Newsgroups: comp.ai.neural-nets
From: David@longley.demon.co.uk (David Longley)
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!swrinde!pipex!bt!btnet!peernews.demon.co.uk!longley.demon.co.uk!David
Subject: Re: linear separable boolean functions -- lists?
Distribution: world
References: <3makuv$jng@agate.berkeley.edu>
Organization: Myorganisation
Reply-To: David@longley.demon.co.uk
X-Newsreader: Demon Internet Simple News v1.29
Lines: 27
X-Posting-Host: longley.demon.co.uk
Date: Thu, 13 Apr 1995 06:59:20 +0000
Message-ID: <797756360snz@longley.demon.co.uk>
Sender: usenet@demon.co.uk

In article <3makuv$jng@agate.berkeley.edu>
           crounse@fred.EECS.Berkeley.EDU "Kenneth R. Crounse" writes:
> 
> 
> Hi all--
> 
> I would like to find lists, preferably on the net,
> of all the linearly separable boolean functions of
> 3,4,5,... variables.  What I have in mind is: for example
> for 2 variables there are 16 ways to fill out the truth table
> and all but XOR and its complement are linear separable, so
> the other 14 would be listed by truthtable or a decimal equivalent.  
> Second best, a program to compute them.
> Any clues?  
> 
> thanks,
> 
> ken crounse

I would be interested too. I have a reference to a paper written some years ago
which I will endeavour to dig out and post when I can lay my hands on its ref.
Just as an aside, a colleague of mine (I'm a psychologist) suggested that the
non-linearities which so many neural-net folk make a fuss of, may just be the
interaction terms in regression or other statistical analyses. Any comments
anyone?
-- 
David Longley
