Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!newsfeed.pitt.edu!gatech!newsfeed.internetmci.com!in1.uu.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: general regression net code
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <Dnns4H.1CG@unx.sas.com>
Date: Sat, 2 Mar 1996 21:09:53 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <4h1q77$bgp@qns3.qns.com> <4h3ppe$mkv@cloner2.ix.netcom.com>
Organization: SAS Institute Inc.
Lines: 35


In article <4h3ppe$mkv@cloner2.ix.netcom.com>, jdadson@ix.netcom.com(Jive Dadson ) writes:
|> In <4h1q77$bgp@qns3.qns.com> rking@vialink.com writes: 
|> >
|> >I've been searching for source code for the General Regression
|> >Neural Network paradigm. Can anyone help me?
|> 
|> Try looking also under "Nadaraya-Watson".
|> 
|> Timothy Masters' _Advanced Algorithms for Neural Networks_ has
|> source code on IBM diskette. The algorithm itself is extremely
|> short and simple. 

But a thorough discussion of how to implement the algorithm
_efficiently_ would have lengthened the book by a hundred pages or so.

|> Choosing the kernel width can be trickier. I would
|> recommend supplimenting your reading with B.W. Silverman's _Density
|> Estimation for Statistics and Data Analysis_ for alternate kernels (in
|> particular, the Epanechnikov kernel) and some important analysis of
|> selecting kernel widths. The book only deals with density estimation,
|> but the ideas carry through exactly to general function estimation.

Also:

   Scott, D.W. (1992), _Multivariate Density Estimation_, Wiley.

   Haerdle, W. (1990), _Applied Nonparametric Regression_, Cambridge
   Univ. Press.

-- 

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.
