Re: DM: Book on datamining

[iparsa]

Warren:

Thank you for the illuminating reply.

Just FYI but Swingler bases most of his "what-to" and "how-to"
judgments on _Neural Computing: Best Practice Guidelines
for Developing Neural Computing Applications_. It's an
out-of-print material published by a consortium delegated by
the Department of Trade and Industry, United Kingdom (and
Chris Bishop was academic advisor to the consortium!)

Kind regards,

Ismail Parsa
Epsilon
50 Cambridge Street
Burlington MA 01803 USA

E-MAIL:   iparsa@epsilon.com
V-MAIL: (781) 273-0250*6734
FAX:    (781) 272-8604




To:   datamine-l@nautilus-sys.com, bodart@dcc.ufmg.br
cc:    (bcc: Ismail Parsa/Boston50/Epsilon)
Subject:  Re: DM: Book on datamining




Ismail Parsa writes:
> ...
> Among related subject matter areas, Swingler's book (Applying Neural
> Networks) does an excellent job of covering all aspects of NN 
>modeling.

I beg to differ. Swingler's book contains numerous gross errors and
has thereby received the rare distinction of being placed on "The
Worst" list of books in the Neural Net FAQ. See:

ftp://ftp.sas.com/pub/neural/FAQ4.html#A_books_worst_swingler
ftp://ftp.sas.com/pub/neural/FAQ4.html#A_books_code_swingler

--

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not 
necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.