Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!ames!elroy!orion.cf.uci.edu!uci-ics!ucla-cs!gblee
From: gblee@maui.cs.ucla.edu
Newsgroups: comp.ai.neural-nets
Subject: Re: GD and LSE
Message-ID: <22206@shemp.CS.UCLA.EDU>
Date: 24 Mar 89 18:56:24 GMT
Sender: news@CS.UCLA.EDU
Reply-To: gblee@CS.UCLA.EDU ()
Organization: UCLA Computer Science Department
Lines: 27

> There is another paper with a similar claim.
   **************************************************************
>  "Gradient descent fails to separate" is its title.
>            By : M. Brady and R.Raghavan
    *****************************************************
>The paper shows the failure of BP in the case of examples where 
>there are no local minima.  They assert (and they could be right as ...
>                                                               
>                                         (FIAT LUX)

Can you tell us where the paper you mentioned is published and when?
May be somebody else in this news group are also interested in ...
I know another similar paper which attacked GD....

 Sutton, R. Two problems with BP and other steepest-descent learning
 procedures for networks.

 He points out:
1. steepest descent is a particulary poor for surface containing "ravines"
2. steepest descent results in high level of interference between learning
with different patterns...

Unfortunately, I forgot where this paper was published.
Can anybody out there tell where it was published for us?

--Geunbae Lee
  AI lab, UCLA