A quantified sensitivity measure for multilayer perceptron to input perturbation

Neural Computation

Volumn 15, Issue 1, 2003, Pages 183-212

  Zeng, Xiaoqin ^a   Yeung, Daniel S ^a  

^a HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; EVALUATION; SENSITIVITY AND SPECIFICITY;

EVALUATION STUDIES; NEURAL NETWORKS (COMPUTER); SENSITIVITY AND SPECIFICITY;

EID: 0037264956     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976603321043757     Document Type: Article

References (14)

1. Alippi, C., Piuri, V., & Sami, M. (1995). Sensitivity to errors in artificial neural networks: A behavioral approach. IEEE Transactions on Circuits and Systems-I: Fundamental Theory and Applications, 42(6), 358-361.
2. Cheng, A. Y., & Yeung, D. S. (1999). Sensitivity analysis of neocognitron. IEEE Transactions on System, Man, and Cybernetics - Part C: Applications and Reviews, 29(2), 238-249.
3. Choi, J. Y., & Choi, C. H. (1992). Sensitivity analysis of multilayer perception with differentiable activation functions. IEEE Transactions on Neural Networks, 3(1), 101-107.
4. Engelbrecht, A. P., & Cloete, I. (1999). Incremental learning using sensitivity analysis. In Proceedings of IEEE IJCNN'99 (Vol. 2, pp. 1350-1355). Washington, DC.
5. Engelbrecht, A. P., Fletcher, L., & Cloete, I. (1999). Variance analysis of sensitivity information for pruning multilayer feedforward neural networks. In Proceedings of IEEE IJCNN'99 (Vol. 3, pp. 1829-1833). Washington, DC.
6. Fu, L., & Chen, T. (1993). Sensitivity analysis for input vector in multilayer feedforward neural networks. In Proceedings of IEEE International Conference on Neural Networks (Vol. 1, pp. 215-218). San Francisco.
7. Hashem, S. (1992). Sensitivity analysis for feedforward artificial neural networks with differentiable activation functions. In Proceedings of IJCNN'92 (Vol. 1, pp. 419-424). Baltimore, MD.
8. Lee, Y., & Oh, S. H. (1994). Input noise immunity of multilayer perceptrons. ETRI Journal, 16(1), 35-43.
9. Piché, S. W. (1995). The selection of weight accuracies for madalines. IEEE Transactions on Neural Networks, 6(2), 432-445.
10. Stevenson, M., Winter, R., & Widrow, B. (1990). Sensitivity of feed forward neural networks to weight errors. IEEE Transactions on Neural Networks, 1(1), 71-80.
11. Yeung, D. S., & Sun, X. (2002). Using function approximation to analyze the sensitivity of MLP with antisymmetric squashing activation function. IEEE Transactions on Neural Networks, 13(1), 34-44.
12. Zeng, X. (2001). Output sensitivity of MLPs derived from statistical expectation. Unpublished doctoral dissertation, Hong Kong Polytechnic University.
13. Zeng, X., & Yeung, D. S. (2001). Sensitivity analysis of multilayer perceptron to input and weight perturbations. IEEE Transactions on Neural Networks, 12(6), 1358-1366.
14. Zurada, J. M., Malinowski, A., & Usui, S. (1997). Perturbation method for deleting redundant inputs of perceptron networks. Neurocomputing, 14, 177-193.