Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!purdue!bu-cs!bloom-beacon!apple!vsi1!wyse!mips!prls!philabs!linus!sdo
From: sdo@linus.UUCP (Sean D. O'Neil)
Newsgroups: comp.ai.neural-nets
Subject: Re: GD and LSE
Message-ID: <47009@linus.UUCP>
Date: 27 Mar 89 15:19:32 GMT
References: <22206@shemp.CS.UCLA.EDU>
Reply-To: sdo@faron.UUCP (Sean D. O'Neil)
Organization: The MITRE Corporation, Bedford MA
Lines: 26

In article <22206@shemp.CS.UCLA.EDU> gblee@CS.UCLA.EDU () writes:
>>  "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 ...
>
>Can you tell us where the paper you mentioned is published and when?


I attended the presentation by Raghavan at ICNN '88 in San Diego, so 
at least the paper has been published in those proceedings.  My 
impression is that their result is fairly simple to understand.  
Essentially, they point out that minimizing the number of misclassifications 
is not identical to the least-squares solution, and they give several 
examples in which linear class separation is possible but the least-squares 
solution does not in fact separate the classes.

Aha, here it is.  The paper is:

Brady, M., R. Raghavan, and J. Slawny, "Gradient Descent Fails to
Separate", in IEEE International Conference on Neural Networks,
IEEE, San Diego, CA, pp. I-649 to I-656, July 24-27, 1988.


Sean