Newsgroups: comp.ai.fuzzy
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!udel!news.sprintlink.net!cs.utexas.edu!news.tamu.edu!news.utdallas.edu!corpgate!bcarh189.bnr.ca!nott!torn!news.unb.ca!coranto.ucs.mun.ca!nstn.ns.ca!cs.dal.ca!cfn.cs.dal.ca!ac007
From: ac007@cfn.cs.dal.ca (Wolodymyr Barabash)
Subject: Re: BUG!  Fuzzy Systems Handbook. HELP!!!
Message-ID: <D63xsp.47D@cs.dal.ca>
Sender: usenet@cs.dal.ca (USENET News)
Nntp-Posting-Host: cfn.cs.dal.ca
Organization: Chebucto FreeNet
References: <reinhard.22.00BC38E3@mindspring.com> <3kqr7d$8c2@crcnis3.unl.edu> <reinhard.23.00E1B399@mindspring.com>
Date: Mon, 27 Mar 1995 16:29:11 GMT
Lines: 21

: I'd like to expand the library to include some adaptive measures 
: (genetics/neural) as it applys to the rules, as well as to make it more 
: c++ class oriented.Any tips where I can pick up some example source 
on how : to do this, especially regarding fuzzy neurons?  Or genetics?

You are quite right about the hack job. His job on how fuzzy inferences 
work is very poor. I suspect Mr. Cox uses the book more as a sales tool 
to gain contracts from people not in the programming field but in the 
applications arena. I suggest that it be used by anyone interested in 
doing work in that area outside of engineering just in that manner. It is 
a sales tool that gives credibility to a contract analyst/programmer in a 
field which does not have a lot of installed up and running applications.

FOr real programming, you are largely on your own. For sales, his book is 
undoubtedly a very very useful product. Welstead and others have some 
fuzzy code in their recent books. Folger and Klir's book Fuzzy Sets, 
Uncertainty and Informations is THE one to own for theory. BTW, Welstead's
book "Neural Network and Fuzzy Logic applications in C/C++" covers
genetic algorithms with fuzzy as well.

Regards, Wolly
