Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!news.sprintlink.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Adaptive Activation Functions
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <D5t68F.C7w@unx.sas.com>
Date: Tue, 21 Mar 1995 20:57:51 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <3kn00p$roa@taloa.unice.fr> <D5sy7t.E8y@news.uwindsor.ca>
Organization: SAS Institute Inc.
Lines: 26


In article roa@taloa.unice.fr, destro@alto.unice.fr (Joao.DESTRO) writes:
|>     I have already spent quite a time in order to discover some
|> bibliography on adaptive activation functions.
|>     Unfortunately, I couldn't find anything.

Projection pursuit regression is a feedforward net with one hidden
layer and highly adaptive hidden activation functions.

   Friedman, J.H. and Stuetzle, W. (1981) "Projection pursuit regression,"
   J. of the American Statistical Association, 76, 817-823.

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

   Huber, P.J. (1985) "Projection pursuit," _Annals of Statistics_, 13,
   435-475.

   Jones, M.C. and Sibson, R. (1987), "What is projection pursuit?"
   J. of the Royal Statistical Society, Series A, 150, 1-38.

-- 

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.
