Advertisement

A Dedicated Multi-Chip Programmable System for Cellular Neural Networks

  • Mario Salerno
  • Fausto Sargeni
  • Vincenzo Bonaiuto
Article

Abstract

Cellular Neural Networks (CNN's) represent a remarkable improvement in the hardware implementation of Artificial Neural Networks (ANN's). In fact, their regular structure and their local connectivity feature contribute to render this class of neural networks especially appealing for VLSI implementations. CNNs are widely applied in several fields, including image processing and pattern recognition. In this research, the authors already presented two fully digitally programmable CNN chips with 3×3 (3×3DPCNN chip) and 6×6 cells (6×6DPCNN chip) respectively. In this paper, a system with twenty of the latter chips will be presented. The main features of this electronic system consist of the full digital programmability of the templates, the digital input/output for logic operations, the analog outputs for dynamic analysis and the implementation of space-variant as well as space-invariant CNNs.

neural networks cellulan neural networks VLSI 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    L. O. Chua and L. Yang, “Cellular Neural Networks: Theory.” IEEE Trans. Circuits and Systems 32, pp. 1257–1272, 1988.Google Scholar
  2. 2.
    L. O. Chua and L. Yang, “Cellular Neural Networks: Applications.” IEEE Trans. Circuits and Systems 32, pp. 1273–1290, 1988.Google Scholar
  3. 3.
    L. O. Chua and T. Roska, “The CNN universal machine: an analogic array computer.” IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing 40(3), pp. 163–173, 1993.Google Scholar
  4. 4.
    T. Roska and J. A. Nossek (Eds), “Special Issue on Cellular Neural Networks.” IEEE Trans. on Circuits and Systems 40(3), 1993.Google Scholar
  5. 5.
    “Analogic CNN Program Library.” Version 6.2, DNS–7–1995, Analogic and Neural Computing Laboratory, Computer and Automation Inst., Hungarian Academy of Sciences, 1995.Google Scholar
  6. 6.
    J. M. Cruz and L. O. Chua, “A CNN chip for Connected Component Detection.” IEEE Trans. Circuits and Systems 38, pp. 812–817, 1991.Google Scholar
  7. 7.
    K. Halonen, V. Porra, T. Roska, and L. O. Chua, “Programmable analog VLSI CNN chip with local digital logic.” Int. Journal of Circuit Theory and Applications 20(5), pp. 573–582, 1992.Google Scholar
  8. 8.
    M. Anguita, F. J. Pelajo, A. Prieto, and J. Ortega, “Analog CMOS implementation of a discrete time CNN with Programmable Cloning Templates.” IEEE Trans. on Circuits and Systems 40(3), pp. 215–218, 1993.Google Scholar
  9. 9.
    P. Kinget and M. Steyaert, “A Programmable analog Cellular Neural Network CMOS chip for high speed image processing.” IEEE Journal of Solid-State Circuits 30(3), pp. 235, 243, March 1995.Google Scholar
  10. 10.
    A. Paasio, A. Dawidziuk, K. Halonen, and V. Porra, “Digitally controllable weights in current mode Cellular Neural Networks.” Proceedings of CNNA-94, pp. 73–77, 1994.Google Scholar
  11. 11.
    A. Paasio, A. Dawidziuk, K. Halonen, and V. Porra, “High speed 16 by 16 CNN chip.” IEEE Int. Symp.on Circuit and System (ISCAS-96) Atlanta GE, pp. 519–522, 1996.Google Scholar
  12. 12.
    A. Paasio, A. Dawidziuk, K. Halonen, and V. Porra, “Minimum Size 0.5 Micron CMOS Programmable 48 by 48 CNN Test Chip.” European Conference on Circuit Theory and Design (ECCTD'97) Budapest, pp. 154–156, 1997.Google Scholar
  13. 13.
    S. Espejo, R. Carmona, R. Dominguez-Castro, and A. Rodriguez-Vazquez, “CNN Universal Chip in CMOS technology.” Int. Journal on Circuit Theory and Applications Special Issue on CNN, part I, 24, pp. 93–111, 1996.Google Scholar
