Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!tut.cis.ohio-state.edu!retina.cis.ohio-state.edu!kolen-j From: kolen-j@retina.cis.ohio-state.edu (john kolen) Newsgroups: comp.ai.neural-nets Subject: Re: Backprop Weight Initialization Message-ID: Date: 6 Dec 90 20:25:48 GMT References: <16266@imag.imag.fr> <1990Dec6.161422.5314@cs.utk.edu> Sender: news@tut.cis.ohio-state.edu Organization: Ohio State Computer Science Lines: 23 In-reply-to: sfp@mars.ornl.gov's message of 6 Dec 90 16:14:22 GMT In article <1990Dec6.161422.5314@cs.utk.edu> sfp@mars.ornl.gov (Phil Spelt) writes: I remember seeing a reference to an aritcle which dealt with the effects of random initialization of weights in a backporpagation network. I believe the article reported that it *does* make a difference how the weight matrix is initialized. Jordan Pollack and I have a paper appearing in the current issue of Complex Systems (Vol 4, Num 3) titled, "Backpropagation is Sensitive to Initial Conditions" in which we demonstrate how small changes in the initial weights can have dramatic differences in convergence time and final solution weights. The take-home message was: save your initial weights if you want your work replicated. John Kolen ========================================================================== -- John Kolen (kolen-j@cis.ohio-state.edu)|computer science - n. A field of study Laboratory for AI Research |somewhere between numerology and The Ohio State Univeristy |astrology, lacking the formalism of the Columbus, Ohio 43210 (USA) |former and the popularity of the latter