# Behavioral Simulation of Densely-Connected Analog Cellular Array Processors for High-Performance Computing

## Abstract

The analog cellular neural network (CNN) model is a powerful parallel processing paradigm in solving many scientific and engineering problems. The network consists of densely-connected analog computing cells. Various applications can be accomplished by changing the local interconnection strengths, which are also called coefficient templates. The behavioral simulator could help designers not only gain insight on the system operations, but also optimize the hardware-software co-design characteristics. An unique feature of this simulator is the hardware annealing capability which provides an efficient method of finding globally optimal solutions. This paper first gives an overview of the cellular network paradigm, and then discusses the nonlinear integration techniques and related partition issues, previous work on the simulator and our own simulation environment. Selective simulation results are also presented at the end.

## Keywords

Cellular Network Cellular Neural Network IEEE International Workshop VLSI System Behavioral Simulation## Preview

Unable to display preview. Download preview PDF.

## References

- 1..L. O. Chua and L. Yang, “Cellular neural networks: Theory.”
*IEEE Trans, on Circuits and Systems*35, pp. 1257–1272, Oct. 1988.MathSciNetMATHCrossRefGoogle Scholar - 2.L. O. Chua and L. Yang, “Cellular neural networks: Applications.”
*IEEE Trans, on Circuits and Systems*35, pp. 1273–1290, Oct. 1988.MathSciNetCrossRefGoogle Scholar - 3.C. Mead,
*Analog VLSI and Neural Systems*. Addison Wesley, 1989.MATHGoogle Scholar - 4.L. O. Chua and T. Roska, “The CNN paradigm.”
*IEEE Trans. on Circuits and Systems I*40, pp. 147–156, Mar. 1993.MathSciNetMATHCrossRefGoogle Scholar - 5.K. R. Crounse, T. Roska and L. O. Chua, “Image halftoning with cellular neural networks.”
*IEEE Trans, on Circuits and Systems II*40, pp. 267–283, Apr. 1993.MATHCrossRefGoogle Scholar - 6.T. Sziranyi and J. Csicsvari, “High-speed character recognition using a dual cellular neural network architecture.”
*IEEE Trans. on Circuits and Systems II*40, pp. 223–231, Mar. 1993.MATHCrossRefGoogle Scholar - 7.A. G. Radvanyi, “A dual CNN model of cyclopean perception and its application potentials in artificial stereopsis,” in
*IEEE Proc. of Workshop on Cellular Neural Networks and Applications*, Munich, Germany, Oct. 1992, pp. 222–227.Google Scholar - 8.T. W. Berger, B. J. Sheu and R. H.-K. Tsai, “Analog VLSI implementation of a nonlinear systems model of the Hippocampal brain region,” in
*Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)*, December, 1994, pp. 47–51.CrossRefGoogle Scholar - 9.A. Jacobs, T. Roska and F. Werblin, “Techniques for constructing physiologically motivated neuromorphic models in CNN,” in
*Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)*, December, 1994, pp. 53–58.CrossRefGoogle Scholar - 10.S. H. Bang, “Performance optimization in cellular neural network and associated VLSI architectures,” SIPI Technical Report #268, Dept. of EE, University of Southern California, 1994.Google Scholar
- 11.B. J. Sheu and J. Choi,
*Neural Information Processing and VLSI*. Kluwer Academic Publishers: Boston, MA, 1995. in*Cellular Neural Networks*, edited by T. Roska and J. Vandewalle, Wiley, 1993.Google Scholar - 12.W. H. Press, B. P. Flannery, S. A. Teukolsky and W. T. Vetterling,
*umerical Recipes in C*.Cambridge University Press, 1988.Google Scholar - 13.J. M. Ortega and W. G. Poole, Jr.,
*Introduction to Numerical Methods for Differential Equations*Pitman Publishing Inc., 1981.MATHGoogle Scholar - 14.“Cellular Neural Network Simulator User’s Manual, ver. 3.6,”Google Scholar
- 15.Jose Pineda de Gyvez, “XCNN: A software package for color image processing,” in
*Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)*, December, 1994, pp. 219–234.CrossRefGoogle Scholar - 16.R. Domínguez-Castro, S. Espejo, A. Rodriguez-Vázquez, I. García-Vargas, J. F. Ramos and R. Carmona, “SIRENA: A simulation environment for CNNs,” in
- 17.The simulator is written by J. A. Osuna. Additional information can be found by ftp:/ife.ethz.ch/pub/NeuroBasic.Google Scholar
- 18.S. Espejo,
*VLSI Design and Modeling of CNNs*. Ph.D. Dissertation, University of Sevilla, Spain, Apr. 1994.Google Scholar - 19.T. Roska, “CNN analogic (dual) software library.” Internal Report DNS-1–1993, Computer and Automation Institute, Hungarian Academy of Science, Jan. 1993.Google Scholar
- 20.S. Bang, B.J. Sheu and T. H. Wu “Optimal solutions for cellular neural networks by paralleled hardware annealing,” accepted by
*IEEE Trans, on Neural Networks*.Google Scholar - 21.T. Matsumoto, L. O. Chua and H. Suzuki, “CNN cloning template: connected component detector.”
*IEEE Trans, on Circuits and Systems*37, pp. 663–635, May 1990.MathSciNetCrossRefGoogle Scholar - 22.T. Matsumoto, L. O. Chua and R. Furukawa, “CNN cloning template: Hole filler.”
*IEEE Trans, on Circuits and Systems*37, pp 635–638, May 1990.CrossRefGoogle Scholar - 23.M. J. Ogorzalek, A. Dabrowski and W. Dabrowski, “Hyper-chaos, clustering and cooperative phenomena in CNN arrays composed of chaotic circuits,” in
- 24.L. O. Chua, G.-N. Lin, “Canonical Realization of Chua’s Circuits Family.”
*IEEE Trans, on Circuits and Systems*37(7) pp. 885–902,1990.MathSciNetMATHCrossRefGoogle Scholar - 25.R. A. Saleh,
*iSPUCES Version 3 User’s Guide*. Dept. of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign.Google Scholar