This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Fault-Tolerant Design of Neural Networks for Solving Optimization Problems
December 1996 (vol. 45 no. 12)
pp. 1450-1455

Abstract—First, the incorporation of the alternative ways of representing the solution to the traveling salesman problem by neural network is proposed to deal with the asymmetric tolerance of neural networks to unidirectional faults. Next, in order to cope with the simultaneous occurrence of a s-a-0 and s-a-1 faults, the triplication scheme with a proper merging function is considered. Finally, the combination of the alternative representations and the triplication scheme is used.

[1] J.J. Hopfield, "Neural Networks and Physical Systems with Emergent Collective Computational Ability," Proc. Nat'l Academy of Science,USA, vol. 79, pp. 2,254-2,558, Apr. 1982.
[2] S.E. Fahlman and G.E. Hinton, "Massively Parallel Architecture for AI: NETL, Thistle, and Boltzmann Machines," Proc. Nat'l Conf. Artificial Intelligence (AAAI-83), pp. 109-113, 1983.
[3] J.J. Hopfield, "Neurons with Graded Response have Collective Computational Properties Like Those of Two-State Neurons," Proc. Nat'l Academy of Science,USA, vol. 81, pp. 3,088-3,092, May 1984.
[4] J.J. Hopfield and D.W. Tank, "Neural Computation of Decisions in Optimization Problems," Biological Cybernetics, vol. 52, pp. 141-152, 1985.
[5] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, "Learning Internal Representations by Error Propagation," Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations, D.E. Rumelhart and J.L. McClelland et al., eds., chapter 8, pp. 318-362.Cambridge, Mass.: MIT Press, 1986.
[6] L.A. Belfore II, B.W. Johnson, and J.H. Aylor, "The Design of Inherently Fault-Tolerant Systems," Concurrent Computations—Algorithms, Architectures, and Technology, chapter 28, pp. 565-583.New York: Plenum Press, 1988.
[7] G.V. Wilson and G.S. Pawley, "On the Stability of the Travelling Salesman Problem Algorithm of Hopfield and Tank," Biological Cybernetics, vol. 58, pp. 63-70, 1988.
[8] Y. Akiyama, A. Yamashita, M. Kajiura, and H. Aiso, "Combinational Optimization with Gaussian Machines," Proc. Int'l Joint Conf. Neural Networks (IJCNN-89), pp. I-533-540, 1989.
[9] J.A.G. Nijhuis and L. Spaanenburg, "Fault-Tolerance of Neural Associative Memories," IEE Proc., vol. 36-E, no. 5, pp. 389-394, Sept. 1989.
[10] G. Swaminathan, S. Srinivasan, S. Mitra, J. Minnix, B. Johnson, and R.M. Inigo, "Fault Tolerance in Neural Networks," Proc. IJCNN-90, pp. II-699-702, 1990.
[11] J. Nijhuis, B. Höffinger, A. van Schaik, and L. Spaanenburg, "Limit to the Fault-Tolerance of a Feedforward Neural Network with Learning," Proc. FTCS-20, pp. 228-235, June 1990.
[12] P.W. Protzel and M. Arras, "Fault-Tolerance of Optimization Networks," Proc. IJCNN90, pp. I-455-458, 1990.
[13] P.W. Protzel, D.L. Palumbo, and M. Arras, "Performance and Fault-Tolerance of Neural Networks for Optimization," ICASE Report No. 91-45/NASA Contractor Report 187582, ICASE/NASA Langley Research Center, June 1991.
[14] J. Hertz, A. Krogh, and R.G. Palmer, Introduction to the Theory of Neural Computation. Addison-Wesley, 1991.
[15] S.P. Eberhart, D. Daud, D.A. Kerns, T.X. Brown, and A.P. Thakoor, "Competitive Neural Architecture for Hardware Solution to the Assignment Problem," Neural Networks, vol. 4, pp. 431-442, 1991.
[16] Y. Koyanagi and Y. Tohma, "Fault Tolerant Neural Networks in Optimization Problems," Proc. FTCS-22, pp. 412-418, July 1992.
[17] R. Geist and D. Suggs, "Neural Networks for the Design of Distributed, Fault-Tolerant, Computing Environment," Proc. 11th Symp. Reliable Distributed Systems,Houston, pp. 189-195, Oct. 1992.
[18] Y. Tohma and Y. Koyanagi, "Design of Neural Networks to Tolerate the Mixture of Two Types of Faults," Proc. 23rd Int'l Symp. Fault-Tolerant Computing (FTCS-23), pp. 268-278,Toulouse, June22-24, 1993.

Index Terms:
Fault tolerance, unidirectional fault, mixed stuck-type fault, neural network, optimization problem.
Citation:
Yoshihiro Tohma, Yoichi Koyanagi, "Fault-Tolerant Design of Neural Networks for Solving Optimization Problems," IEEE Transactions on Computers, vol. 45, no. 12, pp. 1450-1455, Dec. 1996, doi:10.1109/12.545976
Usage of this product signifies your acceptance of the Terms of Use.