Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!fs7.ece.cmu.edu!hudson.lm.com!godot.cc.duq.edu!newsfeed.pitt.edu!gatech!swrinde!pipex!uunet!spstimes.sps.mot.com!mogate!newsgate!wetware!chance
From: chance@ae.sps.mot.com (Chance Harris)
Subject: Re: MLP vs Projection Pursuit
Message-ID: <1994Dec6.174703.10427@newsgate.sps.mot.com>
Sender: news@newsgate.sps.mot.com
Nntp-Posting-Host: wetware.sps.mot.com
Organization: sps
X-Newsreader: TIN [version 1.2 PL2]
References: <66979.alison@atp.biochem.usyd.edu.au> <D0Cqvy.LEC@unx.sas.com>
Date: Tue, 6 Dec 1994 17:47:03 GMT
Lines: 29

Warren Sarle (saswss@hotellng.unx.sas.com) wrote:

: In article <66979.alison@atp.biochem.usyd.edu.au>,  <alison@atp.biochem.usyd.edu.au> writes:
: |> Given a nonparametric regression problem in which there are multiple,
: |> continuous-valued inputs and outputs (i.e., multivariate / multiresponse)
: |> what are the pros and cons of using a multilayer perceptron (with sigmoid
: |> hidden units and linear output units) and projection-pursuit regression
: |> (with multuple outputs).

: The obvious advantage of an MLP is that it is easier to compute
: predicted values (i.e. outputs). I would speculate that projection
: pursuit regression is less prone to local minima. However, I know of
: no studies that have performed nontrivial comparisons of these two
: methods.

:    Haerdle, W. (1990), _Applied Nonparametric Regression_, Cambridge
:    Univ. Press.

What is projection-pursuit regression ?
Forgive me if its in the book cited here, but I've never
heard heard of it and am just wondering whats the general idea.


------------------------------------------------
Chance Harris
Motorola Emerging Computing Operations
chance@wetware.sps.mot.com
#include<std_disclaimer.h>

