BIROn - Birkbeck Institutional Research Online

    Reliable estimation of a neural network’s domain of validity through interval analysis based inversion

    Adam, S.P. and Karras, D.A. and Magoulas, George D. and Vrahatis, M.N. (2015) Reliable estimation of a neural network’s domain of validity through interval analysis based inversion. In: 2015 International Joint Conference on Neural Networks (IJCNN), 12-17 July 2015, Killarney.

    [img]
    Preview
    Text
    AKMV_IJCNN_paper.pdf - Published Version of Record

    Download (565kB) | Preview

    Abstract

    Reliable estimation of a neural network’s domain of validity is important for a number of reasons such as assessing its ability to cope with a given problem, evaluating the consistency of its generalization etc. In this paper we introduce a new approach to estimate the domain of validity of a neural network based on Set Inversion Via Interval Analysis (SIVIA), the methodology established by Jaulin andWalter [1]. This approach was originally introduced in order to solve nonlinear parameter estimation problems in a bounded error context and proved to be effective in tackling several types of problems dealing with nonlinear systems analysis. The dependence of a neural network output on the pattern data is a nonlinear function and hence derivation of the impact of the input data to the neural network function can be addressed as a nonlinear parameter estimation problem that can be tackled by SIVIA. We present concrete application examples and show how the proposed method allows to delimit the domain of validity of a trained neural network. We discuss advantages, pitfalls and potential improvements offered to neural networks.

    Metadata

    Item Type: Conference or Workshop Item (Paper)
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Research Centres and Institutes: Birkbeck Knowledge Lab
    Depositing User: George Magoulas
    Date Deposited: 12 Feb 2016 09:57
    Last Modified: 09 Aug 2023 12:37
    URI: https://eprints.bbk.ac.uk/id/eprint/14187

    Statistics

    Activity Overview
    6 month trend
    358Downloads
    6 month trend
    286Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item