Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!uwm.edu!cs.utexas.edu!asuvax!ncar!tank!mimsy!mojo!linco
From: linco@eng.umd.edu (Sam Lin)
Newsgroups: comp.ai.neural-nets
Subject: Re: Eliminate BackPropagation Blues
Message-ID: <1990Mar1.212914.26070@eng.umd.edu>
Date: 1 Mar 90 21:29:14 GMT
References: <27433@cup.portal.com>
Sender: linco@eng.umd.edu
Distribution: usa
Organization: Maryversity of Uniland, College Purgatory
Lines: 26

In article <27433@cup.portal.com> mgj@cup.portal.com (Mark Gregory Jurik) writes:
>Pre-publication report on BACKPERCOLATION
>
>While BackPropagation creates output error gradients for each cell, BackPercolation is a second pass that creates,
>or assigns, true error to each cell.  With this information,

[description deleted]

>
>If you are interested, I will mail you a copy of the experimental
>results via U.S. Post.  Your request *must* include a self-
>addressed stamped envelope (standard business size).  I'll go
>broke otherwise.  If you like what you see, I'll then send you
>the algorithm details.
>
>Why this approach and not via a conference?  Simply put, that
>route will take too long.  I'm looking for co-researchers and/or
>other experimenters NOW.  
>
>Send your request to Mark Jurik
>                     PO 2379
>                     Aptos, CA  95001   USA

How about posting the algorithm to the net?  It would be even faster
than USnail, and save everyone lotsa stamps and envelopes.  It sounds
very interesting.