Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!news.mathworks.com!news.duke.edu!agate!hpg30a.csc.cuhk.hk!hkuxb.hku.hk!hkuxa.hku.hk!h9218252
From: h9218252@hkuxa.hku.hk (IP Yu Ting)
Subject: No. of hidden neurons ...
Message-ID: <D44LrC.IM2@hkuxb.hku.hk>
Sender: usenet@hkuxb.hku.hk (USENET News System)
Nntp-Posting-Host: hkuxa.hku.hk
Organization: The University of Hong Kong
X-Newsreader: TIN [version 1.1 PL6]
Date: Fri, 17 Feb 1995 03:59:35 GMT
Lines: 14


Hi there,

Is it true that any multilayer perceptron with ONE hidden layer can
realize ANY function ?  Or just binary functions ?

What about continuous valued functions ?  What is the minimum
architecture that will enable mapping of p continuous valued patterns
to a single continous output ?

Any comments, advices, discussions ......

--Deryck

