Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!gatech!concert!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Statistics vs NN (was Re: Newbie question on stock prediction)
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <Cz0zDw.HxI@unx.sas.com>
Date: Thu, 10 Nov 1994 00:15:32 GMT
Distribution: na
References: <39b9in$of0@omnifest.uwm.edu> <39k43i$3q0@Radon.Stanford.EDU> <39kf8c$mkp@maui.cs.ucla.edu> <39qe5t$j7u@Radon.Stanford.EDU> <39rhlg$pmj@maui.cs.ucla.edu>
Nntp-Posting-Host: hotellng.unx.sas.com
Organization: SAS Institute Inc.
Lines: 32


In article <39rhlg$pmj@maui.cs.ucla.edu>, edwin@maui.cs.ucla.edu (E. Robert Tisdale) writes:
|> drakop@Xenon.Stanford.EDU (John Andrew Drakopoulos) writes:
[an astonishing sequence of non sequiturs which Bob Tisdale rashly
attempted to respond to, which he will propbably regret :-)] 

|> If you want to do research on learning algorithms for ANNs, you need
|> to bring yourself up to speed in Statistics.  But you should be aware
|> that there has been no substantial progress in the methods used over
|> the last 200 years.

What about:
   Levenberg-Marquardt
   quasi-Newton
   conjugate-gradients
   simulated annealing
   maximum likelihood estimation
   likelihood ratio tests and confidence intervals
   M estimation
   sandwich covariance estimators
   randomization tests
   bootstrapping
   Gibbs sampling
to name a few numerical and statistical methods of wide applicability?

And don't cite Hecht-Nielsen--he doesn't know anything about statistics.

-- 

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.
