Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!travelers.mail.cornell.edu!news.kei.com!news.mathworks.com!newsfeed.internetmci.com!news.sprintlink.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Measuring nonlinearity
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <DEwJ5A.G3L@unx.sas.com>
Date: Thu, 14 Sep 1995 15:31:58 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References:  <alwang.170.021FAD3C@eniac.seas.upenn.edu>
Organization: SAS Institute Inc.
Lines: 23


In article <alwang.170.021FAD3C@eniac.seas.upenn.edu>, alwang@eniac.seas.upenn.edu (Teen Age Riot) writes:
|> I suppose this doesn't fall directly under neural networks, but I'm sure it's
|> a subject considered by many others in the field: given a training data set,
|> is there anyway to numerically evaluate the linearity of the system?

Measures of nonlinearity are discussed in:

   Bates, D.M. and Watts, D.G. (1988) Nonlinear Regression Analysis &
   Its Applications, Wiley: NY.

|> This
|> would be useful in determing the number of layers and nodes necessary for a
|> network to learn the data.

Not so simple. You have to train a suitable network in order to get
the measures of nonlinearity in the first place.

-- 

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.
