A neural network model of visual object recognition impairment after brain damage

N. Davey, R. Frank, T.M. Gale, S. George

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    35 Downloads (Pure)

    Abstract

    Dysfunction of the visual object recognition system in humans is briefly discussed and a basic connectionist model of visual object recognition is introduced. Experimentation in which two variants of this model are lesioned is undertaken. The results suggest that the well documented phenomenon of superordinate preservation is model independent. Differential category specific recognition deficits are also observed in this model, however these are sensitive to each particular variant.
    Original languageEnglish
    Title of host publicationIn: Procs of ICONIP 1998
    Pages1470-1473
    Publication statusPublished - 1998

    Fingerprint

    Dive into the research topics of 'A neural network model of visual object recognition impairment after brain damage'. Together they form a unique fingerprint.

    Cite this