• DocumentCode
    1228827
  • Title

    Long-term CMOS static storage cell performing AD/DA conversion for analogue neural network implementations

  • Author

    Heim, P. ; Jabri, Mohamed Ali

  • Author_Institution
    Dept. of Electr. Eng., Sydney Univ., NSW
  • Volume
    30
  • Issue
    25
  • fYear
    1994
  • fDate
    12/8/1994 12:00:00 AM
  • Firstpage
    2124
  • Lastpage
    2125
  • Abstract
    The authors describe a simple n-bit CMOS static storage cell intended to store and restore synaptic weights in neural network implementations. The principle is based on the successive approximation of the synaptic weight current with binary-weighted current sources, and the result is directly stored into standard static RAM cells. The cell restores a quantised value of the weight current to a common I/O access node by means of a mismatch-insensitive bidirectional current mirror
  • Keywords
    CMOS analogue integrated circuits; CMOS memory circuits; analogue-digital conversion; digital-analogue conversion; neural chips; random-access storage; AD/DA conversion; ADC; DAC; analogue neural network implementations; bidirectional current mirror; binary-weighted current sources; common I/O access node; long-term CMOS static storage cell; mismatch-insensitive current mirror; quantised value restoration; standard static RAM cells; successive approximation; synaptic weight current; synaptic weights storage;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19941480
  • Filename
    350155