Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!hookup!news.moneng.mei.com!howland.reston.ans.net!vixen.cso.uiuc.edu!newsfeed.ksu.ksu.edu!moe.ksu.ksu.edu!osuunx.ucc.okstate.edu!rsi.ceat.okstate.edu!fmeng
From: fmeng@master.ceat.okstate.edu
Subject: What NN is the best for control application? 
Message-ID: <Cz2FMz.rE@osuunx.ucc.okstate.edu>
Sender: fmeng@rsi.ceat.okstate.edu (FUN MENG HOCK)
Nntp-Posting-Host: rsi.ceat.okstate.edu
Organization: OS
Date: Thu, 10 Nov 1994 19:04:10 GMT
Lines: 13

Hi,
	The are a lot of NN architecture around now such
as Radial Basis NN, Recurent NN, Feedforword NN, Modular NN 
and ...
	Which methods is the most accurate and most suitable
for control application? 
	To my knowledge, feedforward NN using 
Marquardt-Levenberg method is the fastest in training. But,
is Modular Neural Network faster than it?
What about others, eg Radial Basis and Recurent NN and etc?

Fun Meng Hock
 