  14. 14.
    A. Rodriguez-Vazquez, S. Espejo, R. Dominguez-Castro, J. Huertas, and E. Sanchez-Sinencio, “Current-mode techniques for the implementation of continuous and discrete-time Cellular Neural Networks.” IEEE Trans. on Circuits and Systems-II 40, pp. 147–155, 1993.Google Scholar
  15. 15.
    F. Sargeni, “Digitally Programmable Transconductance Amplifier for CNN applications.” Electronics Letters 30(11), pp. 870–872, 1994.Google Scholar
  16. 16.
    F. Sargeni and V. Bonaiuto, “High performance digitally programmable CNN chip with discrete templates.” Proc. of CNNA-94 pp. 67–72.Google Scholar
  17. 17.
    M. Salerno, F. Sargeni, and V. Bonaiuto, “DPCNN: a modular chip for large CNN arrays.” IEEE Int. Conf. on Circ. and Sys.(ISCAS-95) Seattle, WA USA, pp. 417–420, 1995.Google Scholar
  18. 18.
    F. Sargeni and V. Bonaiuto, “A fully digitally programmable CNN chip.” IEEE Trans. on Circuits and Systems-II 42(11), pp. 741–745, 1995.Google Scholar
  19. 19.
    F. Sargeni and V. Bonaiuto, “A 3 × 3 digitally programmable CNN chip.” Int. Journal of Circuit Theory and App. 24(3), pp. 369–379, 1996.Google Scholar
  20. 20.
    M. Salerno, F. Sargeni, and V. Bonaiuto, “A 9 × 9 multi chip CNN board for Cellular Neural Networks.” Proc. of CNNA-96, 4th IEEE Int. Workshop on Cellular Neural Networks and their App Seville, Spain, pp. 261, 266, 1996.Google Scholar
  21. 21.
    M. Salerno, F. Sargeni, and V. Bonaiuto, “6 × 6DPCNN: a programmable mixed analog-digital chip for Cellular Neural Networks.” Proc. of CNNA-96 4th IEEE Int. Workshop on Cellular Neural Networks and their App Seville, Spain, pp. 451, 456, 1996.Google Scholar
  22. 22.
    M. Salerno, F. Sargeni, and V. Bonaiuto, “A 6 × 6 cells interconnection-oriented programmable chip for CNN.” to be appeared in Analog Integrated Circuits and Signal Processing.Google Scholar
  23. 23.
    Jose Pineda de Gyvez, E. Sanchez-Sincencio, and Gunhee Han, “Optimal Manufacturable CNN Array Size for Time Multiplexing Schemes.” Proc. of CNNA-96, 4th IEEE Int. Workshop on Cellular Neural Networks and their App. Seville, Spain, pp. 387, 392, 1996.Google Scholar
  24. 24.
    T. Matsumoto, L. O. Chua, and H. Suzuki, “CNN cloning template: connected component detector.” IEEE Transactions on Circuits and Systems 37(5), pp. 633–635, 1990.Google Scholar
  25. 25.
    H. Suzuki, T. Matsumoto, and L. O. Chua, “A CNN handwritten character recognizer.” Intern. Journal of Circuit Theory and Applications 20(5), pp. 601–612, 1992.Google Scholar
  26. 26.
    T. Matsumoto, L. O. Chua, and R. Furukawa, “CNN cloning template: hole-filler.” IEEE Transactions on Circuits and Systems 37(5), 635–638, 1990.Google Scholar
  27. 27.
    T. Matsumoto, L. O. Chua, and H. Suzuki, “CNN cloning template: shadow detector.” IEEE Transactions on Circuits and Systems 37(8), 1070–1073, 1990.Google Scholar
  28. 28.
    A. Radvànyi, “Using Cellular Neural Network to “See” Random-Dot-Stereograms.” Computer Analysis of Images and Patterns, Lecture Notes in Computer Science Springer Verlag, pp. 719, 1993.Google Scholar
  29. 29.
    P. L. Venetianer, F. Werblin, T. Roska, and L. O. Chua, “Analogic CNN algorithms for some image compression and restoration tasks.” IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications 42(5), pp. 278–284, 1995.Google Scholar

Copyright information

© Kluwer Academic Publishers 1999

Authors and Affiliations

  • Mario Salerno
    • 1
  • Fausto Sargeni
    • 1
  • Vincenzo Bonaiuto
    • 1
  1. 1.Department of Electronic EngineeringUniversity of Rome “Tor Vergata”RomeItaly

Personalised recommendations