• DocumentCode
    2754044
  • Title

    Real-time synthesis of FIR filters in frequency domain by feedback neural nets

  • Author

    Bhattacharya, Dipankar ; Antoniou, Andreas

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
  • Volume
    2
  • fYear
    1994
  • fDate
    3-5 Aug 1994
  • Firstpage
    1069
  • Abstract
    A Hopfield-type neural network is proposed for the synthesis of FIR filters. Given the amplitude response in the frequency domain the all-analog network computes the filter coefficients in real time. The network is simulated with HSPICE and two examples are included to show that this is an efficient way of computing filter coefficients compared to the standard techniques for FIR filter design
  • Keywords
    FIR filters; Hopfield neural nets; SPICE; active filters; analogue processing circuits; circuit CAD; frequency-domain synthesis; FIR filters; HSPICE; Hopfield-type neural network; all-analog network; amplitude response; feedback neural nets; filter coefficients; filter design; frequency domain; real-time synthesis; Computational modeling; Computer networks; Cost function; Feedback; Finite impulse response filter; Frequency domain analysis; Hopfield neural networks; Intelligent networks; Linear programming; Network synthesis; Neural networks; Neurofeedback; Neurons;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems, 1994., Proceedings of the 37th Midwest Symposium on
  • Conference_Location
    Lafayette, LA
  • Print_ISBN
    0-7803-2428-5
  • Type

    conf

  • DOI
    10.1109/MWSCAS.1994.518996
  • Filename
    518996