A representation of representation applied to a discussion of variable binding

Richard Rohwer

    Research output: Chapter in Book/Published conference outputChapter

    Abstract

    States or state sequences in neural network models are made to represent concepts from applications. This paper motivates, introduces and discusses a formalism for denoting such representations; a representation for representations. The formalism is illustrated by using it to discuss the representation of variable binding and inference abstractly, and then to present four specific representations. One of these is an apparently novel hybrid of phasic and tensor-product representations which retains the desirable properties of each.
    Original languageEnglish
    Title of host publicationNeurodynamics and Psychology
    EditorsM. Oaksford, G. D. A. Brown
    PublisherAcademic Press
    Pages255-266
    Number of pages12
    ISBN (Print)0125235151
    Publication statusPublished - 4 Jan 1994
    EventNeuro Dynamics and Psychology -
    Duration: 4 Jan 19944 Jan 1994

    Other

    OtherNeuro Dynamics and Psychology
    Period4/01/944/01/94

    Bibliographical note

    Error in formula 25.

    Keywords

    • neural network
    • representation
    • variable binding
    • inference abstractly

    Fingerprint

    Dive into the research topics of 'A representation of representation applied to a discussion of variable binding'. Together they form a unique fingerprint.

    Cite this