Path: utzoo!censor!geac!torsqnt!news-server.csri.toronto.edu!rutgers!usc!chaph.usc.edu!aludra.usc.edu!manjunat From: manjunat@aludra.usc.edu (bsm) Newsgroups: comp.ai.neural-nets Subject: Re: Backprop Weight Initialization Message-ID: <13534@chaph.usc.edu> Date: 8 Dec 90 17:49:47 GMT References: <268@daedalus.albany.edu> Sender: news@chaph.usc.edu Organization: University of Southern California, Los Angeles, CA Lines: 28 Nntp-Posting-Host: aludra.usc.edu In article bellido@psych.stanford.edu writes: > > >Also markh@csd4.csd.uwm.edu (Mark William Hopkins) says: > >>I know this may not sound like much, but one sure bet is to initialize the >>weights close to their final values... :) >> >>Other than that, it really sounds like an impossible problem. Think of what >>would happen if the error function looked like a lunar surface with billions >>of craters deep and shallow all over the place. >> >>Doing backpropagation on it would be like trying to find a real 'deep' crater >>on the moon by riding a lunar rover constantly downhill from where the lunar >>lander set down. You really have to be near the crater to find it, else it >>could be on the other size of the moon... > >I like this analogy about the moon surface. More than that, its >worse because we search on a different moon eachtime we begin a search. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ No ! We start at a different location on the SAME moon (unless ofcourse you start on a different problem (meaning, a different surface, different moon). > > Ignacio >-- Manjunath