Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!nntp.club.cc.cmu.edu!goldenapple.srv.cs.cmu.edu!das-news2.harvard.edu!oitnews.harvard.edu!purdue!ames!enews.sgi.com!news.sgi.com!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-chi-13.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: Wanting literature on Statistics vs. Neural Networks
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <E75Lt1.BHD@unx.sas.com>
Date: Sun, 16 Mar 1997 20:48:37 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <5g1eom$all$1@msunews.cl.msu.edu> <Pine.SOL.3.91.970310142846.4620F-100000@miles> <01bc30e7$03cbd580$2e6bb3c2@default>
Organization: SAS Institute Inc.
Lines: 31


In article <01bc30e7$03cbd580$2e6bb3c2@default>, "J. Blas Navarro Pastor" <jblas@conecta.es> writes:
|> > I'm looking for published literature that compares/constrasts
|> > neural networks with traditional statistical methods. I'm looking
|> > for theoretical similarities and differences as opposed to direct
|> > comparisons of performance based on analysis of a specific data
|> > set.
|> 
|> A book that compares statistical methods with neural networks, and explain
|> the foundations of the statistical approach with NN, and is not included in
|> the FAQ, is:
|> 
|> Murray Smith (1993)
|> Neural Networks for Statistical Modeling
|> Van Nostrand Reinhold:New York

Smith is cited in part 4 of the FAQ under "The best elementary
textbooks on practical use of NNs", but this book is not a good
place to look for "theoretical similarities and differences",
since it is rather light on theory. The title is a bit misleading,
since the book really doesn't cover much of what a statistician
thinks of as "statistical modeling". The books by Bishop and Ripley
(also cited in the FAQ) are much more thorough in that regard.

-- 

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! ***

