A quantitative study of fault tolerance, noise immunity, and generalization ability of MLPs

Neural Computation

Volumn 12, Issue 12, 2000, Pages 2941-2964

  Bernier, J L ^a   Ortega, J ^a   Ros, E ^a   Rojas, I ^a   Prieto, A ^a  

^a NONE

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0039178084     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976600300014782     Document Type: Article

References (24)

1. Alippi, C., Piuri, V., & Sami, M. (1994). Sensitivity to errors in artificial neural networks: A behavioral approach. In Proc. IEEE Int. Symp. on Circuits & Systems (pp. 459-462).
2. Bernier, J. L., Ortega, J., Rodriguez, M. M., Rojas, I., & Prieto, A. (1999a). An accurate measure for multilayer perceptron tolerance to weight deviations. Neural Processing Letters, 10(2), 121-130.
3. Bernier, J. L., Ortega, J., Rojas, I., & Prieto, A. (2000). Improving the tolerance of multilayer perceptrons by minimizing the statistical sensitivity to weight deviations. Neurocomputing, 31, 87-103.
4. Bernier, J. L., Ortega, J., Ros, E., Rojas, I., & Prieto, A. (1999b). A new measurement of noise immunity and generalization ability for MLPs. International Journal of Neural Systems, 9(6), 511-522.
5. Bishop, C. (1995a). Training with noise is equivalent to Tikhonov regularization. Neural Computation, 7(1), 108-116.
6. Bishop, C. M. (1995b). Neural networks for pattern recognition. New York: Oxford University Press.
7. Chiu, C., Mehrotra, K., Mohan, C. K., & Ranka, S. (1994). Modifying training algorithms for improved fault tolerance. Proc. IEEE Int. Conf. on Neural Networks, 1, 333-338.
8. Choi, J. Y., & Choi, C. (1992). Sensitivity analysis of multilayer perceptron with differentiable activation functions, IEEE Trans. on Neural Networks, 3(1), 101-107.
9. Edwards, P. J., & Murray, A. F. (1995). Can deterministic penalty terms model the effects of synaptic weight noise on network fault-tolerance? Int. Journal of Neural Systems, 6(4) 401-416.
10. Edwards, P. J., & Murray, A. F. (1998a). Towards optimally distributed computation. Neural Computation, 10, 997-1015.
11. Edwards, P. J., & Murray, A. F. (1998b). Weight saliency regularisation in augmented networks. In European Symp. on Artificial Neural Networks, ESANN (pp. 261-266).
12. Edwards, P. J., & A. F. Murray. (1998c). Fault tolerance via weight noise in analog VLSI implementations of MLPs - A case study with EPSILON. IEEE Trans. on Circuits and Systems II: Analog and Digital Signal Processing, 45(9), 1255-1262.
13. Hochreiter, H., & Schmidhuber, J. (1997). Flat minima. Neural Computation, 9, 1-42.
14. Krogh, A., & Hertz, J. A. (1992). A simple weight decay improves generalization. In Proc. Neural Information Processing Systems (NIPS) Conference, (pp. 950-957). San Mateo, CA: Morgan Kaufmann.
15. Mao, J., & Jain, A. K. (1993). Regularization techniques in artificial neural networks. World Congress on Neural Networks (pp. 75-79).
16. Minnix, J. I. (1992). Fault tolerance of the backpropagation neural network trained on noisy inputs. Int. Joint Conference on Neural Networks (pp. 75-79).
17. Murray, A. F., & Edwards, P. J. (1994). Synaptic weight noise euring MLP training: Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training. IEEE Transactions on Neural Networks, 5(5), 792-802.
18. Neti, C., Schneider, M. H., & Young, E. D. (1992). Maximally fault tolerant neural networks. IEEE Transactions on Neural Networks, 3(1), 14-23.
19. Pathak, D. S., & Koren, I. (1995). Complete and partial fault tolerance of feed-forward neural nets. IEEE Transactions on Neural Networks, 6(2), 446-456.
20. Prechelt, L. (1994). PROBEN1 - A set of neural network benchmark problems and benchmarking rules (Tech. Rep. No. 21/94). Universitat Karlsruhe, Germany.
21. Segee, B. E., & Carter, M. J. (1994). Comparative fault tolerance of parallel distributed processing networks. IEEE Trans. on Computers, 43(11), 1323-1329.
22. Stevenson, M., Winter, R., & Widrow, B. (1990). Sensitivity of neural networks to weight errors. IEEE Trans. on Neural Networks, 7(1), 71-80.
23. Sudkamp, T., & Hammell, R. (1994). Interpolation, completion, and learning fuzzy rules. IEEE Trans. on Systems, Man & Cybernetics, 24(2), 332-342.
24. Wang, L. (1994). Adaptive fuzzy systems and control: design and stability analysis. Englewood Cliffs, NJ: Prentice Hall.