Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!news.sprintlink.net!redstone.interpath.net!sas!mozart.unx.sas.com!news
From: sukdap@mvs.sas.com (Derek Powell)
Subject: Re: Sin Curve
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <D6ysIw.2EM@unx.sas.com>
Date: Thu, 13 Apr 1995 08:20:56 GMT
X-Nntp-Posting-Host: 130.96.73.65
Reply-To: sukdap@mvs.sas.com (Derek Powell)
References: <1995Apr9.194843.18446@Princeton.EDU>
Organization: SAS Institute Inc.
X-Newsreader: IBM NewsReader/2 v1.09
Lines: 34

In <1995Apr9.194843.18446@Princeton.EDU>, adaml@isler.Princeton.EDU (Adam E. Lichtenstein) writes:
>I am writing a program to develop a nueral network for robotic control.  As a
>test case, I am using 10 points along a sin curve.  I modeled the back
>propagation algorithm after Quickprop (epsilon = 0.1 - 1.0, maxfactor = 1.75, 
>sigma prime offset = 0.1, decay = -0.001).  The network has one input and one
>output and two hidden layers with sizes varying from two nodes each to ten nodes.
> The initial weights are randomly set between -1 and 1.  
>	The problem is that the neural net rarely converges to anything like a
>sin curve.  The graph of RMS has a lot of noise in it, and it usually settles
>down around RMS = 0.4 (generally corresponding to a horizontal line between 0 and
>PI).  I don't think the code is entirely wrong given that sometimes it converges
>quite nicely, but I don't want to attempt a much more difficult problem until I'm
>sure I'm doing everything correctly.
>	I would appreciate any suggestions.  It might be helpful if someone has a
>working data set that I could look at (along with the results).  Thanks for your
>help.
>
>	- Adam
>--------------------------------------------------------
>
>Adam Lichtenstein
>
>P.O. Box 1193                            301S Dod Hall
>Princeton, NJ 08542-1193          Princeton University
>U.S.A.                             Princeton, NJ 08544
>
>(609) 258-7847
>Fax: (609) 258 - 2649
Hi Adam,
We're mising a few important pieces of information here, distribution of the 10 values
, type of backprop (Plain Vanilla) etc, Tranfer function, is data normalised ?
Can you post the data in text form to me in a mail and I'll have a look !.
Derek

