• DocumentCode
    298838
  • Title

    Design of 2-D FIR filters by feedback neural networks

  • Author

    Bhattacharya, D. ; Antoniou, A.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
  • Volume
    2
  • fYear
    1995
  • fDate
    30 Apr-3 May 1995
  • Firstpage
    1297
  • Abstract
    A Hopfield-type neural network is proposed for the design of 2-D FIR filters. Given the amplitude response, the all-analog network computes the filter coefficients in real time. The network is simulated with HSPICE and a few examples are included to show that this is an efficient way of solving the approximation problem and has high potential for implementation in analog VLSI
  • Keywords
    FIR filters; Hopfield neural nets; SPICE; network synthesis; two-dimensional digital filters; 2D FIR filters; HSPICE simulation; Hopfield-type neural networks; amplitude response; analog VLSI; approximation problem; design; feedback neural networks; Computational modeling; Cost function; Finite impulse response filter; Frequency; Hopfield neural networks; Linear programming; Neural networks; Neurofeedback; Neurons; Transfer functions;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on
  • Conference_Location
    Seattle, WA
  • Print_ISBN
    0-7803-2570-2
  • Type

    conf

  • DOI
    10.1109/ISCAS.1995.520383
  • Filename
    520383