Path: utzoo!attcan!uunet!aplcen!samsung!cs.utexas.edu!hellgate.utah.edu!helios.ee.lbl.gov!ucsd!sdcc6!sdcc13!pa1159
From: pa1159@sdcc13.ucsd.edu (Matt Kennel)
Newsgroups: comp.ai.neural-nets
Subject: Re: Neural Network for ranking football teams.
Keywords: Hopfield nets, linear algebra
Message-ID: <5285@sdcc6.ucsd.edu>
Date: 21 Nov 89 08:15:25 GMT
References: <13645@boulder.Colorado.EDU> <80663@linus.UUCP>
Sender: news@sdcc6.ucsd.edu
Reply-To: pa1159@sdcc13.ucsd.edu (Matt Kennel)
Organization: University of California, San Diego
Lines: 22

In article <80663@linus.UUCP> sdo@faron.UUCP (Sean D. O'Neil) writes:
>
>Note that I am NOT saying that Hopfield or constraint satisfaction networks
>have no use.  Often one wishes to constrain values that the outputs of the
>network can take on.  This is usually done implicitly by shaping the transfer 
>or activation function in some way---typically a sigmoidal shape is used.
>In such cases, one CANNOT take the algebraic approach I described above and
>it is often the case that the easiest solution technique is to run the
>network and let it converge.

Simon says, "Lagrange multipliers."



 
 
 
 
 
 
Matt Kennel
pa1159@sdcc13.ucsd.edu