Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!elroy.jpl.nasa.gov!usc!julius.cs.uiuc.edu!news.cs.indiana.edu!ariel.unm.edu!neuron.unm.edu!bill
From: bill@neuron.unm.edu (william horne)
Newsgroups: comp.ai.neural-nets
Subject: Re: $$$ NN-Contest $$$
Message-ID: <1991Feb11.214818.19434@ariel.unm.edu>
Date: 11 Feb 91 21:48:18 GMT
References: <2571@opal.cs.tu-berlin.de> <1991Feb7.171338.894@cenatls.cena.dgac.fr>
Distribution: comp
Organization: University of New Mexico, Albuquerque
Lines: 15

In article <1991Feb7.171338.894@cenatls.cena.dgac.fr> vutien@secto.cenatls.cena.dgac.fr (Vutien CAP SESA - TDV) writes:
>Definition of NN in one word : a non linear filter.

You lose... this is a phrase.  The appropriate response is "A neural net is
a nonlinear filter".  ;-)

Actually, lets extend this a bit:  A neural net is a nonlinear adaptive
filter.

or perhaps:  A neural net is a nonlinear adaptive dynamical system.

I'll have dinner with President Bush and ask him:  "Can you define an energy
policy in one sentance?"

-Bill