@Bibtex-file{Neural/soft-share.bib,
  title =        "Bibliography of the paper {"}Simplifying Neural
                 networks by Soft Weight-Sharing{"}",
  author-1 =     "Steven J. Nowlan",
  address-1 =    "Computational Neurobiology Laboratory\\The Salk
                 Institute\\P.O. Box 85800\\San Diego, CA 92186-5800,
                 USA",
  author-2 =     "Geoffrey E. Hinton",
  address-2 =    "Department of Computer Science \\ University of
                 Toronto \\ Toronto, Canada M5S 1A4",
  supported =    "gone",
  abstract =     "Abstract of {"}\htmladdnormallink{Simplifying Neural
                 networks by Soft Weight-Sharing}
                 {ftp://archive.cis.ohio-state.edu/pub/neuroprose/nowlan.soft-share.ps.Z}{"}:\par
                 One way of simplifying neural networks so they
                 generalize better is to add an extra term to the error
                 function that will penalize complexity. Simple versions
                 of this approach include penalizing the sum of the
                 squares of the weights or penalizing the number of
                 non-zero weights. We propose a more complicated penalty
                 term in which the distribution of weight values is
                 modelled as a mixture of multiple gaussians. A set of
                 weights is simple if the weights have high probability
                 densities under the mixture model. This can be achieved
                 by clustering the weights into subsets with the weights
                 in each cluster having very similar values. Since we do
                 not know the appropriate means or variances of the
                 clusters in advance, we allow the parameters of the
                 mixture model to adapt at the same time as the network
                 learns. Simulations on two different problems
                 demonstrate that this complexity term is more effective
                 than previous complexity terms.",
}