This Article 
 Bibliographic References 
 Add to: 
Hyperneural Network-An Efficient Model for Test Generation in Digital Circuits
January 1996 (vol. 45 no. 1)
pp. 115-121

Abstract—This paper considers the problem of applying neural network for logic circuit testing and proposes an efficient method based on hyperneural network (HNN). The HNN uses an energy function that not only considers binary relations but also captures all higher order relations among N neurons. We illustrate the hyperneural concept using two formulations. First, a constraint engery function is defined and the gate model is obtained. Second, the Hopfield network is reformulated to generate the gate level hyperneural model. The gate level HNNs are used to give a mathematical form to the digital circuit that, in turn, requires optimization techniques to solve the test generation problem. We have used ISCAS'85 benchmark circuits to illustrate the method. Results are compared with those obtained from PODEM, MODEM, and FAN.

[1] P.R. Bhattacharjee,S.K. Basu, and J.C. Paul,"Translation of the problem of complete test set generation of pseudo-Boolean programming," IEEE Trans. Computers, vol. 40, pp. 864-866, July 1991.
[2] N.N. Biswas,Introduction to Logic and Switching Theory.New York: Gordon and Breach, 1975.
[3] S. Chakradhar,V.D. Agrawal, and M. Bushnell,Neural Models and Algorithms for Digital Testing.Boston: Kluwer Academic, 1991.
[4] P. Goel,"An implicit enumeration algorithm to generate tests for combinational logic circuits," IEEE Trans. Computers, vol. 30, pp. 215-222, Mar. 1981.
[5] K.D. Heidtmann,"Arithmetic spectrum applied to fault detection for combinational circuits," IEEE Trans. Computers, vol. 40, pp. 320-324, Mar. 1991.
[6] J.J. Hopfield and D.W. Tank,"Neural computation of decisions in optimization problems," Biol. Cyber., vol. 52, pp. 141-152, 1985.
[7] Open Architecture Silicon Implementation Software Manual, MCNC, North Carolina, Ver. 2.0, 1992.
[8] H. Fujiwara,"Three-valued neural networks for test generation," Int'l Conf. Fault Tolerant Computing, pp. 64-71, 1990.
[9] H. Fujiwara,"FAN: A fast test generation system for VLSI circuits," Research Reports of the Faculty of Eng., Meiji Univ., vol. 50, 1986.
[10] W. Kunz and D.K. Pradhan, Recursive Learning: A New Implication Technique for Efficient Solution to CAD Problems Test, Verification and Optimization IEEE Trans. Computer-Aided Design, pp. 1143-1158, Sept. 1994.
[11] T. Larrabee,"Efficient generation of test patterns using Boolean difference," Proc. 1989 Int'l Test Conf., pp. 795-809.
[12] T. Lengauer, Combinatorial Algorithms for Integrated Circuit Layout. Chichester, U.K.: Wiley, 1990.
[13] J. Ortega et al., "Generalized Hopfield neural network for concurrent testing," IEEE Trans. Computers, vol. 42, pp. 898-912, Aug. 1993.
[14] D.A. Pierre,Optimization Theory with Applications.New York: Dover Publications, Inc., 1986.
[15] S. Wolfram,Mathematica.Reading, Mass.: Addison-Wesley, 1991.
[16] S. Rai,"Hyperneural network—A new model for test generation in combinational circuits," Technical report, Electrical and Computer Eng. Dept., Louisiana State Univ., July 1993.

Index Terms:
Hyperneural model, logic circuit testing. neural network, NP-completeness, optimization, pseudo-Boolean programming, satisfiability problem.
Suresh Rai, Weian Deng, "Hyperneural Network-An Efficient Model for Test Generation in Digital Circuits," IEEE Transactions on Computers, vol. 45, no. 1, pp. 115-121, Jan. 1996, doi:10.1109/12.481493
Usage of this product signifies your acceptance of the Terms of Use.