Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!usc!wuarchive!uunet!stanford.edu!msi.umn.edu!aps1.spa.umn.edu!ted From: ted@aps1.spa.umn.edu (Ted Stockwell) Newsgroups: comp.ai.neural-nets Subject: Re: solving the XOR problem with Rumelhart's neural net Message-ID: Date: 24 Jun 91 21:59:19 GMT References: <1991Jun24.182310.11745@jato.jpl.nasa.gov> Sender: news@s1.msi.umn.edu Organization: Univ. of Minnesota Astronomy Dept., APS Lab Lines: 30 In-Reply-To: greg@huey.Jpl.Nasa.GOV's message of 24 Jun 91 18: 23:10 GMT Nntp-Posting-Host: aps1.spa.umn.edu In article <1991Jun24.182310.11745@jato.jpl.nasa.gov> 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 I attempted to train 1000 nets with weights and bias terms randomly initialized to values in the range from 0.5 to -0.5 with a learning rate of 0.25 and a momentum of 0.9 . Training was aborted if it had not succeeded after 750 passes through the training data. This was the case for 264 of the attempts. For the networks that completed training, an average of 499 passes were required, however the number of passes needed were well distributed from 250 to greater than 700. In the book, it does not say how Chauvin's networks were initialized, and it appears that this makes a significant difference. -- Ted Stockwell U of MN, Dept. of Astronomy ted@aps1.spa.umn.edu Automated Plate Scanner Project