Path: utzoo!news-server.csri.toronto.edu!cs.utexas.edu!uunet!mcsun!ukc!warwick!esrmm
From: esrmm@warwick.ac.uk (Denis Anthony)
Newsgroups: comp.ai.neural-nets
Subject: Re: Are Conjugate Gradient algorithms any good?
Keywords: NETtalk, Conjugate Gradient algorithms, Back-propagation
Message-ID: <72D&2$@warwick.ac.uk>
Date: 8 Mar 91 16:09:17 GMT
References: <1991Mar4.142559.21857@daimi.aau.dk> <^9B&5R#@warwick.ac.uk> <pluto.668285404@cornelius>
Sender: news@warwick.ac.uk (Network news)
Organization: Computing Services, Warwick University, UK
Lines: 33
Nntp-Posting-Host: orchid

In article <pluto.668285404@cornelius> pluto@cornelius.ucsd.edu (Mark Plutowski) writes:
>Reiterating the discussion so far:
>Some quite interesting empirical results comparing two gradient descent algorithms:
>
>(1) a version of conjugate gradient ("Scaled Conjugate Gradient")
>(2) backpropagation.
>
>
>Variations of these two algorithms are formed by processing the training examples
>in the following modes:
>
>(a) batched (a.k.a. "epoch") learning:  the calculation of each weight
>update utilizes information from all of the available training examples.
>
>(b) pattern learning:  each weight update is performed after presentation
>of a single example.
>
>(c) "Block" learning: this lies between (a) and (b) in the sense that each
>weight update utilizes a subset of the available training examples.
>
>
>Remarks:
>I was most interested in the report by Denis Anthony, i.e.,
>
>	>... using epoch updates was inferior to pattern updates.
>
>except it was unclear from context whether this refers to
>a comparison of (1a) v. (1b), or between  (2a) and (2b).
>

2a v 2b (ie. backprop)

Denis