Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!agate!hpg30a.csc.cuhk.hk!hkuxb.hku.hk!h9218252
From: h9218252@hkuxb.hku.hk (IP Yu Ting)
Subject: Error surfaces ...continuous vs binary output
Message-ID: <D5D8s8.BsI@hkuxb.hku.hk>
Sender: usenet@hkuxb.hku.hk (USENET News System)
Nntp-Posting-Host: hkuxb.hku.hk
Organization: The University of Hong Kong
X-Newsreader: TIN [version 1.1 PL6]
Date: Mon, 13 Mar 1995 06:31:20 GMT
Lines: 11


Consider a function from a set of continuous valued vectors to one continuous 
valued output and another with the same vectors but with binary outputs.

Am I correct in claiming that the error suface of the former is *smoother* 
(just because its output is continous) ? 

Thanks.

--D.Ip

