Path: utzoo!censor!geac!torsqnt!news-server.csri.toronto.edu!clyde.concordia.ca!uunet!aplcen!samsung!munnari.oz.au!mullian.ee.mu.OZ.AU!akkh
From: akkh@mullian.ee.mu.OZ.AU (A. Hui)
Newsgroups: comp.ai.neural-nets
Subject: What is Conjugate Gradient method???
Message-ID: <5417@munnari.oz.au>
Date: 10 Sep 90 06:54:05 GMT
Sender: news@cs.mu.oz.au
Reply-To: akkh@mullian.ee.mu.OZ.AU (A. Hui)
Organization: Dept. of Electrical Engineering, University of Melbourne
Lines: 18

To all experts!

I recently came across the learning algorithm called "Conjugate Gradient
method" which is supposed to improve the performance of NN during the
learning phase.

I digged up a few references but was astonded by the huge vol. of maths
that is involved in the method.

So, Could someone gives me in simple term the general idea behind the method?
Or, a reference which you think is simple enough for a beginner in NN??

Thanks in advance!

===============================================================================
	Alvaro Hui		|ACSnet		akkh@mullian.oz
    4th Year B.E.\ B.Sc.	|Internet &	akkh@mullian.ee.mu.OZ.AU
   University of Melbourne	|Arpanet	rcoahk@koel.co.rmit.OZ.AU