Context dependent learning in neural networks

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    1 Citation (Scopus)
    49 Downloads (Pure)

    Abstract

    In this paper an extension to the standard error backpropagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to be trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.
    Original languageUndefined
    Title of host publicationFifth International Conference on Image Processing and Its Applications
    Place of PublicationPiscataway, NJ
    PublisherIEE
    Pages632-636
    Number of pages5
    ISBN (Print)0 85296 642 3
    DOIs
    Publication statusPublished - Jul 1995
    Event5th International Conference on Image Processing and its Applications 1995 - Edinburgh, United Kingdom
    Duration: 4 Jul 19956 Jul 1995
    Conference number: 5

    Publication series

    Name
    PublisherIEEE

    Conference

    Conference5th International Conference on Image Processing and its Applications 1995
    CountryUnited Kingdom
    CityEdinburgh
    Period4/07/956/07/95

    Keywords

    • SCS-Safety
    • IR-16549
    • AVR
    • Back propagation
    • multilayer feedforward neural networks
    • multilayer perceptrons
    • Neural Networks
    • average risk
    • context-dependent learning
    • feedforward neural nets
    • error backpropagation
    • error backpropagation learning rule
    • error function
    • EWI-1782
    • METIS-113434

    Cite this

    Spreeuwers, L. J., van der Zwaag, B. J., & van der Heijden, F. (1995). Context dependent learning in neural networks. In Fifth International Conference on Image Processing and Its Applications (pp. 632-636). Piscataway, NJ: IEE. https://doi.org/10.1049/cp:19950736
    Spreeuwers, Lieuwe Jan ; van der Zwaag, B.J. ; van der Heijden, Ferdinand. / Context dependent learning in neural networks. Fifth International Conference on Image Processing and Its Applications. Piscataway, NJ : IEE, 1995. pp. 632-636
    @inproceedings{3e7f69ba76cf48de95144816e4ea081d,
    title = "Context dependent learning in neural networks",
    abstract = "In this paper an extension to the standard error backpropagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to be trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.",
    keywords = "SCS-Safety, IR-16549, AVR, Back propagation, multilayer feedforward neural networks, multilayer perceptrons, Neural Networks, average risk, context-dependent learning, feedforward neural nets, error backpropagation, error backpropagation learning rule, error function, EWI-1782, METIS-113434",
    author = "Spreeuwers, {Lieuwe Jan} and {van der Zwaag}, B.J. and {van der Heijden}, Ferdinand",
    year = "1995",
    month = "7",
    doi = "10.1049/cp:19950736",
    language = "Undefined",
    isbn = "0 85296 642 3",
    publisher = "IEE",
    pages = "632--636",
    booktitle = "Fifth International Conference on Image Processing and Its Applications",

    }

    Spreeuwers, LJ, van der Zwaag, BJ & van der Heijden, F 1995, Context dependent learning in neural networks. in Fifth International Conference on Image Processing and Its Applications. IEE, Piscataway, NJ, pp. 632-636, 5th International Conference on Image Processing and its Applications 1995, Edinburgh, United Kingdom, 4/07/95. https://doi.org/10.1049/cp:19950736

    Context dependent learning in neural networks. / Spreeuwers, Lieuwe Jan; van der Zwaag, B.J.; van der Heijden, Ferdinand.

    Fifth International Conference on Image Processing and Its Applications. Piscataway, NJ : IEE, 1995. p. 632-636.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - Context dependent learning in neural networks

    AU - Spreeuwers, Lieuwe Jan

    AU - van der Zwaag, B.J.

    AU - van der Heijden, Ferdinand

    PY - 1995/7

    Y1 - 1995/7

    N2 - In this paper an extension to the standard error backpropagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to be trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.

    AB - In this paper an extension to the standard error backpropagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to be trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.

    KW - SCS-Safety

    KW - IR-16549

    KW - AVR

    KW - Back propagation

    KW - multilayer feedforward neural networks

    KW - multilayer perceptrons

    KW - Neural Networks

    KW - average risk

    KW - context-dependent learning

    KW - feedforward neural nets

    KW - error backpropagation

    KW - error backpropagation learning rule

    KW - error function

    KW - EWI-1782

    KW - METIS-113434

    U2 - 10.1049/cp:19950736

    DO - 10.1049/cp:19950736

    M3 - Conference contribution

    SN - 0 85296 642 3

    SP - 632

    EP - 636

    BT - Fifth International Conference on Image Processing and Its Applications

    PB - IEE

    CY - Piscataway, NJ

    ER -

    Spreeuwers LJ, van der Zwaag BJ, van der Heijden F. Context dependent learning in neural networks. In Fifth International Conference on Image Processing and Its Applications. Piscataway, NJ: IEE. 1995. p. 632-636 https://doi.org/10.1049/cp:19950736