Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!howland.reston.ans.net!news.sprintlink.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Neural Networks v/s Statistics
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <DBIJvK.3or@unx.sas.com>
Date: Mon, 10 Jul 1995 18:40:32 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <3tbvf3$4oh@caesar.wits.ac.za> <3tpov1$dlj@newsbf02.news.aol.com>
Organization: SAS Institute Inc.
Lines: 18


In article <3tpov1$dlj@newsbf02.news.aol.com>, jxidus@aol.com (JXidus) writes:
|> I can't say I'm an expert in the field, but I think that for most NNs, to
|> understand the algorithms, mostly all you need is matrix algebra...  Sure,
|> there are varieties of NNs like statistical and probabilistic, but I'd say
|> the majority just require matrix algebra for an understanding of the
|> algorithms.

Perhaps, if you have noise-free data, although calculus would certainly
help. But once you've got noisy data, then you're doing statistics
whether you realize it or not, since "statistical inference" means
"generalizing from noisy data".

-- 

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.
