Nonlinear Mappings with Cellular Neural Networks

  • J. Álvaro Fernández-Muñoz
  • Víctor M. Preciado-Díaz
  • Miguel A. Jaramillo-Morán
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4177)


In this paper, a general technique for automatically defining multilayer Cellular Neural Networks to perform Chebyshev optimal piecewise linear approximations of nonlinear functions is proposed. First, a novel CNN cell output function is proposed. Its main goal is to control input and output dynamic ranges. Afterwards, this 2-layer CNN is further programmed to achieve generic piecewise Chevyshev polynomials that approximate a nonlinear function.


Chebyshev Polynomial Piecewise Linear Function Output Image Cellular Neural Network Piecewise Linear Approximation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chua, L.O., Yang, L.: Cellular Neural Networks: Theory. IEEE Trans. Circ. Syst. 35(10), 1257–1272 (1988)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Chua, L.O., Yang, L.: Cellular Neural Networks: Applications. IEEE Trans. Circ. Syst. 35(10), 1273–1290 (1988)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Rodríguez, A., Linán, G., Carranza, L., Roca, E., Carmona, R., Jiménez, F., Domínguez, R., Espejo, S.: ACE16k: The Third Generation of Mixed-Signal SIMD-CNN ACE Chips Toward VSoCs. IEEE Trans. Circ. Syst. I: Reg. Papers 51(5), 851–863 (2004)CrossRefGoogle Scholar
  4. 4.
    Matsumoto, T., Chua, L.O., Furukawa, R.: CNN Cloning Template: Hole-Filler. IEEE Trans. Circ. Syst. 37(5), 635–638 (1990)CrossRefGoogle Scholar
  5. 5.
    Martinelli, G., Perfetti, R.: Generalized Cellular Neural Network for Novelty Detection. IEEE Trans. Circ. Syst. I: Fund. Theory Appl. 41(2), 187–190 (1994)CrossRefGoogle Scholar
  6. 6.
    Chua, L.O., Roska, T.: The CNN Paradigm. IEEE Trans. Circ. Syst. I: Fund. Theory Appl. 40(3), 147–156 (1993)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Jaramillo, M.A., Fernández, J.A.: Adaptive Adjustment of the CNN Output Function to Obtain Contrast Enhancement. In: Mira, J. (ed.) IWANN 1999. LNCS, vol. 1607, pp. 412–421. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  8. 8.
    Jain, A.K.: Fundamentals of Digital Image Processing. Prentice-Hall, Englewood Cliffs (1989)MATHGoogle Scholar
  9. 9.
    Fisher, R., Perkins, S., Walker, A., Wolfart, E.: Hypermedia Image Processing Reference (HIPR2). Web: University of Edinburgh, UK (2004),
  10. 10.
    Glaseby, C.A.: An Analysis of Histogram Based Thresholding Algorithms. Graph. Models Imag. Proc. 55, 532–537 (1993)CrossRefGoogle Scholar
  11. 11.
    Ter Brugge, M.H., Nijhuis, J.A.G., Spaanenburg, L.: Efficient DT-CNN Implementations for Large-neighborhood Functions. In: Proc. CNNA 1998, London, UK, pp. 88–93 (1998)Google Scholar
  12. 12.
    Kék, L., Zarándy, A.: Implementation of Large Neighborhood Non-Linear Templates on the CNN Universal Machine. Intl. J. Circuit Theory Appl. 26, 551–566 (1998)MATHCrossRefGoogle Scholar
  13. 13.
    Burden, R.L., Douglas, J.: Numerical Analysis. PWS Publishing Co., New York (1993)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • J. Álvaro Fernández-Muñoz
    • 1
  • Víctor M. Preciado-Díaz
    • 2
  • Miguel A. Jaramillo-Morán
    • 1
  1. 1.Dpto. Electrónica e Ing. Electromecánica, Escuela de Ingenierías IndustrialesUniversidad de ExtremaduraBadajozSpain
  2. 2.Laboratory for Electromagnetic and Electronic Systems (LEES)Massachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations