Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!howland.reston.ans.net!news.moneng.mei.com!news.ecn.bgu.edu!siemens!flake
From: flake@scr.siemens.com (Gary William Flake)
Subject: Re: Gaussian transfer function ???
Message-ID: <D69FMK.2D1@scr.siemens.com>
Sender: news@scr.siemens.com (NeTnEwS)
Nntp-Posting-Host: gull.scr.siemens.com
Organization: Siemens Corporate Research, Princeton NJ
References: <1995Mar30.113145.1831@cathy.ijs.si> <mike.796573835@motion>
Date: Thu, 30 Mar 1995 15:42:20 GMT
Lines: 30

In article <mike.796573835@motion>, Mike Dawson <mike@psych.ualberta.ca> wrote:
>robert.kocjancic@ijs.si (Robert Kocjancic, IJS) writes:
>
>>This is quite urgent. I think I heard something about gaussian transfer 
>>function in backpropagation neural nets, but I can't find any information
>>about this.
>
>
>Dawson, M.R.W., & Schopflocher, D.P. (1992).  Modifying the generalized
>	delta rule to train networks of nonmonotonic processors for pattern
>	classification.  Connection Science, 4, 19-31.

This is the central issue in my PhD dissertation.  You can ftp a short
version from

   ftp.umiacs.umd.edu:/pub/peyote/thesis-tr.ps.Z

or get it the hard way, throught UMI, with the information below.

@PHDTHESIS{Fla93a,
        AUTHOR = {G.~W.~Flake},
        TITLE = {Nonmonotonic Activation Functions in Multilayer Perceptrons},
        SCHOOL = {University of Maryland},
        YEAR = {1993},
        ADDRESS = {College Park, MD},
        MONTH = {December}
}
-- 
Gary W. Flake,  flake@scr.siemens.com,  Phone: 609-734-3676,  Fax: 609-734-6565
Siemens Corporate Research,  755 College Road East,  Princeton, NJ  08540,  USA
