A unipolar shift-invariant associative hamming net

Francis T.S. Yu, Guowen Lu, Chii Maw Uang, Shizhuo Yin, Zhongkong Wu

    Research output: Contribution to journalConference article

    Abstract

    Aunipolar shift-invariant associative Hamming net is described in this paper. The proposed Hamming net is a threelayer neural network, in which the first layer is a shift-invariant Hamming layer using unipolar interconnection weight matrix (IWM), the second layer is a winner-Take-All layer, and the last layer is a memory-mapping layer. In experiment, a hybrid optical architecture using photorefractive holograms is proposed.

    Original languageEnglish (US)
    Pages (from-to)294-301
    Number of pages8
    JournalProceedings of SPIE - The International Society for Optical Engineering
    Volume2237
    DOIs
    StatePublished - Mar 1 1994
    EventOptical Pattern Recognition V 1994 - Orlando, United States
    Duration: Apr 4 1994Apr 8 1994

    All Science Journal Classification (ASJC) codes

    • Electronic, Optical and Magnetic Materials
    • Condensed Matter Physics
    • Computer Science Applications
    • Applied Mathematics
    • Electrical and Electronic Engineering

    Fingerprint Dive into the research topics of 'A unipolar shift-invariant associative hamming net'. Together they form a unique fingerprint.

  • Cite this