Path: utzoo!attcan!utgpu!news-server.csri.toronto.edu!clyde.concordia.ca!uunet!cs.utexas.edu!uwm.edu!rpi!bu.edu!snorkelwacker!bloom-beacon!eru!luth!sunic!mcsun!ukc!cam-eng!niranjan
From: niranjan@eng.cam.ac.uk (Mahesan Niranjan)
Newsgroups: comp.ai.neural-nets
Subject: Re: Using deltas at the input layer
Message-ID: <13104@rasp.eng.cam.ac.uk>
Date: 28 Jul 90 09:35:26 GMT
References: <12039@sdcc6.ucsd.edu>
Sender: niranjan@eng.cam.ac.uk
Organization: Cambridge University Engineering Department, UK
Lines: 14

In article <12039@sdcc6.ucsd.edu> demers@beowulf.ucsd.edu (David Demers) writes:
>I'm curious to know if anyone has done anything
>with computation of deltas for input units.  I'm
>aware of the paper by Risto Mikkulainen & Mike Dyer
>in 1988 Connectionist Models Summer School proceedings.
>
>It seems silly on the face of it to compute
>an "error" for the input - a determination of
>what the input SHOULD HAVE BEEN to produce a

It depends on the application. If it is noise reduction (or some kind of
filtering), then you are actually doing something to the input data.

niranjan