Neural networks can be used for image classification. They are powerful instruments in image and pattern recognition because they have following advantages: parallel structure, training in the process of the classifier preparation, and possibility to implement them as an electronic circuit. A special type of neural classifier, LIRA (Limited Receptive Area) neural classifier, has been developed and used to solve different tasks, for example, handwritten digit recognition, face recognition, texture and shape recognition, etc. It is important to reduce the time of system work so the neural classifier was implemented in a FPGA device.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    FPGA Based LIRA Neural Classifier


    Contributors:
    Vega, A. (author) / Baidyk, T. (author) / Kussul, E. (author) / Silva, J. L. P. (author)


    Publication date :

    2011-11-01


    Size :

    899869 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Lira lir : tretʹja kniga stikhov

    Bobrov, Sergej P. | TIBKAT | 1917


    Apollo Fanciullo con Lira Tav. XVII

    DataCite | 1804

    Free access



    Modeling using the LIRA 9.6 software package of contact interaction of the retaining wall with the base

    Radomir Timchenko / Dmytro Krishko / Volodymyr Savenko | DOAJ | 2019

    Free access