Handwritten digit recognition: a neural network demo

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

    4 Citations (Scopus)
    515 Downloads (Pure)


    A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen¿s self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task. Whereas the main goal was a purely educational one, a moderate recognition rate of 98% was reached on a test set.
    Original languageUndefined
    Title of host publicationComputational Intelligence: Theory and Applications, Proceedings of the International Conference 7th Fuzzy Days
    EditorsBernd Reusch
    Place of PublicationBerlin
    Number of pages10
    ISBN (Print)3 540 42732 5
    Publication statusPublished - Oct 2001
    EventComputational Intelligence: Theory and Applications, International Conference 7th Fuzzy Days - Dortmund, Germany
    Duration: 1 Oct 20013 Oct 2001

    Publication series

    NameLecture Notes in Computer Science


    ConferenceComputational Intelligence: Theory and Applications, International Conference 7th Fuzzy Days
    Other1-3 Oct 2001


    • METIS-200571
    • IR-42161
    • EWI-1775

    Cite this