Newsgroups: sci.logic,sci.stat.math,comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!newsstand.cit.cornell.edu!portc01.blue.aol.com!portc02.blue.aol.com!howland.erols.net!vixen.cso.uiuc.edu!ais.net!news.sprintlink.net!news-chi-8.sprintlink.net!interpath!news.interpath.net!news.interpath.net!sas!newshost.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Occam's razor & WDB2T [was Decidability question]
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <E16y83.FD6@unx.sas.com>
Date: Wed, 20 Nov 1996 22:52:51 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <E0vt38.6JL@unx.sas.com> <56oq25$s7q@miranda.its.deakin.edu.au>
Organization: SAS Institute Inc.
Lines: 22
Xref: glinda.oz.cs.cmu.edu sci.logic:20914 sci.stat.math:13331 comp.ai.neural-nets:34681


In article <56oq25$s7q@miranda.its.deakin.edu.au>, webb@deakin.edu.au (Geoff Webb) writes:
|> ...
|> First, my paper addresses the common application of a technique or principle
|> in machine learning, often called Occam's razor, that seeks to minimise
|> the surface syntactic complexity of the inferred classifier in the expectation
|> that doing so will in general increase predictive accuracy.  I believe that
|> I have provided strong evidence that this is misguided.

If you have studied regularization in neural network training or
smoothing in statistical methodology, then you already know that
surface syntactic complexity is relevant to predictive accuracy
only in certain limited situations such as maximum likelihood
estimation.

-- 

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.
 *** Do not send me unsolicited commercial or political email! ***

