Design of Robust Neural Network Classifiers

Jan Larsen, Lars Nonboe Andersen, Mads Hintz-Madsen, Lars Kai Hansen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    478 Downloads (Pure)


    This paper addresses a new framework for designing robust neural network classifiers. The network is optimized using the maximum a posteriori technique, i.e., the cost function is the sum of the log-likelihood and a regularization term (prior). In order to perform robust classification, we present a modified likelihood function which incorporates the potential risk of outliers in the data. This leads to the introduction of a new parameter, the outlier probability. Designing the neural classifier involves optimization of network weights as well as outlier probability and regularization parameters. We suggest to adapt the outlier probability and regularisation parameters by minimizing the error on a validation set, and a simple gradient descent scheme is derived. In addition, the framework allows for constructing a simple outlier detector. Experiments with artificial data demonstrate the potential of the suggested framework
    Original languageEnglish
    Title of host publicationAcoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
    Publication date1998
    ISBN (Print)0-7803-4428-6
    Publication statusPublished - 1998
    EventICASSP'98, IEEE Int.Conf. on Acoustics, Speech, and Signal Processing - Seattle, USA
    Duration: 1 Jan 1998 → …


    ConferenceICASSP'98, IEEE Int.Conf. on Acoustics, Speech, and Signal Processing
    CitySeattle, USA
    Period01/01/1998 → …

    Bibliographical note

    Copyright: 1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

    Fingerprint Dive into the research topics of 'Design of Robust Neural Network Classifiers'. Together they form a unique fingerprint.

    Cite this