• DocumentCode
    886129
  • Title

    MOS circuit for nonlinear Hebbian learning

  • Author

    Cohen, M.H. ; Andreau, A.C.

  • Author_Institution
    John Hopkins Univ.,Baltimore, MD, USA
  • Volume
    28
  • Issue
    6
  • fYear
    1992
  • fDate
    3/12/1992 12:00:00 AM
  • Firstpage
    591
  • Lastpage
    593
  • Abstract
    An analogue MOS circuit that implements a nonlinear Hebbian learning rule is presented. The circuit has two differential inputs (voltages) and yields an output (current) which approximates the product of a cubic and a hyperbolic tangent function of the two input voltages. This has been successfully incorporated in an analogue integrated circuit implementation of the Herault-Jutten neuromorphic network.
  • Keywords
    MOS integrated circuits; linear integrated circuits; multiplying circuits; neural nets; Herault-Jutten neuromorphic network; analogue MOS circuit; analogue integrated circuit; circuit diagram; cubic function; differential inputs; hyperbolic tangent function; multiplying circuits; nonlinear Hebbian learning rule; two input voltages;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19920372
  • Filename
    126517
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=886129