An equivalence between sigmoidal gain scaling and training with noisy (jittered) input data

Proceedings 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, RNNS 1992

Volumn , Issue , 1992, Pages 120-127

  Reed, R ^a   Marks, R J ^a   Oh, S ^a  

^a UNIVERSITY OF WASHINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

NEURAL NETWORKS;

COMPUTATIONAL COSTS; EXPECTED EFFECTS; HIDDEN LAYERS; INPUT DATAS; INPUT NOISE; LINEAR OUTPUT; SIGMOID NONLINEARITY;

JITTER;

EID: 84942839657     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/RNNS.1992.268603     Document Type: Conference Paper

References (9)

1. L. Holmstrom and P. Koistinen. Using additive noise in back-propagation training. IEEE Transactions on Neural Networks, 3(l):24-38, Jan. 1992.
2. P. Koistinen and L. Holmstrom. Kernel regression and backpropagation training with noise. In Proceedings of the International Joint Conference on Neural Networks, pages 367-372, 1991. (Singapore).
3. P. Koistinen and L. Holmstrom. Kernel regression and backpropagation training with noise. In J. E. Moody, S. J. Hanson, R, P. Lippmann, editors, Advances in Neural Information Processing (4), pages 1035-1039, 1992.
4. J. K. Kruschke. Creating local and distributed bottlenecks in hidden layers of back-propagation networks. In D. Touretzky, G. Hinton, T. Sejnowski, editors, Proceedings of the 1988 Connectionist Models Summer School, pages 120-126, Morgan Kaufmann Publishers, 1988.
5. A. Linden and J. Kinder mann. Inversion of multilayer nets. In Proceedings of the International Joint Conference on Neural Networks, page 425, 1989.
6. I. Minnix. Fault tolerance of the backpropagation neural network trained on noisy inputs. In Proceedings of the International Joint Conference on Neural Networks, pages 847-852, 1992. vol. I, (Baltimore).
7. R. Reed, S. Oh, R. J. Marks II. Regulariztion using jittered training data. In Proceedings of the International Joint Conference on Neural Networks, pages 147-152, 1992. vol. Ill, (Baltimore).
8. J. Sietsma and R. J. F. Dow. Creating artificial neural networks that generalize. Neural Networks 4(l):67-69, 1991.
9. A. S. Weigend, D. E. Rumelhart, B. A. Huberman. Generalization by weight-elimination applied to currency exchange rate prediction. In Proceedings of the International Joint Conference on Nevral Networks, page 837, 1991.