Path: utzoo!attcan!uunet!lll-winken!ames!purdue!bu-cs!bucsb!adverb
From: adverb@bucsb.UUCP (Josh Krieger)
Newsgroups: comp.ai.neural-nets
Subject: ART and non-stationary environments
Keywords: ART
Message-ID: <2503@bucsb.UUCP>
Date: 27 Apr 89 20:40:50 GMT
Reply-To: adverb@bucsb.bu.edu (Josh Krieger)
Organization: Boston Univ Comp. Sci.
Lines: 9

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.

-- Josh Krieger