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!malgudi.oar.net!utnetw.utoledo.edu!news
From: dweddin@uoft02.utoledo.edu
Subject: Re: # of hidden nodes for Radial Basis Function Networks ?
Message-ID: <CyoGvH.5Bu@utnetw.utoledo.edu>
Lines: 21
Sender: news@utnetw.utoledo.edu (News Manager)
Organization: University of Toledo
References: <CyB9LI.LtK@utnetw.utoledo.edu> <38s1i2$4oj@newsbf01.news.aol.com>
Date: Wed, 2 Nov 1994 20:04:19 GMT

In Article <38s1i2$4oj@newsbf01.news.aol.com>
tiednbound@aol.com (TiedNBound) writes:
>In article <CyB9LI.LtK@utnetw.utoledo.edu>, dweddin@uoft02.utoledo.edu
>writes:
>
><but then
>I switched my method of selecting the centers and radii and drastically
>reduced the number of nodes in the hidden layer.>
>
>Ditto experience . . . the number of hidden nodes in RBF's is generally
>much less than required in backprop. 

Thank God!

Somebody else has the same RBF experience as me....i thought i was
going crazy!!!!  ;-)


don


