Shift invariant pattern recognition by associative memory

Jennie Si, A. N. Michel

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

    Abstract

    We present a network architecture that can perform shif invariant patter recognition. The network is composed of a preprocessing block and an associative memory block (a recurrent neural network). The preprocessing network is designed in such a way that the output of this block is "almost" invariant under shifted input patters (i.e., initial conditions for the neural network). The assoiative memory block is employed to recall the original patterns stored in the system. A step by step design procedure for realizing shift invariant patter recognition is provided.

    Original languageEnglish (US)
    Title of host publication1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages2913-2916
    Number of pages4
    ISBN (Electronic)0780305930
    DOIs
    StatePublished - 1992
    Event1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 - San Diego, United States
    Duration: May 10 1992May 13 1992

    Publication series

    NameProceedings - IEEE International Symposium on Circuits and Systems
    Volume6
    ISSN (Print)0271-4310

    Conference

    Conference1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
    Country/TerritoryUnited States
    CitySan Diego
    Period5/10/925/13/92

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering

    Fingerprint

    Dive into the research topics of 'Shift invariant pattern recognition by associative memory'. Together they form a unique fingerprint.

    Cite this