Abstract
In this paper, based on a stochastic model for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error characteristics of a class of multilayered perceptrons with threshold functions is proposed by using statistical approach. Furthermore, the formula to calculate the robustness of the networks is also given. The result of computer simulation indicates the correctness of the algorithm.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Xiao Benzheng, Jiang Jiguang, Zheng Junli, Sensitivity of multilayered feedforward networks: analysis and reduced learning algorithm. Journal of Tsinghua University, 34(1994)1, 92–98, (in Chinese).
J. Y. Choi, et al., Sensitivity analysis of multilayer perceptron with differentiable action functions, IEEE Trans. on Neural Networks, 3(1992)1, 101–107.
M. Stevenson, R. Winter, B. Widrow, Sensitivity of feedforward neural networks to weight errors. IEEE Trans. on Neural Networks, 1(1990)1, 71–80.
S. W. Piche, Robustness of feedforward neural networks. Proceedings of IJCNN, Baltimore, Maryland, U.S.A.: 1992, II-346–II-351.
S. W. Piche, The selection of weight accuracies for Madalines. IEEE Trans. on Neural Networks, 6(1995)2, 432–445.
Author information
Authors and Affiliations
Additional information
Supported by the National Science Foundation of China and the Doctoral Fund of the State Education Commission of China
About this article
Cite this article
Yang, L., Hu, D. & Luo, Y. Error response and robustness of a class of multilayered perceptrons with threshold functions. J. of Electron.(China) 16, 179–186 (1999). https://doi.org/10.1007/s11767-999-1040-0
Issue Date:
DOI: https://doi.org/10.1007/s11767-999-1040-0