Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!uwm.edu!gem.mps.ohio-state.edu!ginosko!rex!uflorida!beach.cis.ufl.edu!tgk
From: tgk@beach.cis.ufl.edu (Tom Krajna)
Newsgroups: comp.ai.neural-nets
Subject: PDP Question
Message-ID: <20900@uflorida.cis.ufl.EDU>
Date: 19 Sep 89 20:29:00 GMT
Sender: news@uflorida.cis.ufl.EDU
Reply-To: tgk@beach.cis.ufl.edu ()
Organization: UF CIS Department
Lines: 21


I'm using version 1.1 of the PDP software.  When using the backprop
program (bp), the program runs until the total sum of squares (tss)
drops below a critical error level (ecrit).  At this point, if a
"test all" command (tall) is executed, and you test all the patterns,
the tss is no longer the same as the one which had just caused the
program to stop running.  (As a matter of fact, it seems to be the
"next" tss that would be calculated, if you ran all the patterns through
one more time, and adjusted the weights.)

Why is this a problem?  Sometimes, due to the meanderings of the
gradient descent, the "next" tss may be greater than the one which
was just low enough to meet the ecrit criterion.  So your net has
stopped, but statistically, it may not be a good enough fit.

Anyone have a solution or a work-around?
--

Tom Krajna		    UUCP:    ...gatech!uflorida!beach.cis.ufl.edu!tgk
University of Florida	    Internet: tgk@beach.cis.ufl.edu   CIS: 73267,1652
                            What's an analogy like?