Path: utzoo!attcan!telly!lethe!torsqnt!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!uakari.primate.wisc.edu!aplcen!jhunix!ins_atge
From: ins_atge@jhunix.HCF.JHU.EDU (Thomas G Edwards)
Newsgroups: comp.ai.neural-nets
Subject: Re: Backprop Weight Initialization
Message-ID: <7069@jhunix.HCF.JHU.EDU>
Date: 7 Dec 90 09:09:47 GMT
References: <KOLEN-J.90Dec6152548@retina.cis.ohio-state.edu> <BELLIDO.90Dec6135649@aragorn.world> <8150@uwm.edu>
Organization: The Johns Hopkins University - HCF
Lines: 15

>In article <BELLIDO.90Dec6135649@aragorn.world> bellido@psych.stanford.edu writes:

>>What I think is really important is to find some way on wich
>>backpropagation can be made almost independent of this initial
>>configuration...

Any parallel, non-linear system will probably be chaotic with 
respect to its initial values.  However, methods which reduce the
total learning time may make such differences in learning time less
important.  I am curious how independed Cascade-Correlation
learning time is to initial weight conditions (although that is
a tougher question since you are continually adding new tiers of
initial weight all the time).

-Tom