Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!newsstand.cit.cornell.edu!newstand.syr.edu!news.maxwell.syr.edu!news.mathworks.com!newsgate.duke.edu!interpath!news.interpath.net!news.interpath.net!sas!newshost.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: mathematical material
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <E5sDLL.L91@unx.sas.com>
Date: Tue, 18 Feb 1997 06:48:57 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <01bc187c$1f873fe0$032b20c3@caanbbdb.isnet.it> <5e1sbt$2q4$1@gemini.yars.free.net>
Organization: SAS Institute Inc.
Lines: 25


In article <5e1sbt$2q4$1@gemini.yars.free.net>, ltwood@uniyar.ac.ru (LtWood) writes:
|> >
|> >I'm a student of computer science and I'm preparing an axam of systems
|> >theory. I would like to study a neural network (or an ID3 algorithm) to
|> >predict the result of soccer matches (something like greyhound
|> >races). Where can I get some material with mathematical description of the
|> >argument? ...
|> >
|> Firstly you must to study the articles of Hopfield,
|> wich are the best introduction to modern NN theory.

For predicting soccer matches??? I don't think so.

Take a look at http://dmawww.epfl.ch/~kuonen/CALCIO/ and note that
logistic regression is a feedforward NN with no hidden layer and a
logistic output activation function. 

-- 

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.
 *** Do not send me unsolicited commercial or political email! ***

