0
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found

      A Quantitative Study of Fault Tolerance, Noise Immunity, and Generalization Ability of MLPs

      1 , 1 , 1 , 1 , 1

      Neural Computation

      MIT Press - Journals

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          An analysis of the influence of weight and input perturbations in a multilayer perceptron (MLP) is made in this article. Quantitative measurements of fault tolerance, noise immunity, and generalization ability are provided. From the expressions obtained, it is possible to justify some previously reported conjectures and experimentally obtained results (e.g., the influence of weight magnitudes, the relation between training with noise and the generalization ability, the relation between fault tolerance and the generalization ability). The measurements introduced here are explicitly related to the mean squared error degradation in the presence of perturbations, thus constituting a selection criterion between different alternatives of weight configurations. Moreover, they allow us to predict the degradation of the learning performance of an MLP when its weights or inputs are deviated from their nominal values and thus, the behavior of a physical implementation can be evaluated before the weights are mapped on it according to its accuracy.

          Related collections

          Most cited references 13

          • Record: found
          • Abstract: not found
          • Article: not found

          Flat Minima

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Training with Noise is Equivalent to Tikhonov Regularization

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Sensitivity of feedforward neural networks to weight errors

                Bookmark

                Author and article information

                Journal
                Neural Computation
                Neural Computation
                MIT Press - Journals
                0899-7667
                1530-888X
                December 01 2000
                December 01 2000
                : 12
                : 12
                : 2941-2964
                Affiliations
                [1 ]Departamento de Arquitectura y Tecnologia de Computadores, Universidad de Granada, Spain
                Article
                10.1162/089976600300014782
                © 2000

                Comments

                Comment on this article