Simulation of ATPG neural network and its experimental results

  • Zhang Zhong 
Regular Papers


This paper first establishes a neural network model for logic circuits from the truth table by using linear equations theory, presents a kind of ATPG neural network model, and investigates energy local minima for the network. And then, it proposes the corresponding techniques to reduce the number of energy local minima as well as some approaches to escaping from local minimum of energy. Finally, two simulation systems, the binary ATPG neural network and the continuous ATPG neural network, are implemented on SUN 3/260 workstation in C language. The experimental results and their analysis and discussion are given. The preliminary experimental results show that this method is feasible and promising.


Neural networks logic circuits automatic test pattern generation (ATPG) local minimum linear equations theory 


  1. [1]
    Agrawal V D, Seth S C. Test Generation for VLSI Chips. IEEE Computer Press, Washington D.C., 1988.Google Scholar
  2. [2]
    Yau S S, Tang Y S. An efficient algorithm for generating complete test sets for combinational logic circuits.IEEE Trans. on Computers, 1971, C-20: 1245–1251.MATHCrossRefMathSciNetGoogle Scholar
  3. [3]
    Roth J P, Bouricious W G. Programmed algorithms to computer tests to detect and distinguish between failures in logic circuits.IEEE Trans. Election. Computers, 1967, EC-16(10): 567–580.CrossRefGoogle Scholar
  4. [4]
    Goel P. An implicit enumeration algorithm to generate tests for combinational logic circuits.IEEE Trans. on Computers, 1981, C-30(3): 215–222.MATHCrossRefMathSciNetGoogle Scholar
  5. [5]
    Fujiwara H, Snimono T. On the acceleration of test generation algorithms.IEEE Trans. on Computers, 1983, C-32(12): 1137–1144.CrossRefGoogle Scholar
  6. [6]
    Khanna T. Foundations of Neural Networks. Addison-Wesley Publishing Company, Inc., 1990.Google Scholar
  7. [7]
    Abu-Mostafa Y S. Neural Networks for Computing? Neural Networks for Computing (Snow-bird). Denker J S (ed.), American Institute of Physics, New York, 1986, pp. 1–6.Google Scholar
  8. [8]
    Chakradhar S T, Bushnell M L, Agrawal V D. Toward massively parallel automatic test generation.IEEE Trans. on CAD, 1990, 9(9): 981–994.Google Scholar
  9. [9]
    Chakradhar S T, Bushnell M L, Agrawal V D. Neural net and Boolean satisfiability models of logic circuits.IEEE Design and Test of Computers, 1990, 7(5): 54–57.CrossRefGoogle Scholar
  10. [10]
    Chakradhar S T, Bushnell M L, Agrawal V D. Automatic test generation using neural networks. InProc. Int. Conf. on CAD, pp. 416–419, Nov. 1988.Google Scholar
  11. [11]
    Fujiwara H. Three-valued neural networks for test generation. InProc. 20-th Fault-Tolerant Computing Symposium, pp. 64–71, 1990.Google Scholar
  12. [12]
    Chakradhar S T, Bushnell M L, Agrawal V D. Automatic test generation using quadratic 0–1 programming. InProc. 27-th ACM/IEEE Design Automation Conference, pp. 654–659, 1990.Google Scholar
  13. [13]
    Zhang Zhong. New Testing Methods for Digital Circuits and Their Simulation Experiments. Ph.D. Dissertation, Institute of Computing Technology, The Chinese Academy of Sciences, 1991.Google Scholar
  14. [14]
    Zhang Zhong and Wei Daozheng. Neural network model for logic circuits.Acta Electronica Sinica, 1993, 21(8): 77–81. (in Chinese).MathSciNetGoogle Scholar
  15. [15]
    Zhang Zhong. Modelling the neural network for logic circuits by linear equations theory. InProc. 9th National Conference on Pattern Recognition and Artificial Intelligence, pp. 331–339, 1993. (in Chinese)Google Scholar
  16. [16]
    Zhang Zhong, Dai Ruwei. Necessary and sufficient condition for the existence of neural network model of logic circuits. InProc. of World Congress on Neural Networks, San Diego, U.S.A., Vol.II, pp.491–497, 1994.Google Scholar
  17. [17]
    Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. InProc. of Natl. Acad. Sci. USA, Vol.79, pp.2554–2558, 1982.Google Scholar
  18. [18]
    Hopfield J J. Neurons with graded response have collective computational properties like those of two-State neurons. InProc. of Natl. Acad. Sci. USA, Vol. 81, pp.3088–3092, 1984.Google Scholar
  19. [19]
    Hopfield J J. Neural computation of decisions in optimization problems.Biological Cybernetics, Vol. 52, pp.141–152, 1985.MATHMathSciNetGoogle Scholar
  20. [20]
    Hopfield J J. Artificial neural networks.IEEE Circuits and Devices Magazine, 1987, 4(5): 3–10.CrossRefMathSciNetGoogle Scholar
  21. [21]
    Takeda M, Goodman J W. Neural ntworks for cmputation: Number representations and programming complexity.Applied Optics, 1986, 25(18): 3033–3046.CrossRefGoogle Scholar

Copyright information

© Science Press, Beijing China and Allerton Press Inc. 1995

Authors and Affiliations

  • Zhang Zhong 
    • 1
  1. 1.National Research Center for Intelligent Computing SystemsBeijing

Personalised recommendations