Classification of handwritten digits using a RAM neural net architecture

    Research output: Contribution to journalConference articleResearchpeer-review

    Abstract

    Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature.
    Original languageEnglish
    JournalInternational Journal of Neural Systems
    Volume8
    Issue number1
    Pages (from-to)17-25
    ISSN0129-0657
    DOIs
    Publication statusPublished - Feb 1997
    Event2nd International Conference on Engineering Applications of Neural Networks - London, United Kingdom
    Duration: 17 Jun 199619 Jun 1996
    Conference number: 2

    Conference

    Conference2nd International Conference on Engineering Applications of Neural Networks
    Number2
    CountryUnited Kingdom
    CityLondon
    Period17/06/199619/06/1996

    Fingerprint

    Dive into the research topics of 'Classification of handwritten digits using a RAM neural net architecture'. Together they form a unique fingerprint.

    Cite this