Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!news.kei.com!simtel!harbinger.cc.monash.edu.au!bunyip.cc.uq.oz.au!munnari.oz.au!cs.mu.OZ.AU!munta.cs.mu.OZ.AU!schuller
From: schuller@munta.cs.mu.OZ.AU (Wayne Paul SCHULLER)
Subject: Using RPROP with cascade correlation
Message-ID: <9516618.5420@mulga.cs.mu.OZ.AU>
Sender: news@cs.mu.OZ.AU (CS-Usenet)
Organization: Computer Science, University of Melbourne, Australia
Date: Thu, 15 Jun 1995 08:38:02 GMT
Lines: 18

hi,

Has any one tried RPROP using cascade correlation.

The report for cc I have by Fahlmann et al. use quickprop probably
because quickprop was fahlmanns idea.

Yet the RPROP paper I have claims to be better than quickprop...

So has anyone tried CC with RPROP weight updates? is there a paper or 
something?

While I'm here, who currently has the best feed forward network for
the two spirals problem?

(CC is the best I've seen...)

wayne.
