Path: utzoo!attcan!uunet!samsung!usc!zaphod.mps.ohio-state.edu!swrinde!ucsd!pacbell.com!lll-winken!tristan!loren
From: loren@tristan.llnl.gov (Loren Petrich)
Newsgroups: comp.ai.neural-nets
Subject: Conjugate Gradients vs. Gradient Descent?
Message-ID: <67938@lll-winken.LLNL.GOV>
Date: 14 Sep 90 02:14:02 GMT
Sender: usenet@lll-winken.LLNL.GOV
Organization: Lawrence Livermore National Laboratory
Lines: 20
Originator: loren@tristan


	I checked on the subject of Conjugate Gradients in that big
book, "Numerical Recipes", and it did not seem to be anything other
than gradient descent.

	If I am in error about this, please correct me, and write out
the basic Conjugate Gradient algorithm, with the Gradient Descent
algorithm nearby.

	I think that it would be helpful to post the basic forms of
Gradient Descent and of modifications of it and of other algorithms,
just so one can readily compare them.


$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
Loren Petrich, the Master Blaster: loren@sunlight.llnl.gov

Since this nodename is not widely known, you may have to try:

loren%sunlight.llnl.gov@star.stanford.edu