Training with noise is equivalent to Tikhonov regularization

Christopher M. Bishop

    Research output: Contribution to journalArticlepeer-review

    Abstract

    It is well known that the addition of noise to the input data of a neural network during training can, in some circumstances, lead to significant improvements in generalization performance. Previous work has shown that such training with noise is equivalent to a form of regularization in which an extra term is added to the error function. However, the regularization term, which involves second derivatives of the error function, is not bounded below, and so can lead to difficulties if used directly in a learning algorithm based on error minimization. In this paper we show that, for the purposes of network training, the regularization term can be reduced to a positive definite form which involves only first derivatives of the network mapping. For a sum-of-squares error function, the regularization term belongs to the class of generalized Tikhonov regularizers. Direct minimization of the regularized error function provides a practical alternative to training with noise.
    Original languageEnglish
    Pages (from-to)108-116
    Number of pages9
    JournalNeural Computation
    Volume7
    Issue number1
    Publication statusPublished - Jan 1995

    Keywords

    • noise
    • neural network
    • performance
    • error regularization
    • learning algorithm
    • network training
    • mapping
    • Tikhonov regularizer

    Fingerprint

    Dive into the research topics of 'Training with noise is equivalent to Tikhonov regularization'. Together they form a unique fingerprint.

    Cite this