Synaptic Weight Noise During MLP Learning Enhances Fault-Tolerance, Generalization and Learning Trajectory

By A. Murray, P. J. Edwards. 1992

Citations in the corpus

• Deep learning in neural networks: An overview (2014, methodology): “In a Bayesian framework (Bayes, 1763), weight decay can be derived (Hinton & van Camp, 1993) from Gaussian or Laplacian weight priors (Gauss, 1809; Laplace, 1774); see also Murray and Edwards (1993).”
• Flat Minima (1997, unknown): “…8 ij : v ij = w ij g. Flatness condition 1 is a \robustness condition" (or \fault tolerance condition", or \perturbation tolerance condition" { see, e.g., Minai & Williams, 1994; Murray & Edwards, 1993; Neti et al., 1992; Matsuoka, 1992; Bishop, 1993; Kerlirzin & Vallet, 1993; Carter et al., 1990).”