Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!news.mathworks.com!uunet!in2.uu.net!news.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Nearest Neighbour Classifiers
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <DoHJDp.1FE@unx.sas.com>
Date: Mon, 18 Mar 1996 22:49:01 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References:  <4ieogp$gt@newsflash.hol.gr>
Organization: SAS Institute Inc.
Lines: 19


In article <4ieogp$gt@newsflash.hol.gr>, hanis@hol.gr (Hani) writes:
|> Has any body used the Nearest Neighbour classifiers in real work. How
|> does it compare with NN ?. 

Simple (1) nearest-neighbor classifiers often generalize poorly. It
is usually necessary to use k-nearest-neighbor methods or "editing"
to get good generalization. See:

   Hand, D.J. (1981) Discrimination and Classification, NY: Wiley.

   Ripley, B.D. (1996) Pattern Recognition and Neural Networks, 
   Cambridge: Cambridge University Press, ISBN 0-521-46086-7.

-- 

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.
