Neural networks: A principled perspective

Christopher M. Bishop

    Research output: Working paper › Technical report

    Abstract

    Introductory accounts of artificial neural networks often rely for motivation on analogies with models of information processing in biological networks. One limitation of such an approach is that it offers little guidance on how to find optimal algorithms, or how to verify the correct performance of neural network systems. A central goal of this paper is to draw attention to a quite different viewpoint in which neural networks are seen as algorithms for statistical pattern recognition based on a principled, i.e. theoretically well-founded, framework. We illustrate the concept of a principled viewpoint by considering a specific issue concerned with the interpretation of the outputs of a trained network. Finally, we discuss the relevance of such an approach to the issue of the validation and verification of neural network systems.
    Original languageEnglish
    Place of PublicationBirmingham
    PublisherAston University
    Number of pages9
    ISBN (Print)NCRG/95/014
    Publication statusPublished - Mar 1995

    Fingerprint

    Neural networks
    Pattern recognition

    Keywords

    • artificial neural networks
    • information processing
    • biological networks
    • optimal algorithms
    • correct performance
    • neural network systems
    • statistical pattern recognition
    • principled viewpoint
    • trained network
    • validation
    • verification

    Cite this

    Bishop, C. M. (1995). Neural networks: A principled perspective. Birmingham: Aston University.
    Bishop, Christopher M. / Neural networks: A principled perspective. Birmingham : Aston University, 1995.
    @techreport{5dad8fb7425d480a9761c5d7c80fa11a,
    title = "Neural networks: A principled perspective",
    abstract = "Introductory accounts of artificial neural networks often rely for motivation on analogies with models of information processing in biological networks. One limitation of such an approach is that it offers little guidance on how to find optimal algorithms, or how to verify the correct performance of neural network systems. A central goal of this paper is to draw attention to a quite different viewpoint in which neural networks are seen as algorithms for statistical pattern recognition based on a principled, i.e. theoretically well-founded, framework. We illustrate the concept of a principled viewpoint by considering a specific issue concerned with the interpretation of the outputs of a trained network. Finally, we discuss the relevance of such an approach to the issue of the validation and verification of neural network systems.",
    keywords = "artificial neural networks, information processing, biological networks, optimal algorithms, correct performance, neural network systems, statistical pattern recognition, principled viewpoint, trained network, validation, verification",
    author = "Bishop, {Christopher M.}",
    year = "1995",
    month = "3",
    language = "English",
    isbn = "NCRG/95/014",
    publisher = "Aston University",
    type = "WorkingPaper",
    institution = "Aston University",

    }

    Bishop, CM 1995 'Neural networks: A principled perspective' Aston University, Birmingham.

    Neural networks: A principled perspective. / Bishop, Christopher M.

    Birmingham : Aston University, 1995.

    Research output: Working paper › Technical report

    TY - UNPB

    T1 - Neural networks: A principled perspective

    AU - Bishop, Christopher M.

    PY - 1995/3

    Y1 - 1995/3

    N2 - Introductory accounts of artificial neural networks often rely for motivation on analogies with models of information processing in biological networks. One limitation of such an approach is that it offers little guidance on how to find optimal algorithms, or how to verify the correct performance of neural network systems. A central goal of this paper is to draw attention to a quite different viewpoint in which neural networks are seen as algorithms for statistical pattern recognition based on a principled, i.e. theoretically well-founded, framework. We illustrate the concept of a principled viewpoint by considering a specific issue concerned with the interpretation of the outputs of a trained network. Finally, we discuss the relevance of such an approach to the issue of the validation and verification of neural network systems.

    AB - Introductory accounts of artificial neural networks often rely for motivation on analogies with models of information processing in biological networks. One limitation of such an approach is that it offers little guidance on how to find optimal algorithms, or how to verify the correct performance of neural network systems. A central goal of this paper is to draw attention to a quite different viewpoint in which neural networks are seen as algorithms for statistical pattern recognition based on a principled, i.e. theoretically well-founded, framework. We illustrate the concept of a principled viewpoint by considering a specific issue concerned with the interpretation of the outputs of a trained network. Finally, we discuss the relevance of such an approach to the issue of the validation and verification of neural network systems.

    KW - artificial neural networks

    KW - information processing

    KW - biological networks

    KW - optimal algorithms

    KW - correct performance

    KW - neural network systems

    KW - statistical pattern recognition

    KW - principled viewpoint

    KW - trained network

    KW - validation

    KW - verification

    M3 - Technical report

    SN - NCRG/95/014

    BT - Neural networks: A principled perspective

    PB - Aston University

    CY - Birmingham

    ER -

    Bishop CM. Neural networks: A principled perspective. Birmingham: Aston University. 1995 Mar.

    Access to Document