Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!wuarchive!zaphod.mps.ohio-state.edu!uakari.primate.wisc.edu!aplcen!jhunix!ins_atge
From: ins_atge@jhunix.HCF.JHU.EDU (Thomas G Edwards)
Newsgroups: comp.ai.neural-nets
Subject: Re: Using Newton's Method to speed up backpropagation.
Summary: Ways to find local minima
Message-ID: <6873@jhunix.HCF.JHU.EDU>
Date: 14 Nov 90 16:36:34 GMT
References: <7556@uwm.edu> <2124@cybaswan.UUCP>
Organization: The Johns Hopkins University - HCF
Lines: 13

In article <2124@cybaswan.UUCP> eeoglesb@cybaswan.UUCP (j.oglesby eleceng pgrad) writes:
>I use a quadratic interpolation line search using a couple of points in the
>search direction. This involves a couple of function evalutions in the search
>direction from which an estimate of the step size to the minimum is calculated.
>This potentially shuld be good at finding LOCAL MINIMUM but I haven't found
>this a problem in 3 years of experience. 4 D EXOR's are generally solved in 
>< 10 line searches.

Have you tried the 2 intertwined spirals problem?  It really gives my
conjugate-gradient backprop neural net program a rough time with
local minima.  But it is easily solved with cascade-correlation.

-Tom