Path: utzoo!attcan!uunet!lll-winken!xanth!ames!haven!purdue!mentor.cc.purdue.edu!pur-ee!pc.ecn.purdue.edu!cb.ecn.purdue.edu!vaidyana
From: vaidyana@cb.ecn.purdue.edu (Ramaswamy Vaidyanathan)
Newsgroups: comp.ai.neural-nets
Subject: Re: : Step Function
Message-ID: <1114@cb.ecn.purdue.edu>
Date: 24 Aug 89 14:38:56 GMT
Organization: Purdue University Engineering Computer Network
Lines: 12

In a recent article, Heinrich writes:

> This statement makes me uncomfortable.  It has been proven (White) that a
> two-layer feed forward network with a signmoid activation function (such as
> you find in standard back propagation networks) can approximate any Borel
> 
>
Could you please post where this paper this paper by White was published.
I have not seen this paper, it could be useful in my work.
Thanks in advance.
Vaidya.
 -------------------------