin, trains a 3 node net to solve the
XOR problem in an average of 245 iterations.  When I attempt to recreate this result,
my net solves it in ~2000 iterations.  I believe I have used the correct input range (0,1) and
output values (.1, .9), and I have used correct values for learning rate and momentum --
n  = .25 and momentum = .9. Omitting the momnetum term, did not decrease my iteration time.
I have used several different sets of weights, and my results have been consistently longer
than Rumelhart's.

				Greg