Path: utzoo!attcan!uunet!ncrlnk!ncr-sd!hp-sdd!hplabs!decwrl!purdue!mailrus!ncar!noao!asuvax!enuxha!rao
From: rao@enuxha.eas.asu.edu (Arun Rao)
Newsgroups: comp.ai.neural-nets
Subject: Re: Learning arbitrary transfer functions
Summary: Interpolation problem
Message-ID: <188@enuxha.eas.asu.edu>
Date: 17 Nov 88 16:00:26 GMT
References: <399@uvaee.ee.virginia.EDU> <282@nvuxh.UUCP>
Organization: Arizona State Univ, Tempe
Lines: 19


 In article <399@uvaee.ee.virginia.EDU> aam9n@uvaee.ee.virginia.EDU (Ali Minai) writes:
 >I am looking for any references that might deal with the following
 >problem:
 >
 >y = f(x);         f(x) is nonlinear in x
 >
 >Training Data = {(x1, y1), (x2, y2), ...... , (xn, yn)}
 >
 >Can the network now produce ym given xm, even if it has never seen the
 >pair before?
	Sounds like a standard interpolation problem to me, though a good
	deal of effort has been expended to make neural networks  inter-
	polate. Any elementary book on numerical analysis will treat
	this problem, but the author of the above probably knows this.
	I would be interesting in other ramifications to the above problem
	which are not readily amenable to classical techniques.

	- Arun Rao