Worst case analysis of weight inaccuracy effects in multilayer perceptrons

IEEE Transactions on Neural Networks

Volumn 10, Issue 2, 1999, Pages 415-418

  Anguita, Davide ^a,b   Ridella, Sandro ^a,b   Rovetta, Stefano ^a  

^a UNIVERSITY OF GENOA   (Italy)

^b IEEE   (Italy)

Author keywords

Interval arithmetic; Multilayer perceptron; Quantization; Robustness

Indexed keywords

COMPUTATIONAL METHODS; DIGITAL ARITHMETIC; ERROR ANALYSIS;

INTERVAL ARITHMETIC; WEIGHT QUANTIZATION EFFECTS; WORST CASE ANALYSIS;

MULTILAYER NEURAL NETWORKS;

EID: 0033100852     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.750571     Document Type: Article

References (14)

1. S. Sakaue, T. Kohda, H. Yamamoto, S. Marano, and Y. Shimeki, "Reduction of required precision bits for back-propagation applied to pattern recognition," IEEE Trans. Neural Networks, vol. 4, pp. 270-275, Mar. 1993.
2. J. Y. Choi and C. H. Choi, "Sensitivity analysis of multilayer perceptrons with differentiable activation functions," IEEE Trans. Neural Networks, vol. 3, pp. 101-107, Jan. 1992.
3. Y. Xie and M. A. Jabri, "Analysis of the effects of quantization in multilayer neural networks using a statistical model," IEEE Trans. Neural Networks, vol. 3, pp. 334-338, Mar. 1992.
4. M. Hoehfeld and S. E. Fahlman, "Learning with limited numerical precision using the cascade-correlation algorithm," IEEE Trans. Neural Networks, vol. 3, pp. 602-611, July 1992.
5. G. Dündar and K. Rose, "The effects of quantization on multilayer neural networks," IEEE Trans. Neural Networks, vol. 6, pp. 1446-1451, Nov. 1995.
6. G. Alefeld and J. Herzberger, Introduction to Interval Computation. Reading, MA: Addison-Wesley, 1986.
7. H. Ishibuchi and H. Tanaka, "An extension of the BP-algorithm to interval input vectors - Learning from numerical data and expert's knowledge," in Proc. 1991 IEEE Int. Joint Conf. Neural Networks, Singapore, Nov. 18-21, 1991, vol. 2, pp. 1588-1593.
8. H. Ishibuchi, H. Tanaka, and H. Okada, "An architecture of neural networks with interval weights and its application to fuzzy regression analysis," Fuzzy Sets Syst, vol. 57, pp. 27-39, 1993.
9. D. Anguita, S. Ridella, S. Rovetta, and R. Zunino, "Limiting the effects of weight errors in feed forward networks using interval arithmetic," in Proc. IEEE Int. Conf. Neural Networks, Washinghton DC, June 3-6, 1996, pp. 414-417.
10. R. B. Kearfott, M. Dawande, K. Du, and C. Hu, "INTLIB: A portable fortran 77 interval standard-function library," ACM Trans. Math. Software, vol. 20, no. 4, pp. 447-459, Dec. 1994.
11. D. Anguita, S. Ridella, S. Rovetta, and R. Zunino, "Incorporating a priori knowledge into neural networks," Electron. Lett., vol. 31, no. 22, pp. 1930-1931, Oct. 1995.
12. D. W. Ruck, S. K. Rogers, M. Kabrisky, M. E. Oxley, and B. W. Suter, "The multilayer perceptron as an approximation to a Bayes optimal discriminant function," IEEE Trans. Neural Networks, vol. 1, Dec. 1990.
13. H. Ishibuchi and A. Miyazaki, "Determination of inspection order for classifying new samples by neural networks," in Proc. IEEE Int. Conf. Neural Networks, Orlando, FL, June 27-29, 1994, vol. 5, pp. 2907-2910.
14. L. P. Lippmann, "An introduction to computing with neural nets," IEEE Acoust., Speech, Signal Processing Mag., vol. 4, pp. 4-22, 1987.