Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!usc!samsung!olivea!uunet!munnari.oz.au!metro!macuni!sunb!lhamey From: lhamey@sunb.mqcc.mq.oz.au (Len Hamey) Newsgroups: comp.ai.neural-nets Subject: Re: Backprop Weight Initialization Message-ID: <880@macuni.mqcc.mq.oz> Date: 13 Dec 90 22:22:39 GMT References: <268@daedalus.albany.edu> Sender: news@macuni.mqcc.mq.oz Organization: Macquarie University, Sydney Lines: 17 In article bellido@psych.stanford.edu writes: [In response to John Kolen's posting] > >I saw that poster [Kolen and Pollack: "Back-propagation is Sensitive to > Initial Conditions"] also in last NIPS, but I don't believe this is very >important, I think all of us who work with backpropagation have these If you have not seen Kolen and Pollack's paper, then you should have a look at it (fetch it from cheops). Everyone knows that BP is sensitive to the starting point, but Kolen and Pollack show that the sensitivity has an unexpected Fractal nature. There are some really pretty pictures to look at too. It is not fair to dismiss a piece of work based only on a casual view of the title (although one is often forced to choose which sessions to attend at a conference on that basis alone :-( ). Disclaimer: I have no relationship with Kolen or Pollack except as a satisfied reader :-).