Path: utzoo!attcan!uunet!dino!ux1.cso.uiuc.edu!ux1.cso.uiuc.edu!kbesrl
From: kbesrl@ux1.cso.uiuc.edu
Newsgroups: comp.ai.neural-nets
Subject: Re: Eliminate BackPropagation Blues
Message-ID: <2200002@ux1.cso.uiuc.edu>
Date: 2 Mar 90 17:31:08 GMT
References: <27433@cup.portal.com>
Lines: 22
Nf-ID: #R:cup.portal.com:27433:ux1.cso.uiuc.edu:2200002:000:835
Nf-From: ux1.cso.uiuc.edu!kbesrl    Mar  2 09:08:00 1990


>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.
>>

>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.

I second the proposal for posting it on the net!