Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!oitnews.harvard.edu!purdue!haven.umd.edu!news.umbc.edu!eff!news.duke.edu!news.mathworks.com!news.kei.com!newsfeed.internetmci.com!in2.uu.net!winternet.com!news.minn.net!skypoint.com!umn.edu!news
From: fish0144@gold.tc.umn.edu (Dennis Fisher)
Subject: Re: Why not Cplus objects for neural-nets
Message-ID: <DKF59t.CAE@news.cis.umn.edu>
Sender: news@news.cis.umn.edu (Usenet News Administration)
Nntp-Posting-Host: dialup-4-54.gw.umn.edu
Organization: University of Minnesota, Twin Cities
X-Newsreader: Forte Free Agent 1.0.82
References: <4bv8ii$pd@eiger.pncl.co.uk>
Date: Sat, 30 Dec 1995 21:38:17 GMT
Lines: 12

merv@pncl.co.uk (Mervyn Snow) wrote:

>Neural nets are simple, trying to copy how our mind works. However
>computer languages have evolved to give object orientated languages.
>With these langauges an object can have many instances. Is it not an
>idea to replace these simple neural net nodes with complex objects and
>methods. Why does this not work.

C++ works just fine in this regard. I'm not familiar with any other OO
languages but it seems to me to be a pretty good tool for modeling
cell attributes and functions.

