Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!sdd.hp.com!spool.mu.edu!munnari.oz.au!goanna!minyos.xx.rmit.oz.au!rcssjh
From: rcssjh@minyos.xx.rmit.oz.au (Steven Hayes)
Newsgroups: comp.ai.neural-nets
Subject: Re: solving the XOR problem with Rumelhart's neural net
Keywords: neural nets, logic gates
Message-ID: <1991Jun25.014851.19898@minyos.xx.rmit.oz.au>
Date: 25 Jun 91 01:48:51 GMT
Article-I.D.: minyos.1991Jun25.014851.19898
References: <1991Jun24.182310.11745@jato.jpl.nasa.gov>
Organization: RMIT Computer Centre, Melbourne Australia.
Lines: 18

greg@huey.Jpl.Nasa.GOV (Greg Wanish) writes:

>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


Have you tried it with a lower value for the momentum term? say 0.5?

-Steve