Abstract
The inherent fault tolerance of artificial neural networks (ANNs) is usually assumed, but several authors have claimed that ANNs are not always fault tolerant and have demonstrated the need to evaluate their robustness by quantitative measures. For this purpose, various alternatives have been proposed. In this paper we show the direct relation between the mean square error (MSE) and the statistical sensitivity to weight deviations, defining a measure of tolerance based on statistical sentitivity that we have called Mean Square Sensitivity (MSS); this allows us to predict accurately the degradation of the MSE when the weight values change and so constitutes a useful parameter for choosing between different configurations of MLPs. The experimental results obtained for different MLPs are shown and demonstrate the validity of our model.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
B.E. Segee, M.J. Carter, “Comparative Fault Tolerance of Parallel Distributed Processing Networks”. IEEE Trans on Computers, vol. 43, no. 11, pp. 1323–1329, Nov 1994.
D.S. Pathak, I. Koren, “Complete and Partial Fault Tolerance of Feedforward Neural Nets”. IEEE Trans. on Neural Networks, vol. 6, no, 2, pp. 446–456, Mar 1995.
M. Stevenson, R. Winter, B. Widrow, “Sensitivity of Neural Networks to Weight Errors”, IEEE Trans. on Neural Networks, vol. 1, no. 1, pp. 71–80, Mar 1990.
C. Alippi, V. Piuri, M. Sami, “Sensitivity to Errors in Artificial Neural Networks: a Behavioral Approach”, in Proc. IEEE Int. Symp. on Circuits & Systems, pp. 459–462, May 1994.
P.J. Edwards, A.F. Murray, “Fault Tolerance via Weight-noise in Analogue VLSI Implementations—a Case Study with EPSILON”. IEEE Proc. on Circuits and Systems II: Analog and Digital Signal Processing, vol. 45, no. 9, pp. 1255–1262. Sep 1998.
P.J. Edwards, A.F. Murray, “Can Determisitic, Penalty Terms Model the Effects of Synaptic Weight Noise on Network Fault-Tolerance?”. Int. Journal of Neural Systems, vol. 6, no. 4, pp. 401–416, 1995.
J.Y. Choi, C. Choi, “Sensitivity Analysis of Multilayer Perceptron with Differentiable Activation Functions”. IEEE Trans on Neural Networks, vol. 3, no. 1, pp. 101–107, Jan 1992.
T. Sudkamp, R. Hammell, “Interpolation, Completion and Learning Fuzzy Rules”. IEEE Trans. on Systems, Man & Cybernetics, vol. 24, no. 2, pp. 332–342, Feb 1994.
L. Wang, Adaptive Fuzzy Systems and Control. Design and Stability Analysis. Englewood Cliffs: Prentice Hall, 1994.
J.L. Bernier, J. Ortega, A. Prieto, “A Modified Backpropagation Algorithm to Tolerate Weight Errors”, Lecture Notes in Computer Science, vol. 1240, pp. 763–771, Springer-Verlag, June 1997.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bernier, J.L., Ortega, J., Rodríguez, M.M., Rojas, I., Prieto, A. (1999). An accurate measure for multilayer perceptron tolerance to additive weight deviations. In: Mira, J., Sánchez-Andrés, J.V. (eds) Engineering Applications of Bio-Inspired Artificial Neural Networks. IWANN 1999. Lecture Notes in Computer Science, vol 1607. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0100553
Download citation
DOI: https://doi.org/10.1007/BFb0100553
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66068-2
Online ISBN: 978-3-540-48772-2
eBook Packages: Springer Book Archive