Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!samsung!zaphod.mps.ohio-state.edu!rpi!sarah!cs.albany.edu!berg From: berg@cs.albany.edu (George Berg) Newsgroups: comp.ai.neural-nets Subject: Re: Backprop Weight Initialization Message-ID: <268@daedalus.albany.edu> Date: 7 Dec 90 23:35:04 GMT References: <1990Dec6.161422.5314@cs.utk.edu> Reply-To: berg@daedalus.albany.edu.UUCP (George Berg) Organization: SUNY Albany, Comp. Sci. Dept. Lines: 23 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 >experience and have noted this defect (yes, it's not just a virtue). My >own simulator keeps track of the random seed used to initialize each >process. It may not fit your agenda, but a blanket dismissal of this work is utterly inappropriate. Since backpropagation is a widely-used technique, the *fact* that it is very sensitive to slight changes in initial conditions *is* important. Whether or not you view this property of bp as a "defect" or "virtue" is irrelevant. G.B. ------------------------------------------------------------------------------- | George Berg | Computer Science Dept. | "No one owes you; | | berg@cs.albany.edu | SUNY at Albany, LI 67A | You owe you." | | (518) 442 4267 | Albany, NY 12222 USA | | -------------------------------------------------------------------------------