A probabilistic model for the fault tolerance of multilayer perceptrons

IEEE Transactions on Neural Networks

Volumn 7, Issue 1, 1996, Pages 201-205

  Merchawi, N S ^a   Kumara, Soundar R T ^b   Das, Chita R ^b  

^a UNIVERSITY OF WINDSOR   (Canada)

^b The Pennsylvania State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ERRORS; LEARNING SYSTEMS; MATHEMATICAL MODELS; PATTERN RECOGNITION; PROBABILITY; VECTORS;

FAULT TOLERANCE; MISCLASSIFICATION; MULTILAYER PERCEPTIONS; PROBABILISTIC MODEL; WEIGHT ERRORS;

NEURAL NETWORKS;

EID: 0029733381     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.478405     Document Type: Article

References (15)

1. J. M. Char, V. Cherkassky, H. Wechsler, and G. L. Zimmerman, "Distributed and fault tolerant computation for retrieval tasks using distributed associative memories," IEEE Trans. Comput., vol. C-37, pp. 484-490, 1988.
2. C. H. Sequin and R. D. Clay, "Fault tolerance in artificial neural networks," in Proc. Int. Joint Conf. Neural Networks, vol. I, San Diego, CA, 1990, pp. 703-708.
3. L. A. Belfore, B. W. Johnson, and J. H. Aylor, "Modeling of fault-tolerance in neural networks," in Proc. Int. Joint Conf. Neural Networks, vol. I, 1990, pp. 325-328.
4. M. Stevenson, R. Winter, and B. Widrow, "Sensitivity of feedforward neural networks to weight errors," IEEE Trans. Neural Networks, vol. 1, pp. 71-80, 1990.
5. J. Y. Choi and C. H. Choi, "Sensitivity of multilayer perceptron with differentiable activation functions," IEEE Trans. Neural Networks, vol. 3, pp. 101-107, 1992.
6. N. S. Orzechowski, S. R. T. Kumara, and C. R. Das, "Performance of multilayer neural networks in binary-to-binary mappings under weight errors," in Proc. 1993 Int. Conf. Neural Networks, vol. III, San Francisco, CA, pp. 1684-1689.
7. G. Bolt, "Fault models for artificial neural networks," in Proc. Int. Joint Conf. Neural Networks, vol. II, Seattle, WA, 1991, pp. 1373-1378.
8. E. D. Sontag, "Remarks on interpolation and recognition using neural nets," in Advances in Neural Information Processing Systems 3. San Mateo, CA: Morgan Kaufman, 1991.
9. T. Petsche and B. W. Dickinson, "Trellis codes, receptive fields, and fault tolerant, self repairing neural networks," IEEE Trans. Neural Networks, vol. 3, pp. 154-166, June 1992.
10. M. Mozer and P. Smolenski, "Skeletonization: A technique for trimming the fat from a network via relevance assessement," Comput. Sci. Dep., Univ. Colorado, Boulder, Tech. Rep. CU-CS-421-89, 1989.
11. B. E. Segee and M. J. Carter, "Fault tolerance of pruned multilayer networks," in Proc. Int. Joint Conf. Neural Networks, vol. II, Seattle, WA, pp. 447-452.
12. D. B. I. Feltham and W. Maly, "Physically realistic fault models for analog CMOS neural networks," IEEE J. Solid State Circuits, pp. 1223-1229, Sep. 1991.
13. C. Neti, M. H. Schneider, and E. D. Young, "Maximally fault tolerant neural networks," IEEE Trans. Neural Networks, vol. 3, no. 1, pp. 14-23, Jan. 1992.
14. M. D. Emmerson, "Fault tolerance and redundancy of neural nets for the classification of acoustical data," in Proc. Int. Conf. Acoust., Speech, Signal Processing (ICASSP), Toronto, Canada, vol. II, May 1991, pp. 1053-1056.
15. D. S. Phatak and I. Koren, "Fault tolerance of feedforward nets for classification tasks," in Proc. Int. Joint Conf. Neural Nets (IJCNN), vol. II, Baltimore, MD, June 1992, pp. 386-391.