Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ucbvax!hplabs!gatech!myke
From: myke@gatech.edu (Myke Reynolds)
Newsgroups: comp.ai.neural-nets
Subject: Re: ART and non-stationary environments
Keywords: ART
Message-ID: <18583@gatech.edu>
Date: 28 Apr 89 23:56:08 GMT
References: <2503@bucsb.UUCP>
Reply-To: myke@gatech.UUCP (Myke Reynolds)
Organization: School of Information and Computer Science, Georgia Tech, Atlanta
Lines: 19

In article <2503@bucsb.UUCP> adverb@bucsb.bu.edu (Josh Krieger) writes:
>I think it's important to say one last thing about ART:
>
>ART is primarily usefull in a statistically non-stationary environment
>because its learned categories will not erode with the changing input.
>If your input environment is stationary, then there may be little reason
>to use the complex machinery behind ART; your vanilla backprop net will
>work just fine.
>
BAM is a the stationary version of ART, and blows backprop out of the
water in both power and simplicity. Its less than a linear equation solver,
but thats enough to out-preform backprop.
That backprop is not much worse, is not only wrong, it makes for a skimpy
last ditch effort to argue for a model that has no other defense.
-- 
Myke Reynolds
School of Information & Computer Science, Georgia Tech, Atlanta GA 30332
uucp:	...!{decvax,hplabs,ncar,purdue,rutgers}!gatech!myke
Internet:	myke@gatech.edu